At SmartMove Lab, we advance research in autonomous, cooperative, and intelligent systems spanning maritime informatics, mobility, robotics, and data-driven design.
Our expertise lies in autonomy, multi-agent coordination, and multimodal data fusion, enabling resilient and adaptive operations across sea, land, and air.
Equipped with state-of-the-art infrastructure — including autonomous surface and underwater vehicles, sensor networks, digital twins, and advanced simulation environments — we conduct cutting-edge experiments that bridge theory and real-world deployment.
Through active participation in European research initiatives and close collaboration with academia and industry, we co-create technologies that move the world smarter.
Autonomous and Cooperative Systems
Design, control, and coordination of surface and underwater vehicles for resilient, networked operations.
Maritime Informatics and Digital Twins
Data-driven models for situational awareness, decision support, and intelligent maritime operations.
Multimodal Data Fusion and AI
Integration of sensor, environmental, and operational data for adaptive, predictive, and explainable intelligence.
Publications
AegeaNET Syros AIS Dataset for Vessel Traffic Monitoring
Zenodo (CERN European Organization for Nuclear Research), 2026 · Open Access
Abstract
The Automatic Identification System (AIS) is a collaborative monitoring system designed for collision avoidance in maritime navigation. Originally designed for larger vessels, it is now used by different types of vehicles, from tankers to fishing boats and pleasure crafts. Essentially AIS works on the principle that vessels regularly transmit their current position, along with other characteristics like speed-over-ground, heading and a unique identifier. The abundance of AIS messages have allowed for Geographic Information System (GIS) applications and trajectory analytics to model and describe vessel traffic, extract useful patterns and provide predictions on future trends. To that end, the AegeaNET is an open sensor network composed of AIS and ADS-B receivers, strategically deployed throughout the Aegean Sea. AegeaNET is an academic initiative by the Intelligent Transportation Systems Lab (ITS Lab) of the University of the Aegean (Greece). This network facilitates real-time tracking of maritime activity, providing critical data essential for navigation and safety. We present a publicly accessible dataset originating from a receiver on the island of Syros, covering a large area in the middle of the Aegean sea, including most of the Cyclades. The duration of the dataset is a full three (3) month period, from July to September 2024. The positional messages of all vessels are included in a single AIS file, sorted in ascending order using their respective timestamp. An initial cleaning was performed to remove messages with erroneous or missing critical fields. Finally, for the purpose of anonymity, a masking mechanism was applied on top of the vessel identification field (MMSI).
AegeaNET Syros AIS Dataset for Vessel Traffic Monitoring
Zenodo (CERN European Organization for Nuclear Research), 2026 · Open Access
Abstract
The Automatic Identification System (AIS) is a collaborative monitoring system designed for collision avoidance in maritime navigation. Originally designed for larger vessels, it is now used by different types of vehicles, from tankers to fishing boats and pleasure crafts. Essentially AIS works on the principle that vessels regularly transmit their current position, along with other characteristics like speed-over-ground, heading and a unique identifier. The abundance of AIS messages have allowed for Geographic Information System (GIS) applications and trajectory analytics to model and describe vessel traffic, extract useful patterns and provide predictions on future trends. To that end, the AegeaNET is an open sensor network composed of AIS and ADS-B receivers, strategically deployed throughout the Aegean Sea. AegeaNET is an academic initiative by the Intelligent Transportation Systems Lab (ITS Lab) of the University of the Aegean (Greece). This network facilitates real-time tracking of maritime activity, providing critical data essential for navigation and safety. We present a publicly accessible dataset originating from a receiver on the island of Syros, covering a large area in the middle of the Aegean sea, including most of the Cyclades. The duration of the dataset is a full three (3) month period, from July to September 2024. The positional messages of all vessels are included in a single AIS file, sorted in ascending order using their respective timestamp. An initial cleaning was performed to remove messages with erroneous or missing critical fields. Finally, for the purpose of anonymity, a masking mechanism was applied on top of the vessel identification field (MMSI).
H3CPP: Boundary‑Safe Coverage Path Planning for Multi‑USV Operations in Irregular Coastal Environments
IEEE Access, 2026 · Open Access
Abstract
As the need for persistent ocean monitoring grows, fleets of Unmanned Surface Vessels (USVs) are a promising way to survey large marine protected areas with low operational cost. Their effectiveness, however, depends on solving a challenging multi-robot Coverage Path Planning (CPP) problem over complex coastal geometries while strictly respecting safety boundaries. This paper presents H3CPP, a CPP framework that leverages the H3 hierarchical hexagonal grid to discretize arbitrarily shaped marine areas, cluster them into connected subregions, and construct boundary-aware graphs on which Traveling Salesman Problem (TSP) tours are computed. Each H3 cell is sized to match the nominal sensing footprint of a USV, and edges that intersect land or forbidden zones are exponentially penalized, encouraging safe paths that remain within the operational polygon. We evaluate H3CPP on seven benchmark polygonal maps and on a real-world coastal marina using 1–10 USVs. For a single USV in complex, non-convex environments, H3CPP achieves near-complete coverage (coverage ratio ≈ 1.0 of the target area) while avoiding boundary violations that occur with swath and spiral baselines, and reduces path length by up to 10% compared to these methods in the most irregular shapes. In the Syros marina scenario, multi-USV experiments show that H3CPP decreases the total traveled distance by 4–34% (≈ 20% on average) relative to a decomposition-plus-swaths baseline, while maintaining similar coverage and systematically reducing mission makespan as the fleet size increases from 1 to 10 USVs. The proposed framework therefore combines geodesic hexagonal indexing, connectivity-aware clustering, and penalized graph-based TSP planning into a practical CPP solution for USV swarms operating in realistic coastal environments.
H3CPP: Boundary‑Safe Coverage Path Planning for Multi‑USV Operations in Irregular Coastal Environments
Zenodo (CERN European Organization for Nuclear Research), 2026 · Open Access
Abstract
As the need for persistent ocean monitoring grows, fleets of Uncrewed Surface Vessels (USVs) are a promising way to survey large marine protected areas with low operational cost. Their effectiveness, however, depends on solving a challenging multi-robot Coverage Path Planning (CPP) problem over complex coastal geometries while strictly respecting safety boundaries. This paper presents H3CPP, a CPP framework that leverages the H3 hierarchical hexagonal grid to discretize arbitrarily shaped marine areas, cluster them into connected subregions, and construct boundary-aware graphs on which Traveling Salesman Problem (TSP) tours are computed. Each H3 cell is sized to match the nominal sensing footprint of a USV, and edges that intersect land or forbidden zones are exponentially penalized, encouraging safe paths that remain within the operational polygon. We evaluate H3CPP on seven benchmark polygonal maps and on a real-world coastal marina using 1–10 USVs. For a single USV in complex, non-convex environments, H3CPP achieves near-complete coverage (coverage ratio ≈1.0 of the target area) while avoiding boundary violations that occur with swath and spiral baselines, and reduces path length by up to 10% compared to these methods in the most irregular shapes. In the Syros marina scenario, multi-USV experiments show that H3CPP decreases the total traveled distance by 4–34% ( ≈20% on average) relative to a decomposition-plus-swaths baseline, while maintaining similar coverage and systematically reducing mission makespan as the fleet size increases from 1 to 10 USVs. The proposed framework therefore combines geodesic hexagonal indexing, connectivity-aware clustering, and penalized graph-based TSP planning into a practical CPP solution for USV swarms operating in realistic coastal environments.
H3CPP: Boundary‑Safe Coverage Path Planning for Multi‑USV Operations in Irregular Coastal Environments
Zenodo (CERN European Organization for Nuclear Research), 2026 · Open Access
Abstract
As the need for persistent ocean monitoring grows, fleets of Uncrewed Surface Vessels (USVs) are a promising way to survey large marine protected areas with low operational cost. Their effectiveness, however, depends on solving a challenging multi-robot Coverage Path Planning (CPP) problem over complex coastal geometries while strictly respecting safety boundaries. This paper presents H3CPP, a CPP framework that leverages the H3 hierarchical hexagonal grid to discretize arbitrarily shaped marine areas, cluster them into connected subregions, and construct boundary-aware graphs on which Traveling Salesman Problem (TSP) tours are computed. Each H3 cell is sized to match the nominal sensing footprint of a USV, and edges that intersect land or forbidden zones are exponentially penalized, encouraging safe paths that remain within the operational polygon. We evaluate H3CPP on seven benchmark polygonal maps and on a real-world coastal marina using 1–10 USVs. For a single USV in complex, non-convex environments, H3CPP achieves near-complete coverage (coverage ratio ≈1.0 of the target area) while avoiding boundary violations that occur with swath and spiral baselines, and reduces path length by up to 10% compared to these methods in the most irregular shapes. In the Syros marina scenario, multi-USV experiments show that H3CPP decreases the total traveled distance by 4–34% ( ≈20% on average) relative to a decomposition-plus-swaths baseline, while maintaining similar coverage and systematically reducing mission makespan as the fleet size increases from 1 to 10 USVs. The proposed framework therefore combines geodesic hexagonal indexing, connectivity-aware clustering, and penalized graph-based TSP planning into a practical CPP solution for USV swarms operating in realistic coastal environments.
Abstract
The development and evaluation of autonomous maritime vessels rely heavily on data-driven insights from iterative testing and analysis. While initial analyses are often conducted on small experimental datasets to explore key system characteristics, scaling these analyses to large datasets presents significant challenges. In this study, we extend our prior work on visual exploration of small-scale test bed data by proposing approaches to scaling the visual analytics techniques to large datasets. Using AIS data from ferry boats as a proxy for extensive maritime drone operations, we address the challenges of large-scale data exploration over eight days of repetitive ferry movements across a busy strait, simulating conditions suitable for autonomous vessels. Our approach investigates movement patterns, operational stability during repeated trips, and potential collision scenarios. To support such analyses, we propose a general, reusable workflow and a set of practical guidelines for applying visual analytics techniques to large maritime movement datasets. The findings highlight the scalability and adaptability of visual analytics methods, providing valuable tools for analyzing complex maritime datasets and advancing autonomous vessel technologies.
Data‑Driven Trajectory Imputation for Vessel Mobility Analysis
Open MIND, 2026 · Open Access
Abstract
Modeling vessel activity at sea is critical for a wide range of applications, including route planning, transportation logistics, maritime safety, and environmental monitoring. Over the past two decades, the Automatic Identification System (AIS) has enabled real-time monitoring of hundreds of thousands of vessels, generating huge amounts of data daily. One major challenge in using AIS data is the presence of large gaps in vessel trajectories, often caused by coverage limitations or intentional transmission interruptions. These gaps can significantly degrade data quality, resulting in inaccurate or incomplete analysis. State-of-the-art imputation approaches have mainly been devised to tackle gaps in vehicle trajectories, even when the underlying road network is not considered. But the motion patterns of sailing vessels differ substantially, e.g., smooth turns, maneuvering near ports, or navigating in adverse weather conditions. In this application paper, we propose HABIT, a lightweight, configurable H3 Aggregation-Based Imputation framework for vessel Trajectories. This data-driven framework provides a valuable means to impute missing trajectory segments by extracting, analyzing, and indexing motion patterns from historical AIS data. Our empirical study over AIS data across various timeframes, densities, and vessel types reveals that HABIT produces maritime trajectory imputations performing comparably to baseline methods in terms of accuracy, while performing better in terms of latency while accounting for vessel characteristics and their motion patterns.
Data‑Driven Trajectory Imputation for Vessel Mobility Analysis
ArXiv.org, 2026 · Open Access
Abstract
Modeling vessel activity at sea is critical for a wide range of applications, including route planning, transportation logistics, maritime safety, and environmental monitoring. Over the past two decades, the Automatic Identification System (AIS) has enabled real-time monitoring of hundreds of thousands of vessels, generating huge amounts of data daily. One major challenge in using AIS data is the presence of large gaps in vessel trajectories, often caused by coverage limitations or intentional transmission interruptions. These gaps can significantly degrade data quality, resulting in inaccurate or incomplete analysis. State-of-the-art imputation approaches have mainly been devised to tackle gaps in vehicle trajectories, even when the underlying road network is not considered. But the motion patterns of sailing vessels differ substantially, e.g., smooth turns, maneuvering near ports, or navigating in adverse weather conditions. In this application paper, we propose HABIT, a lightweight, configurable H3 Aggregation-Based Imputation framework for vessel Trajectories. This data-driven framework provides a valuable means to impute missing trajectory segments by extracting, analyzing, and indexing motion patterns from historical AIS data. Our empirical study over AIS data across various timeframes, densities, and vessel types reveals that HABIT produces maritime trajectory imputations performing comparably to baseline methods in terms of accuracy, while performing better in terms of latency while accounting for vessel characteristics and their motion patterns.
Context‑Enriched Natural Language Descriptions of Vessel Trajectories
arXiv (Cornell University), 2026 · Open Access
Abstract
We address the problem of transforming raw vessel trajectory data collected from AIS into structured and semantically enriched representations interpretable by humans and directly usable by machine reasoning systems. We propose a context-aware trajectory abstraction framework that segments noisy AIS sequences into distinct trips each consisting of clean, mobility-annotated episodes. Each episode is further enriched with multi-source contextual information, such as nearby geographic entities, offshore navigation features, and weather conditions. Crucially, such representations can support generation of controlled natural language descriptions using LLMs. We empirically examine the quality of such descriptions generated using several LLMs over AIS data along with open contextual features. By increasing semantic density and reducing spatiotemporal complexity, this abstraction can facilitate downstream analytics and enable integration with LLMs for higher-level maritime reasoning tasks.
Context‑Enriched Natural Language Descriptions of Vessel Trajectories
arXiv (Cornell University), 2026 · Open Access
Abstract
We address the problem of transforming raw vessel trajectory data collected from AIS into structured and semantically enriched representations interpretable by humans and directly usable by machine reasoning systems. We propose a context-aware trajectory abstraction framework that segments noisy AIS sequences into distinct trips each consisting of clean, mobility-annotated episodes. Each episode is further enriched with multi-source contextual information, such as nearby geographic entities, offshore navigation features, and weather conditions. Crucially, such representations can support generation of controlled natural language descriptions using LLMs. We empirically examine the quality of such descriptions generated using several LLMs over AIS data along with open contextual features. By increasing semantic density and reducing spatiotemporal complexity, this abstraction can facilitate downstream analytics and enable integration with LLMs for higher-level maritime reasoning tasks.
Diffusion‑based data augmentation for short‑term multivariate energy prediction in data‑scarce scenarios
Open MIND, 2026 · Open Access
Abstract
This study explores diffusion-based generative modeling as a data augmentation strategy to improve forecasting in data-scarce scenarios. Using the ETTh1 multivariate energy dataset, we evaluate point and quantile forecasting across multiple forecasting architectures (XGBoost, LSTM, BiLSTM). Synthetic samples are generated via the Diffusion-TS framework for the neural models only, and incorporated at varying synthetic-to-real ratios. Results show that BiLSTM models benefit substantially in point forecasting, achieving up to a 15.3% improvement (i.e., reduction) in RMSE and 8.1% in MAE, and similarly improve quantile accuracy, while LSTM models degrade under all ratios. Bias-variance analysis reveals that diffusion-based augmentation mainly reduces variance at moderate levels but introduces bias when excessive synthetic data are used.
Vessel Trajectory Data Mining: A Review
IEEE Access, 2025 · 9 citations · Open Access
Abstract
Recent advancements in sensor and tracking technologies have facilitated the real-time tracking of marine vessels as they traverse the oceans. As a result, there is an increasing demand to analyze these datasets to derive insights into vessel movement patterns and to investigate activities occurring within specific spatial and temporal contexts. This survey offers a comprehensive review of contemporary research in trajectory data mining, with a particular focus on maritime applications. The article collects and evaluates state-of-the-art algorithmic approaches and key techniques pertinent to various use case scenarios within this domain. Furthermore, this study provides an in-depth analysis of recent developments in trajectory data mining as applied to the maritime sector, identifying available data sources and conducting a detailed examination of significant applications, including trajectory forecasting, activity recognition, and trajectory clustering.
A Fuzzy Control Strategy for Multi‑Goal Autonomous Robot Navigation
Sensors, 2025 · 9 citations · Open Access
Abstract
This paper addresses the complex problem of multi-goal robot navigation, framed as an NP-hard traveling salesman problem (TSP), in environments with both static and dynamic obstacles. The proposed approach integrates a novel path planning algorithm based on the Bump-Surface concept to optimize the shortest collision-free path among static obstacles, while a Genetic Algorithm (GA) is employed to determine the optimal sequence of goal points. To manage static or dynamic obstacles, two fuzzy controllers are developed: one for real-time path tracking and another for dynamic obstacle avoidance. This dual-controller system enables the robot to adaptively adjust its trajectory while ensuring collision-free navigation in unpredictable environments. The integration of fuzzy logic with TSP-based path planning and real-time dynamic obstacle handling represents a significant advancement in autonomous robot navigation. Simulations conducted in CoppeliaSim validate the effectiveness of the proposed method, demonstrating robust navigation and obstacle avoidance in realistic environments. This work provides a comprehensive framework for solving multi-goal navigation tasks by incorporating TSP optimization with dynamic, real-time path adjustments.
Multi‑Sensor Inferred Trajectories (MUSIT) for Vessel Mobility
2025 · 2 citations · Open Access
Abstract
The abundance of tracking sensors in recent years has led to the generation of high-frequency and high-volume streams of data, including vessel locations, marine observations captured from many sensors (living resources, sea state, weather conditions, etc.). However, there are cases where the trajectory of a moving object has gaps, errors, or is unavailable. Thus, while a vast pool of tracking data is available, these data remain unexplored or underutilized and have the potential to reveal important information. The MUlti-Sensor Inferred Trajectories (MUSIT) project aims to explore and fuse data from all heterogeneous sources to provide detailed information about the location and behavior of a moving object, reduce gaps, and produce a refined and inferred trajectory with minimal errors. The fusion of multi-sensor data is required to fill in the trajectory gaps of moving objects and attach useful semantics to the trajectory. Artificial intelligence algorithms and spatiotem-poral methodologies that can fuse information and infer missing knowledge are also crucial. Furthermore, different representation models from multiple sensors will also be explored. Multi-sensor datasets will be designed and made available to experiment with models, fusion and trajectory inference algorithms, and deduce new knowledge. Therefore, the MUSIT project will tackle these issues in a three-step process: i) data collection and creation, ii) exploitation and utilization of cross-domain representation models for trajectories, and iii) analysis and processing of outcomes to produce information-rich results related to vessel monitoring.
Effective Ship Trajectory Imputation with Multiple Coastal Cameras
2025 · 1 citation · Open Access
Abstract
The ship trajectories collected by the Automatic Identification System (AIS) are widely used in maritime applications. However, a significant issue with AIS data is that large AIS gaps occur. Existing trajectory imputation methods for AIS data have three main limitations: (1) the temporal aspect is ignored; (2) the methods fall short when dealing with complex ship movements; (3) the common-route assumption does not always hold. To overcome these limitations, we propose TrajImpMC, a tracking-based framework that uses polygon-based ship location estimates from multiple cameras to impute large AIS gaps. TrajImpMC combines speed constraints and Kalman filters, and can return imputed trajectories that contain both spatial and temporal information. Extensive experiments are conducted on real datasets. In terms of the quality of the imputed trajectories, TrajImpMC improves the RMSE errors by at least one order of magnitude over two existing state-of-the-art AIS imputation methods. In addition, a visual comparison shows that the imputed trajectories of TrajImpMC align very well with the real ship trajectories during AIS gaps. The code for this paper is available at: https://github.com/songwu0001/TrajImpMC.
Abstract
Unmanned Surface Vessels (USVs) are increasingly being utilized for a wide range of maritime missions, including surveys, area monitoring, search and rescue, and more. However, most USVs are still operated in “remote control” mode, with a human operator navigating them from a nearby station. This is primarily due to the challenges associated with fully autonomous operation, which relies on Artificial Intelligence for navigation and decision-making. Autonomous systems must be capable of continuously perceiving their environment, planning their path, and controlling their movements. One of the key challenges for USVs in such environments is efficient motion planning, especially when navigating complex and dynamically changing marine conditions. This paper presents a unified real-time motion planning approach. Initially, a modified Probabilistic Roadmap was used to generate a network of paths based on static environmental obstacles and the weather conditions. The USV then begins its motion along this path. If the vessel detects a potential collision risk with a moving object (e.g., another vessel), a decision-making algorithm evaluates the collision risk and determines the safest course of action for the USV, incorporating Dubins curves and CORLEGS rules, when it is necessary. The proposed approach is tested and evaluated using randomly generated simulated scenarios.
Constructing a Global Maritime Road Graph for AIS‑Based Route Forecasting and Navigation
2025
Abstract
Ship navigation is not limited to roads and highways, though it is a common practice for the mariner to navigate their vessel through frequently traveled routes for safety. Most groundings occur when a vessel encounters unfamiliar territory or is forced to stray away from its intended route. On the other hand, high traffic areas demonstrate increased risk of vessel collisions and their expensive consequences, including pollution, loss of goods, and fatal accidents. The project presented in this manuscript aims to mitigate the risks of vessel collision and grounding through route suggestion and forecasting methods using dynamic parameters based on historic maritime traffic data. The main focus of this paper is to illustrate the processes of representing maritime traffic through a geometrical roads network, by transforming raw Automatic Identification System messages into a universal weighted graph network. The scope of the network is to generate the most applicable and efficient pathway based on the vessel's specifications and predict the movement of other vessels in the area.
Techniques for interactive visual examination of vessel performance
Big Data Research, 2025 · Open Access
Abstract
• Scalable Visual Analytics for Maritime Data: Proposed approaches to scaling visual analytics techniques from small experimental datasets to large AIS data for maritime vessel movement analysis. • Insights into Vessel Behavior: Revealed valuable insights into both normal and abnormal vessel behaviors through interactive visualization. • Anomaly Detection and Contextualization: Proposed methods for detecting and contextualizing anomalies in vessel movements using clustering, spatial filtering, and spatio-temporal visualization. • Integration with Domain Knowledge : Demonstrated how combining domain knowledge with visual analytics enhances context-aware interpretation and decision-making. • General Workflow and Guidelines: Developed a reusable analysis workflow and a set of practical guidelines for applying visual analytics to large-scale maritime movement data. • Foundation for Real-World Applications: Positioned the techniques as a foundation for human-in-the-loop decision support in future monitoring systems for autonomous maritime operations. The development and evaluation of autonomous maritime vessels rely heavily on data-driven insights from iterative testing and analysis. While initial analyses are often conducted on small experimental datasets to explore key system characteristics, scaling these analyses to large datasets presents significant challenges. In this study, we extend our prior work on visual exploration of small-scale test bed data by proposing approaches to scaling the visual analytics techniques to large datasets. Using AIS data from ferry boats as a proxy for extensive maritime drone operations, we address the challenges of large-scale data exploration over eight days of repetitive ferry movements across a busy strait, simulating conditions suitable for autonomous vessels. Our approach investigates movement patterns, operational stability during repeated trips, and potential collision scenarios. To support such analyses, we propose a general, reusable workflow and a set of practical guidelines for applying visual analytics techniques to large maritime movement datasets. The findings highlight the scalability and adaptability of visual analytics methods, providing valuable tools for analyzing complex maritime datasets and advancing autonomous vessel technologies.
Abstract
CNNs have excelled in computer vision tasks but face challenges on resource-limited edge devices due to high computational and memory demands. Traditional compression methods like pruning and quantization reduce complexity but often require retraining with the original dataset, which may be unavailable due to privacy or storage constraints. This work explores dataset-independent filter pruning, optimizing CNNs without retraining. We evaluate various techniques on a pretrained VGG16 model with CIFAR-10, assessing accuracy, efficiency, and memory impact. Our findings highlight the potential of such methods for AI deployment in privacy-sensitive and real-time applications like mobile computing and autonomous systems.
Abstract
This paper introduces a specialized profiler for energy consumption prediction and proposes a Conceptual Green Orchestration Pipeline that utilizes the profiler as middleware. The system's architecture integrates a standard orchestrator (like Kubernetes) with a local ONNX model registry, targeting edge devices for deployment. Crucially, the profiler demonstrated strong performance, achieving 89% accuracy in selecting the optimal deployment device for resource-intensive models, a significant improvement over the 33.4% accuracy seen with random placement.
Trajectory Mining and Routing: A Cross‑Sectoral Approach
Journal of Marine Science and Engineering, 2024 · 13 citations · Open Access
Abstract
Trajectory data holds pivotal importance in the shipping industry and transcend their significance in various domains, including transportation, health care, tourism, surveillance, and security. In the maritime domain, improved predictions for estimated time of arrival (ETA) and optimal recommendations for alternate routes when the weather conditions deem it necessary can lead to lower costs, reduced emissions, and an increase in the overall efficiency of the industry. To this end, a methodology that yields optimal route recommendations for vessels is presented and evaluated in comparison with real-world vessel trajectories. The proposed approach utilizes historical vessel tracking data to extract maritime traffic patterns and implements an A* search algorithm on top of these patterns. The experimental results demonstrate that the proposed approach can lead to shorter vessel routes compared to another state-of-the-art routing methodology, resulting in cost savings for the maritime industry. This research not only enhances maritime routing but also demonstrates the broader applicability of trajectory mining, offering insights and solutions for diverse industries reliant on trajectory data.
Balanced task allocation and motion planning of a multi‑robot system under fuzzy time windows
Engineering Computations, 2024 · 11 citations
Abstract
Purpose A fleet of mobile robots has been effectively used in various application domains such as industrial plant inspection. This paper proposes a solution to the combined problem of task allocation and motion planning problem for a fleet of mobile robots which are requested to operate in an intelligent industry. More specifically, the robots are requested to serve a set of inspection points within given service time windows. In comparison with the conventional time windows, our problem considers fuzzy time windows to express the decision maker’s satisfaction for visiting an inspection point. Design/methodology/approach The paper develops a unified approach to the combined problem of task allocation and motion planning for a fleet of mobile robots with three objectives: (a) minimizing the total travel cost considering all robots and tasks, (b) balancing fairly the workloads among robots and (c) maximizing the satisfaction grade of the decision maker for receiving the services. The optimization problem is solved by using a novel combination of a Genetic Algorithm with pareto solutions and fuzzy set theory. Findings The computational results illustrate the efficiency and effectiveness of the proposed approach. The experimental analysis leverages the potential for using fuzzy time windows to reflect real situations and respond to demanding situations. Originality/value This paper provides trade-off solutions to a realistic combinatorial multi-objective optimization problem considering concurrently the motion and path planning problem for a fleet of mobile robots with fuzzy time windows.
Validation and Application of the Accu‑Waves Operational Platform for Wave Forecasts at Ports
Journal of Marine Science and Engineering, 2024 · 8 citations · Open Access
Abstract
This paper presents a recently developed Operational Forecast Platform (OFP) for prevailing sea conditions at very important ports worldwide (Accu-Waves). The OFP produces reliable high-resolution predictions of wave characteristics in and around ocean ports. Its goal is to support safer navigation, predict possible port downtime, assist vessel approaching, enhance management of towing services, and bolster secure ship maneuvering in busy ports around the globe. Accu-Waves OFP is based on integrated, high-resolution wave modelling over the continental shelf and in coastal areas that incorporates data from global- and regional-scale, open-sea wave and ocean circulation forecasts as boundary conditions. The coupling, nesting, calibration, and implementation of the models are reported and discussed in this paper, concerning 50 selected areas near and inside significant port basins. The detailed setup of the Accu-Waves OFP and its sub-system services is also provided regarding three-day forecasts at three-hourly intervals. The validation of the wave forecast system against in situ observations from wave buoys in coastal areas of the USA, Belgium, and Spain, as well as other model predictions by established OFPs, seems very promising, with performance skill scores ranging from adequate to very good. An exceptional case of stormy seas under severe marine weather conditions with very high wave maxima (>10 m) in the port of Algeciras is further discussed, confirming the good performance of the Accu-Waves OFP.
EnvClus*: Extracting Common Pathways for Effective Vessel Trajectory Forecasting
IEEE Access, 2024 · 6 citations · Open Access
Abstract
The task of accurately forecasting the trajectory of a vessel, and in general a moving object operating in free space until its destination remains an open challenge. This paper addresses this problem by describing an unsupervised data-driven framework for short and extended horizon forecasts, from the perspectives of data mining and machine learning. We propose a data-driven algorithmic approach named “EnvClus*” that models efficiently historical vessel trajectories at a global scale, forming a mobility graph that depicts the most likely movements among two ports. EnvClus* is able to make tailored route forecasts considering the characteristics of the vessels (i.e. length, draught) along with information regarding the executed trip. The proposed method is able to forecast the most likely realistic and smooth trajectory from a given query position of a vessel (entire route or underway forecasting) towards its destination port. We illustrate the accuracy and effectiveness of our method through a series of scenarios for long and short term forecasting using real world data from around the globe. These experiments indicate an overall improvement of 33% over state-of-the-art and baseline methods; with the benefits of our approach being more apparent when dealing with longer trips from container vessels.
A Fuzzy‑Based System for Autonomous Unmanned Aerial Vehicle Ship Deck Landing
Sensors, 2024 · 6 citations · Open Access
Abstract
This paper introduces a fuzzy logic-based autonomous ship deck landing system for fixed-wing unmanned aerial vehicles (UAVs). The ship is assumed to maintain a constant course and speed. The aim of this fuzzy logic landing model is to simplify the task of landing UAVs on moving ships in challenging maritime conditions, relieving operators from this demanding task. The designed UAV ship deck landing model is based on a fuzzy logic system (FLS), which comprises three interconnected subsystems (speed, lateral motion, and altitude components). Each subsystem consists of three inputs and one output incorporating various fuzzy rules to account for external factors during ship deck landings. Specifically, the FLS receives five inputs: the range from the deck, the relative wind direction and speed, the airspeed, and the UAV's flight altitude. The FLS outputs provide data on the speed of the UAV relative to the ship's velocity, the bank angle (BA), and the angle of descent (AOD) of the UAV. The performance of the designed intelligent ship deck landing system was evaluated using the standard configuration of MATLAB Fuzzy Toolbox.
Optimal robot task scheduling in cluttered environments considering mechanical advantage
Robotica, 2024 · 4 citations · Open Access
Abstract
Abstract In various industrial robotic applications, the effective traversal of a manipulator amidst obstacles and its ability to reach specific task-points are imperative for the execution of predefined tasks. In certain scenarios, the sequence in which the manipulator reaches these task-points significantly impacts the overall cycle time required for task completion. Moreover, some tasks necessitate significant force exertion at the end-effector. Therefore, establishing an optimal sequence for the task-points reached by the end-effector’s tip is crucial for enhancing robot performance, ensuring collision-free motion and maintaining high-force application at the end-effector’s tip. To maximize the manipulator’s manipulability, which serves as a performance index for assessing its force capability, we aim to establish an optimal collision-free task sequence considering higher mechanical advantage. Three optimization criteria are considered: the cycle time, collision avoidance and the manipulability index. Optimization is accomplished using a genetic algorithm coupled with the Bump-Surface concept for collision avoidance. The effectiveness of this approach is confirmed through simulation experiments conducted in 2D and 3D environments with obstacles employing both redundant and non-redundant robots.
Abstract
Maritime mobility monitoring can be achieved through remote sensing and self-reporting systems, which produce large datasets enabling the extraction of valuable information on global shipping trends. This extraction can be defined as a data mining task of transforming huge amounts of geospatial data, into a descriptive and compact data model, that can then be used for identifying the underlying relationships or patterns. In this work, we present a brief overview of mobility data mining as applied to the maritime use case. We highlight its unique aspects, identify six major data mining tasks, discuss indicative approaches found in literature, and address some challenges for future work.
The Aegean Ro‑Boat Race: A Regatta to Accelerate Innovation in Marine Robotics and Autonomous Vessels
IEEE Aerospace and Electronic Systems Magazine, 2024 · 3 citations · Open Access
Abstract
The “Aegean Ro-boat Race” is an international university level competition, challenging teams to design and develop innovative autonomous robotic systems that can perform at sea in real-world conditions. This is an innovation race among universities, but with the support of industry, which merges visionary thinking from different fields to solve problems in marine robotics and autonomous systems. Topics to be judged include autonomous behavior, sensor fusion, object detection, path planning, reliability, and overall innovation. This year's competition took place in Syros, Greece, on 12 July 2023, and consisted of three mission tasks, focused on high speed and performance, collision avoidance, and endurance. This article details what happened during the first “Aegean Ro-boat Race,” presents the results of this unique learning experience, and discusses advances achieved in terms of innovation.
Optimizing Resource Allocation in the Edge: A Minimum Weighted Vertex Cover Approach
2024 · 2 citations · Open Access
Abstract
The transition from Cloud Computing to a Cloud-Edge continuum introduces novel opportunities and challenges for data-intensive and interactive Next Generation applications. Strategies that were effective in the Cloud environment now necessitate reconsideration to adapt to the Edge's distributed, dynamic, and heterogeneous ecosystem. Proactively planning the placement of application images becomes crucial to minimize image transfer time, align with the dynamic nature of the system, and meet the strict demands of applications. In this regard, this paper proposes an empirical experimental analysis, by comparing the results of different placement strategies and various network topologies. In particular, we model the problem of proactive placement of application images as a Minimum Weighted Vertex Cover problem. Our results demonstrate that the Greedy approach seems to offer the optimal tradeoff with respect to the number of allocated images and execution time.
Uncertainty‑Aware Ship Location Estimation using Multiple Cameras in Coastal Areas
2024 · 1 citation · Open Access
Abstract
Recent advances, especially in deep learning, allow to effectively detect ship targets in surveillance videos. However, the translation of these detections to the real-world locations of ships has not been sufficiently explored. The common approach in the literature is using a transformation matrix to convert a pixel to a real-world coordinate. However, this approach has three shortcomings: first, a set of reference point pairs has to be manually prepared to establish the matrix; second, the matrix always maps a pixel to the same real-world coordinate, ignoring that there is no one-to-one correspondence between discrete pixel coordinates and continuous real-world coordinates; third, this approach can only work with one camera. In light of this, we propose a technique PixelToRegion that explicitly takes into account the uncertainty in coordinate conversion by mapping each pixel to a spatial polygon. Next, we propose a new algorithm MCbSLE that can estimate ship locations using pixel sets from multiple cameras. The precision of location estimation by MCbSLE is enhanced through spatial intersection between polygons from different cameras. Experiments are conducted under 16 carefully designed multi-camera settings to evaluate MCbSLE w.r.t. four factors: different ports, the number of cameras, the distance between cameras, and camera headings. Results on one-day ship trajectory data show that (1) an 79.8% accuracy in the number of coordinates can be achieved by MCbSLE when there are no more than 10 ships in camera views; (2) using multiple cameras can improve the precision of location estimation by one order of magnitude compared with using one camera.
Efficient Task Allocation and Path Planning for Unmanned Surface Vehicle in Supply Chain
2024 · 1 citation
Abstract
The rapid development of autonomous transportation systems is currently motivating several research initiatives. This paper presents an approach for efficient task allocation and path planning for an Unmanned Surface Vehicle (USV) which is requested to transfer products in an island group in the Aegean Sea. The proposed approach is based on a bi-level scheduling methodology, in the upper level, considering the weather conditions and the geographical characteristics of the area we create a square (from/to) travel time matrix. In the lower level, considering travel times we develop a Genetic Algorithm to achieve the USV’s task allocation and path planning. Experimental results demonstrate the effectiveness of our approach in guiding the USV’s to efficiently accomplish short sea container transshipment in the island group of Cyclades.
Edge‑driven Docker registry: facilitating XR application deployment
Computing, 2024 · 1 citation
On Vessel Location Forecasting and the Effect of Federated Learning
arXiv (Cornell University), 2024 · Open Access
Abstract
The wide spread of Automatic Identification System (AIS) has motivated several maritime analytics operations. Vessel Location Forecasting (VLF) is one of the most critical operations for maritime awareness. However, accurate VLF is a challenging problem due to the complexity and dynamic nature of maritime traffic conditions. Furthermore, as privacy concerns and restrictions have grown, training data has become increasingly fragmented, resulting in dispersed databases of several isolated data silos among different organizations, which in turn decreases the quality of learning models. In this paper, we propose an efficient VLF solution based on LSTM neural networks, in two variants, namely Nautilus and FedNautilus for the centralized and the federated learning approach, respectively. We also demonstrate the superiority of the centralized approach with respect to current state of the art and discuss the advantages and disadvantages of the federated against the centralized approach.
Collection: The Aegean Ro‑Boat Race 2023
IEEE data descriptions., 2024 · Open Access
Abstract
In this article, we introduce a publicly available real-world dataset collected during the Aegean Ro-Boat Race 2023, which took place at the University of the Aegean in Syros, Greece. The Aegean Ro-Boat Race represents an international competition at the university level, challenging teams to innovate and develop autonomous marine robotic systems capable of performing in unknown dynamic maritime environments under real-world conditions. The 2023 competition featured three primary mission tasks, each designed to test different aspects of the robotic systems: 1) high-speed performance for evaluating the speed and agility of the autonomous vessels; 2) collision avoidance for assessing the systems’ ability to detect and avoid obstacles in real-time; and 3) endurance for testing the operational longevity and efficiency of the robotic systems over extended periods. In total, seven teams registered for the competition, with five of them being from Greece and two from the countries of Portugal and Latvia. Due to several technical difficulties, three vessels were able to complete all races, and data were recorded during their entire participation. The spatiotemporal data for the “Aegean Ro-Boat Race” was gathered through an onboard data logging system that continuously monitored various sensors, including global positioning system (GPS), for all vessels during the entire competition. The dataset includes positional reports from the vessels during all three races (totaling over 6500 records), the positions of the external track and obstacle buoys, together with a file regarding the weather conditions during the race day. IEEE SOCIETY/COUNCIL Computer Society (CS), Aerospace and Electronic Systems Society (AESS), Signal Processing Society (SPS), Oceanic Engineering Society (OES), Intelligent Transportation Systems Society (ITSS) DATA TYPE/LOCATION CSV; Syros, Greece DATA DOI/PID 10.5281/zenodo.13318421
A data mining approach for analysing globalshipping patterns.
Research Square, 2024 · Open Access
A Study on the Performance of Distributed Storage Systems in Edge Computing Environments
2024 · Open Access
Abstract
Edge computing presents a promising paradigm for the management and processing of the vast volumes of data generated by Internet of Things (IoT) devices. By merging cloud services with decentralized processing at the edge of the network, edge computing optimizes resource utilization while mitigating communication overhead and data transfer delays. Despite advancements, there are issues regarding cloud/edge-based application requirements. A distributed edge storage solution is crucial, ensuring data proximity, minimizing network congestion, and adapting to changing demands. Nevertheless, implementing or selecting an efficient edge-enabled storage system presents numerous challenges due to the distributed and heterogeneous nature of the edge, as well as its limited resource capabilities. Hence, it is essential for the research community to actively contribute towards clarifying the objectives and delineating the strengths and weaknesses of different storage solutions. This work presents an overview and performance analysis of three storage solutions in the edge computing context, namely MinIO, IPFS, and BigchainDB. The evaluation considers a set of Quality of Service (QoS) and resource utilization metrics. The systems are deployed on a cluster of four Raspberry Pis, which function as a network of edge devices. The results demonstrate the superiority of IPFS and provide insights into the performance of the evaluated storage systems for edge deployments.
Abstract
Fish piracy remains widespread globally despite national and international efforts. Experts estimate it accounts for about 20% of the total seafood catch worldwide. Technology is playing a key role in detecting illegal fishing, with satellite imagery and sensors being used to track vessels and monitor fishing practices. Since fishing boats broadcast their positions using a vessel tracking system, this data can be processed to detect illegal activity. This study focuses on classifying fishing vessel trajectories using only positional data. A novel trajectory representation and a Convolutional Neural Network is employed, showing promising results compared to traditional methods.
Efficient ship weather routing using probabilistic roadmaps
Ocean Engineering, 2023 · 38 citations
The fuzzy human‑robot collaboration assembly line balancing problem
Computers & Industrial Engineering, 2023 · 27 citations
Graph neural networks for representing multivariate resource usage: A multiplayer mobile gaming case‑study
International Journal of Information Management Data Insights, 2023 · 25 citations · Open Access
Abstract
The emergence of Multiplayer Mobile Gaming (MMG) applications is intertwined with a plethora of Quality of Service and Quality of Experience requirements. Resource usage prediction can provide valuable insights into the corresponding orchestration and management process in the form of several proactive functionalities in resource scaling, service migration, task offloading and scheduling. These processes are crucial in the Cloud and Edge environments exploited by MMG applications. Thus, producing accurate resource usage predictions concerning these types of applications is of paramount importance. To that end, we propose a resource usage representation paradigm based on Graph Neural Networks (GNNs). The novelty of this approach is based on the process of leveraging the dependencies that exist among the various types of computational resources. Furthermore, we expand upon this representation approach to develop a GNN-based Encoder-Decoder model that caters to the complexities of resource usage and can provide multi-step resource usage predictions. This model is compared against numerous well-established Encoder-Decoder and Deep Learning prediction models to assess its efficiency. Finally, the proposed model is incorporated in a proactive Horizontal Autoscaling solution that manages to outperform a standard reactive Horizontal Autoscaling approach in the context of a large-scale simulation, in terms of various performance metrics, while keeping the volume of the required computational resources to a minimum. The findings of this work showcase the importance of developing novel approaches in order to represent resource usage and the numerous benefits in the context of application performance and resource consumption that may derive from such scientific endeavors.
Monitoring of Critical Undersea Infrastructures: The Nord Stream and Other Recent Case Studies
IEEE Aerospace and Electronic Systems Magazine, 2023 · 21 citations
Abstract
The explosions on 26 September 2022, which damaged the Nord Stream gas pipelines, have highlighted the need and urgency of improving the resilience of critical undersea infrastructures (CUIs). Comprising gas pipelines and power and communication cables, these connect countries worldwide and are critical for the global economy and stability. An attack targeting multiple of such infrastructures could potentially cause significant damage and greatly affect various aspects of daily life. Due to the increasing number of CUIs, existing underwater surveillance solutions, such as autonomous underwater vehicles or remotely operated vehicles, are not adequate enough to ensure thorough monitoring. We show that the combination of information from both underwater and above-water surveillance sensors enables achieving seabed-to-space situational awareness (S3A), mainly thanks to artificial intelligence and information fusion methodologies. These are designed to process immense volumes of information, fused from a variety of sources and generated from monitoring a very large number of assets. The learned knowledge can be used to anticipate future behaviors, identify threats, and determine critical situations concerning CUIs. To illustrate the capabilities and importance of S3A, we consider three events that occurred in the second half of 2022: the aforementioned Nord Stream explosions, the cutoff of the underwater communication cable SHEFA-2 connecting the Shetland Islands and the U.K. mainland, and the suspicious activity of a large vessel in the Adriatic Sea. Specifically, we provide analyses of the available data, from automatic identification system and satellite data, integrated with possible contextual information, e.g., bathymetry, patterns-of-life, weather conditions, and human intelligence.
TraClets: A trajectory representation and classification library
SoftwareX, 2023 · 10 citations · Open Access
Abstract
Due to the advent of new mobile devices and tracking sensors in recent years, huge amounts of data are being produced every day. Therefore, novel methodologies need to emerge that dive through this vast sea of information and generate insights and meaningful information. To this end, researchers have developed several trajectory classification algorithms over the years that are able to annotate tracking data. Similarly, we propose a software that exploits image representations of trajectories, called TraClets, in order to classify trajectories in an intuitive to the human way, through computer vision techniques. The proposed software has been evaluated in three real-world datasets and is currently used in a live vessel tracking terrestrial base station.
An intelligent management system for relocating semi‑autonomous shared vehicles
Transportation Planning and Technology, 2023 · 7 citations
Abstract
Car sharing services with Semi-Autonomous Electric Vehicles (SAEVs) represent an emerging transportation scheme which may comprise an important link in the green mobility chain for smart city operations. The main goal of the present paper is to introduce and develop an intelligent management system for the efficient relocation of SAEVs within the urban car-sharing context. A novel relocation strategy is analyzed regarding the upcoming technology of platooning. Considering real urban road networks for SAEVs, routing decisions are assessed based on the traffic conditions and energy efficiency. Fuzzy logic concepts are incorporated into the proposed system to simulate the uncertainty related to the roads’ traffic conditions. The problem addressed in this work is a constrained optimization problem. Solutions to the addressed problem are yielded using a Genetic Algorithm (GA) in accordance with the fuzzy logic module. Simulated experiments over the city of Patras (Greece) show the efficiency of the developed approach.
Saliency‑Aided Online RPCA for Moving Target Detection in Infrared Maritime Scenarios
Sensors, 2023 · 6 citations · Open Access
Abstract
Moving target detection (MTD) is a crucial task in computer vision applications. In this paper, we investigate the problem of detecting moving targets in infrared (IR) surveillance video sequences captured using a steady camera in a maritime setting. For this purpose, we employ robust principal component analysis (RPCA), which is an improvement of principal component analysis (PCA) that separates an input matrix into the following two matrices: a low-rank matrix that is representative, in our case study, of the slowly changing background, and a sparse matrix that is representative of the foreground. RPCA is usually implemented in a non-causal batch form. To pursue a real-time application, we tested an online implementation, which, unfortunately, was affected by the presence of the target in the scene during the initialization phase. Therefore, we improved the robustness by implementing a saliency-based strategy. The advantages offered by the resulting technique, which we called "saliency-aided online moving window RPCA" (S-OMW-RPCA) are the following: RPCA is implemented online; along with the temporal features exploited by RPCA, the spatial features are also taken into consideration by using a saliency filter; the results are robust against the condition of the scene during the initialization. Finally, we compare the performance of the proposed technique in terms of precision, recall, and execution time with that of an online RPCA, thus, showing the effectiveness of the saliency-based approach.
Building an autonomous boat: a multidisciplinary design engineering approach
2023 · 6 citations · Open Access
Abstract
This paper describes the work completed for the design and development of a prototype autonomous boat (or autonomous surface vessel). The goal of the boat was to compete in a number of races, which were part of the International Aegean Ro-Boat Races, sailing completely autonomously, that is using onboard data sensors and processing, so as to navigate safely, without any input from shore. It outlines the path to development from initial concept and requirements, to detailed design of the physical and software systems, complete to the first sea trials. We describe how the boat performs the entire Sense-Think-Act paradigm on board, at sea, while using occupancy grids to safely navigate and avoid collisions. The boat perceives its surroundings through a collection of low-cost sensors (such as cameras, LIDAR, etc) that are used to map the environment. Following this, path and trajectory planning algorithms, navigate the boat safely and free of collisions towards its destination. Overall this work demonstrates the potential of using open source software and off the shelf components to build a cost effective autonomous vessel with advanced capabilities. Although the design purpose and requirements of this boat were very specific, the basic design of the boat can be adapted to different needs, environments and applications. The system has been extensively tested in various environments, including open water testing, and the results demonstrate its capacity to navigate safely and efficiently.
SERobWaS: a support environment for a robot‑based warehousing system
The International Journal of Advanced Manufacturing Technology, 2023 · 6 citations
The Big Picture: An Improved Method for Mapping Shipping Activities
Remote Sensing, 2023 · 4 citations · Open Access
Abstract
Density maps support a bird’s eye view of vessel traffic, through providing an overview of vessel behavior, either at a regional or global scale in a given timeframe. However, any inaccuracies in the underlying data, due to sensor noise or other factors, evidently lead to erroneous interpretations and misleading visualizations. In this work, we propose a novel algorithmic framework for generating highly accurate density maps of shipping activities, from incomplete data collected by the Automatic Identification System (AIS). The complete framework involves a number of computational steps for (1) cleaning and filtering AIS data, (2) improving the quality of the input dataset (through trajectory reconstruction and satellite image analysis) and (3) computing and visualizing the subsequent vessel traffic as density maps. The framework describes an end-to-end implementation pipeline for a real world system, capable of addressing several of the underlying issues of AIS datasets. Real-world data are used to demonstrate the effectiveness of our framework. These experiments show that our trajectory reconstruction method results in significant improvements up to 15% and 26% for temporal gaps of 3–6 and 6–24 h, respectively, in comparison to the baseline methodology. Additionally, a use case in European waters highlights our capability of detecting “dark vessels”, i.e., vessel positions not present in the AIS data.
Correction to: SERobWaS: a support environment for a robot‑based warehousing system
The International Journal of Advanced Manufacturing Technology, 2023 · 3 citations · Open Access
Multi‑Service Demand Forecasting Using Graph Neural Networks
2023 · 3 citations
Abstract
Accurate service demand forecasting is crucial towards achieving effective resource allocation and service orchestration. However, existing solutions require separate prediction models for each service, which consumes significant computation resources. In this paper, we propose a novel approach that introduces a global prediction model capable of generating accurate multi-step predictions involving multiple services and that can potentially leveraged for facilitating proactive strategies for orchestrating multiple services. The proposed model is based on an Encoder-Decoder architecture that utilizes Graph Neural Networks (GNNs) to capture interdependencies among input variables and their trends. By iteratively updating graph node representations, our model effectively incorporates historical trends and potential dependencies. Furthermore, the incorporation of GNNs into the Encoder-Decoder architecture enables the proposed approach to leverage the correlations among input variables, thus making it suitable for multivariate forecasting. Experimental results demonstrate the superiority of the proposed approach in terms of accurately conducting multi-step multiservice demand predictions, when compared against numerous contemporary deep learning models.
Scalable framework for AIS data exploration through effective density visualizations
2023 · 2 citations · Open Access
Abstract
With tens of thousands of vessels around the globe transmitting their positions daily, interpreting such large volumes of data is more than a challenging task. Through the Automatic Identification System (AIS), introduced in 2002, the coordinates and status of the vessels are continuously reported, with a transmission frequency ranging from 3 minutes down to a few seconds depending on their speed. Today, these millions of AIS messages and dozens of gigabytes of new data produced daily allow monitoring the movement of passenger or commercial vessels, as well as more complex activities like fishing and search-and-rescue operations. Studying the properties of AIS data and modeling vessel behavior has been the subject of numerous works the past few years. These attempts to describe vessel activity aim at a better understanding of their movement, often through the use of advanced mechanisms for capturing specific types of events. Although such approaches have been proven effective for a variety of scenarios, the resulting models are not easily comprehensible by the user, with notable examples being the trained neural networks or many of the classification models. Moreover, although recently there have been a few proposed works for extracting common vessel routes through historic data analysis, the end results by design do not provide the full picture regarding all movement in the area, solely including representative pathways. In order to overcome these issues, easily interpretable visualizations of movement at sea would provide a clear understanding of vessel behavior and the occurring trends. An experimental analysis that highlights the utility of vessel density maps in marine activities was presented in 2015 by Shelmerdine [1], with indicative experiments performed on a limited area around Shetland. A more scenario-specific analysis by Vespe et al. [2] focuses on visualizing the impact of piracy events over transport, while Chen et al. [3] attempted to also include the reported speed and course information from the AIS data in their maps. Furthermore, a framework for creating heat maps through a parallel Kernel Density Estimation (KDE) was proposed recently [4]. In their approach, Huang et al. present an efficient pipeline for trajectory compression and visualization in the context of Internet of Things (IoT) applications, with their solution relying on GPU-related accelerations. In this work, we extend our own MT-AIS-Toolbox [5], and present a scalable and effective tool for handling AIS datasets and visualizing vessel activity. For the purpose of creating an efficient and easily configurable solution, a state-of-the-art framework for scalable data processing, namely PySpark, is utilized. The proposed tool is able to manage large volumes of raw AIS messages and produce effective density maps for vessel movement according to the user configurations and needs. Our approach is split into two separate steps: first a dedicated mechanism is responsible for removing unnecessary or erroneous records and limiting the dataset within the spatio-temporal constraints of each use case. Then, the density of the area of interest is extracted, according to the selected metric, and ready-for-display density maps, that depict the vessel traffic, are generated. A few options for density metrics (such as number of different vessels that passed, the time spent at each area, the number of times vessels passed over an area etc.) are provided, with the user also being able to easily define a function that is best suited for their desired results. Additionally, options for comparing and combining different density maps are also included for a more complete analysis. Indicative experiments on a large real-world trajectory dataset were conducted, highlighting the performance capabilities of the proposed framework, in terms of execution time. Finally, as an application, the proposed extended tool has been utilized for data exploration and preparation during the training of machine learning models, as part of an EU-funded project for the digitalization of vessel behavior (i.e. VesselAI).
Abstract
Discovering shipping networks is a major step toward unveiling the characteristics of port connections. Because of the dynamic nature of shipping, the most reliable method of extracting such insights is by studying the movement of vessels. Through the Automatic Identification System (AIS), large amounts of mobility data are available daily. We describe a method that processes these datasets, at a regional level, and produces density maps through a novel metric that considers the shipping attributes of the traveling vessels and captures the capacity and importance of shipping routes. The proposed approach, published as a configurable open-source tool, is capable of producing data-driven insights regarding vessel movement and shipping trends solely using the raw vessel positions.
Abstract
Monitoring vessel traffic on a global scale is a complex and challenging task. The large number of moving vessels and the complexity of monitoring their position and forecasting their route in real-time require novel, advanced and highly scalable big-data mechanisms. In this work a digital twin for constant maritime situational awareness on a global scale is presented. The described multi-layered system is able to visualize maritime traffic in real-time, based on data from the Automatic Identification System (AIS), while also providing forecasts of future movement based on machine learning and deep learning techniques. The system is validated using real streaming AIS data from around the globe to demonstrate its performance, scalability and parallelization efficiency.
A real‑time trajectory classification module
2023 · 2 citations · Open Access
Abstract
Nowadays, massive volumes of mobility data are being generated from thousands of tracking devices, such as GPS devices, RFID sensors, location-based services, satellites, and wireless communication technologies. This phenomenon can be strongly observed in the maritime domain and as a result, today's industry is flooded with tracking data originating from vessels across the globe that transmit their position at frequent intervals. Automated methodologies able to extract meaningful information and identify mobility patterns from such tracking data are of utmost importance since they can reveal abnormal or illegal vessel activities in due time. To this end, we present a demo of a trajectory classification methodology that is able to classify vessels' trajectories into activities that the vessels are engaged in from AIS data streams in real-time. The goal is to provide maritime authorities with a visualization tool and an API of the vessel trajectories and their activities in real-time. The trajectory classification methodology that is used in this demo achieves a classification performance of over 95%.
A Hybrid Method for Vessel Detection in High‑Resolution Satellite Imagery
2023 · 1 citation
Abstract
In this paper, we introduce an approach that combines both image processing techniques and neural networks to perform vessel detection in satellite imagery. We use image processing as a pre-processing step that filters out image areas (tiles) that do not contain vessels (e.g., sea and land tiles) in order to reduce the amount of data that needs to be provided as input to a neural network that eventually performs the vessel detection task, thus improving performance by reducing unnecessary classification tasks. We evaluate the benefit from using both image processing and machine learning in terms of accuracy and performance.
Monitoring of Underwater Critical Infrastructures: the Nord Stream and Other Recent Case Studies
arXiv (Cornell University), 2023 · 1 citation · Open Access
Abstract
The explosions on September 26th, 2022, which damaged the gas pipelines of Nord Stream 1 and Nord Stream 2, have highlighted the need and urgency of improving the resilience of Underwater Critical Infrastructures (UCIs). Comprising gas pipelines and power and communication cables, these connect countries worldwide and are critical for the global economy and stability. An attack targeting multiple of such infrastructures simultaneously could potentially cause significant damage and greatly affect various aspects of daily life. Due to the increasing number and continuous deployment of UCIs, existing underwater surveillance solutions, such as Autonomous Underwater Vehicles (AUVs) or Remotely Operated Vehicles (ROVs), are not adequate enough to ensure thorough monitoring. We show that the combination of information from both underwater and above-water surveillance sensors enables achieving Seabed-to-Space Situational Awareness (S3A), mainly thanks to Artificial Intelligence (AI) and Information Fusion (IF) methodologies. These are designed to process immense volumes of information, fused from a variety of sources and generated from monitoring a very large number of assets on a daily basis. The learned knowledge can be used to anticipate future behaviors, identify threats, and determine critical situations concerning UCIs. To illustrate the capabilities and importance of S3A, we consider three events that occurred in the second half of 2022: the aforementioned Nord Stream explosions, the cutoff of the underwater communication cable SHEFA-2 connecting the Shetland Islands and the UK mainland, and the suspicious activity of a large vessel in the Adriatic Sea. Specifically, we provide analyses of the available data, from Automatic Identification System (AIS) and satellite data, integrated with possible contextual information, e.g., bathymetry, weather conditions, and human intelligence.
A Fuzzy‑based System for Autonomous UAV Ship Deck Landing
Preprints.org, 2023 · 1 citation · Open Access
Abstract
This paper introduces a fuzzy logic-based autonomous ship-deck landing system for fixed-wing Unmanned Aerial Vehicles (UAVs). The ship is assumed to maintain a constant course and speed. The aim of this fuzzy logic landing model is to simplify the task of landing UAVs on moving ships in challenging maritime conditions, relieving operators from this demanding task. The designed UAV ship-deck landing model is based on a fuzzy system comprised of three interconnected subsystems. Each subsystem consists of three inputs and one output incorporating various fuzzy rules to account for external factors during ship-deck landings. Specifically, the Fuzzy Logic System (FLS) takes inputs such as the airspeed, the relative wind direction and speed, the range from the deck and the UAV's flight altitude. The FLS outputs provide data on the Speed of the UAV relative to the ship’s velocity, the Bank Angle, and the Angle of Descent of the UAV. The performance of the designed intelligent ship-deck landing system is evaluated using the standard configuration of MATLAB Fuzzy Toolbox.
Balanced task allocation and motion planning of a multi‑robot system under fuzzy time windows
Research Square, 2023 · Open Access
An evaluation of time series forecasting models on water consumption data: A case study of Greece
arXiv (Cornell University), 2023 · Open Access
Abstract
In recent years, the increased urbanization and industrialization has led to a rising water demand and resources, thus increasing the gap between demand and supply. Proper water distribution and forecasting of water consumption are key factors in mitigating the imbalance of supply and demand by improving operations, planning and management of water resources. To this end, in this paper, several well-known forecasting algorithms are evaluated over time series, water consumption data from Greece, a country with diverse socio-economic and urbanization issues. The forecasting algorithms are evaluated on a real-world dataset provided by the Water Supply and Sewerage Company of Greece revealing key insights about each algorithm and its use.
Synthetic AIS Dataset of Vessel Proximity Events
Zenodo (CERN European Organization for Nuclear Research), 2023 · Open Access
Abstract
The Automatic Identification System (AIS) allows vessels to share identification, characteristics, and location data through self-reporting. This information is periodically broadcast and can be received by other vessels with AIS transceivers, as well as ground or satellite sensors. Since the International Maritime Organisation (IMO) mandated AIS for vessels above 300 gross tonnage, extensive datasets have emerged, becoming a valuable resource for maritime intelligence. Maritime collisions occur when two vessels collide or when a vessel collides with a floating or stationary object, such as an iceberg. Maritime collisions hold significant importance in the realm of marine accidents for several reasons: Injuries and fatalities of vessel crew members and passengers. Environmental effects, especially in cases involving large tanker ships and oil spills. Direct and indirect economic losses on local communities near the accident area. Adverse financial consequences for ship owners, insurance companies and cargo owners including vessel loss and penalties. As sea routes become more congested and vessel speeds increase, the likelihood of significant accidents during a ship's operational life rises. The increasing congestion on sea lanes elevates the probability of accidents and especially collisions between vessels. The development of solutions and models for the analysis, early detection and mitigation of vessel collision events is a significant step towards ensuring future maritime safety. In this context, a synthetic vessel proximity event dataset is created using real vessel AIS messages. The synthetic dataset of trajectories with reconstructed timestamps is generated so that a pair of trajectories reach simultaneously their intersection point, simulating an unintended proximity event (collision close call). The dataset aims to provide a basis for the development of methods for the detection and mitigation of maritime collisions and proximity events, as well as the study and training of vessel crews in simulator environments. The dataset consists of 4658 samples/AIS messages of 213 unique vessels from the Aegean Sea. The steps that were followed to create the collision dataset are: Given 2 vessels X (vessel_id1) and Y (vessel_id2) with their current known location (LATITUDE [lat], LONGITUDE [lon]): Check if the trajectories of vessels X and Y are spatially intersecting. If the trajectories of vessels X and Y are intersecting, then align temporally the timestamp of vessel Y at the intersect point according to X’s timestamp at the intersect point. The temporal alignment is performed so the spatial intersection (nearest proximity point) occurs at the same time for both vessels. Also for each vessel pair the timestamp of the proximity event is different from a proximity event that occurs later so that different vessel trajectory pairs do not overlap temporarily. Two csv files are provided. vessel_positions.csv includes the AIS positions vessel_id, t, lon, lat, heading, course, speed of all vessels. Simulated_vessel_proximity_events.csv includes the id, position and timestamp of each identified proximity event along with the vessel_id number of the associated vessels. The final sum of unintended proximity events in the dataset is 237. Examples of unintended vessel proximity events are visualized in the respective png and gif files. The research leading to these results has received funding from the European Union's Horizon Europe Programme under the CREXDATA Project, grant agreement n° 101092749.
Synthetic AIS Dataset of Vessel Proximity Events
Zenodo (CERN European Organization for Nuclear Research), 2023 · Open Access
Abstract
The Automatic Identification System (AIS) allows vessels to share identification, characteristics, and location data through self-reporting. This information is periodically broadcast and can be received by other vessels with AIS transceivers, as well as ground or satellite sensors. Since the International Maritime Organisation (IMO) mandated AIS for vessels above 300 gross tonnage, extensive datasets have emerged, becoming a valuable resource for maritime intelligence. Maritime collisions occur when two vessels collide or when a vessel collides with a floating or stationary object, such as an iceberg. Maritime collisions hold significant importance in the realm of marine accidents for several reasons: Injuries and fatalities of vessel crew members and passengers. Environmental effects, especially in cases involving large tanker ships and oil spills. Direct and indirect economic losses on local communities near the accident area. Adverse financial consequences for ship owners, insurance companies and cargo owners including vessel loss and penalties. As sea routes become more congested and vessel speeds increase, the likelihood of significant accidents during a ship's operational life rises. The increasing congestion on sea lanes elevates the probability of accidents and especially collisions between vessels. The development of solutions and models for the analysis, early detection and mitigation of vessel collision events is a significant step towards ensuring future maritime safety. In this context, a synthetic vessel proximity event dataset is created using real vessel AIS messages. The synthetic dataset of trajectories with reconstructed timestamps is generated so that a pair of trajectories reach simultaneously their intersection point, simulating an unintended proximity event (collision close call). The dataset aims to provide a basis for the development of methods for the detection and mitigation of maritime collisions and proximity events, as well as the study and training of vessel crews in simulator environments. The dataset consists of 4658 samples/AIS messages of 213 unique vessels from the Aegean Sea. The steps that were followed to create the collision dataset are: Given 2 vessels X (vessel_id1) and Y (vessel_id2) with their current known location (LATITUDE [lat], LONGITUDE [lon]): Check if the trajectories of vessels X and Y are spatially intersecting. If the trajectories of vessels X and Y are intersecting, then align temporally the timestamp of vessel Y at the intersect point according to X’s timestamp at the intersect point. The temporal alignment is performed so the spatial intersection (nearest proximity point) occurs at the same time for both vessels. Also for each vessel pair the timestamp of the proximity event is different from a proximity event that occurs later so that different vessel trajectory pairs do not overlap temporarily. Two csv files are provided. vessel_positions.csv includes the AIS positions vessel_id, t, lon, lat, heading, course, speed of all vessels. Simulated_vessel_proximity_events.csv includes the id, position and timestamp of each identified proximity event along with the vessel_id number of the associated vessels. The final sum of unintended proximity events in the dataset is 237. Examples of unintended vessel proximity events are visualized in the respective png and gif files. The research leading to these results has received funding from the European Union's Horizon Europe Programme under the CREXDATA Project, grant agreement n° 101092749.
Intelligent fleet management of autonomous vehicles for city logistics
Applied Intelligence, 2022 · 27 citations
Performance Analysis of Storage Systems in Edge Computing Infrastructures
Applied Sciences, 2022 · 17 citations · Open Access
Abstract
Edge computing constitutes a promising paradigm of managing and processing the massive amounts of data generated by Internet of Things (IoT) devices. Data and computation are moved closer to the client, thus enabling latency- and bandwidth-sensitive applications. However, the distributed and heterogeneous nature of the edge as well as its limited resource capabilities pose several challenges in implementing or choosing an efficient edge-enabled storage system. Therefore, it is imperative for the research community to contribute to the clarification of the purposes and highlight the advantages and disadvantages of various edge-enabled storage systems. This work aspires to contribute toward this direction by presenting a performance analysis of three different storage systems, namely MinIO, BigchainDB, and the IPFS. We selected these three systems as they have been proven to be valid candidates for edge computing infrastructures. In addition, as the three evaluated systems belong to different types of storage, we evaluated a wide range of storage systems, increasing the variability of the results. The performance evaluation is performed using a set of resource utilization and Quality of Service (QoS) metrics. Each storage system is deployed and installed on a Raspberry Pi (small single-board computers), which serves as an edge device, able to optimize the overall efficiency with minimum power and minimum cost. The experimental results revealed that MinIO has the best overall performance regarding query response times, RAM consumption, disk IO time, and transaction rate. The results presented in this paper are intended for researchers in the field of edge computing and database systems.
A Hybrid Robotic Network for Maritime Situational Awareness: Results From the INFORE22 Sea Trial
OCEANS 2022, Hampton Roads, 2022 · 9 citations
Abstract
In this paper we describe an integrated system for maritime situational awareness (MSA) applications, built on a cooperative autonomous robotic network, and developed in the maritime use case of the INFORE EU H2020 project. INFORE project developed an interactive, real-time, extreme-scale analytics and forecasting system for handling and analysing massive streams of data. The MSA INFORE system exploits the synergy between global view (AIS data, ESA Sentinel satellite data), which provide contextual information over a wide area, and local view produced by a sensorised hybrid robotic network. Such a network was validated during the INFORE22 sea trial, held off the coast of Portovenere, Italy, in the Gulf of La Spezia, in February-March 2022. It was composed of a thermal camera and of two autonomous underwater vehicles (AUVs) equipped with passive sonars. The robots fused their measurements, and cooperatively adapted their navigation for localising a suspicious vessel, communicating her position to the MSA INFORE platform in real-time. For controlling the robots, we developed a perception layer, based on an occupancy grid map framework, which enabled the fusion of passive sonar bearing-only measurements for target localisation. The perception layer was also the basis for making cooperative decisions to adapt the network spatial configuration for improving mission performance. In this paper we report and discuss results from the INFORE22 trial. These results are one the first demonstrations of how data fusion and cooperative autonomy can increase the performance of a complex robotic network in a passive sonar surveillance mission in a real-world scenario. The INFORE MSA systems paves the way towards the development of complex, integrated MSA systems, which exploit robotic networks, characterised by advanced cooperative autonomy capabilities, for improving the local view picture, and for promptly reacting to the evolving scenario.
AIS‑Enabled Weather Routing for Cargo Loss Prevention
Journal of Marine Science and Engineering, 2022 · 6 citations · Open Access
Abstract
The operation of any vessel includes risks, such as mechanical failure, collision, property loss, cargo loss, or damage. For modern container ships, safe navigation is challenging as the rate of innovation regarding design, speed profiles, and carrying capacity has experienced exponential growth over the past few years. Prevention of cargo loss in container ship liners is of high importance for the Maritime industry and the waterborne sector as it can lead to potentially disastrous, harmful, or even life-threatening outcomes for the crew, the shipping company, the marine environment, and aqua-culture. With the installment of onboard decision support system(s) (DSS) that will provide the required operational guidance to the vessel’s master, we aim to prevent and overcome such events. This paper explores cargo losses in container ships by employing a novel weather routing optimization DS framework that aims to identify excessive motions and accelerations caused by bad weather at specific times and locations; it also suggests alternative routes and, thus, ultimately prevents cargo loss and damage.
Vessel Traffic Density Maps Based on Vessel Detection in Satellite Imagery
IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium, 2022 · 5 citations
Abstract
Nowadays, the volume and variety of vessel tracking data are rapidly increasing. The Automatic Identification System (AIS) is the main source of vessel tracking data as most commercial vessels need to bear an AIS transponder and transmit messages every few seconds to minutes, depending on the vessel type and navigational status. Although calculating the density of vessel traffic based on AIS provides the most valuable insights, other sources of data could also be added in order to obtain a more complete picture of the maritime domain, as there are areas with limited AIS coverage and areas where vessels tend to switch-off their transponders. In the work described in this paper, we highlight those areas by performing vessel detection in Copernicus Sentinel-1 and Sentinel-2 imagery and producing “dark vessel” density maps, i.e., maps showing the density of vessels not transmitting AIS messages. The experimental evaluation of our approach shows that our framework achieves an accuracy greater than 95%.
Navigating through dense waters: a toolbox for creating maritime density maps
2022 · 4 citations
Abstract
Analysing maritime traffic supports understanding activities that take place at sea, for purposes ranging from maritime spatial planning, improving safety of operations and environmental protection, to studying the biodiversity and sustainability of ecosystems. Often studying maritime traffic requires processing very large datasets of vessel movement, such as those produced by the Automatic Identification System (AIS). Originally developed for the purpose of vessel collision avoidance, the AIS allows for constant monitoring of vessel activity through spatiotemporal messages transmitted by the vessels themselves. The surplus of positional data, originating from the large amounts of messages received daily, and the noise on AIS, coming from all sorts of interference, render further analysis a challenging task. In order to overcome these issues we released an open source toolbox that provides a number of modules to support easy handling of AIS data, while improving their transformation into actionable visualisations, such as traffic density maps. More specifically, the toolbox provides scalable mechanisms for processing AIS datasets, like the removal of spoofing or erroneous messages, while the density map extraction can be easily configured to fit the user needs. The implementation is written in python for simplicity, readability and overall ease of use.
TraClets: Harnessing the power of computer vision for trajectory classification
arXiv (Cornell University), 2022 · 4 citations · Open Access
Abstract
Due to the advent of new mobile devices and tracking sensors in recent years, huge amounts of data are being produced every day. Therefore, novel methodologies need to emerge that dive through this vast sea of information and generate insights and meaningful information. To this end, researchers have developed several trajectory classification algorithms over the years that are able to annotate tracking data. Similarly, in this research, a novel methodology is presented that exploits image representations of trajectories, called TraClets, in order to classify trajectories in an intuitive humans way, through computer vision techniques. Several real-world datasets are used to evaluate the proposed approach and compare its classification performance to other state-of-the-art trajectory classification algorithms. Experimental results demonstrate that TraClets achieves a classification performance that is comparable to, or in most cases, better than the state-of-the-art, acting as a universal, high-accuracy approach for trajectory classification.
Real‑time moving target detection in infrared maritime scenarios
2022 IEEE International Workshop on Metrology for the Sea; Learning to Measure Sea Health Parameters (MetroSea), 2022 · 3 citations
Abstract
In maritime surveillance, real-time moving target detection is a crucial task. The purpose of our work was to test some moving target detection techniques inspired by the state-of-the-art on a specific dataset of interest. In this paper, we analyze the performance obtained by Frame Difference and Gaussian Mixture Model-based methods in static InfraRed video sequences. The dataset was collected under real operational conditions during a recent experimental activity. The frames in the dataset are characterized by heterogeneous backgrounds and different targets covering a wide range of sizes and speeds. To evaluate the performance, the ground truth has been manually labeled through direct observation in 4706 frames. All the examined techniques are used to estimate the background. They are preceded by a frame-based z-normalization. After the background estimation, the absolute difference with the normalized frame is computed to highlight both hot and cold targets. Once highlighted, the targets can be separated from the background with a threshold. Then, morphological operations both in time and space are executed to delete small and brief false alarms. Finally, blob analysis is computed to extract the Regions of Interest. The algorithms have been evaluated based on their Precision-Recall curves, and Mean Execution Times.
Assisted Reality as an enabler for resilient remote learning during COVID‑19
2022 IEEE 28th International Conference on Engineering, Technology and Innovation (ICE/ITMC) & 31st International Association For Management of Technology (IAMOT) Joint Conference, 2022 · 2 citations
Abstract
During the COVID'19 pandemic the vital practical aspect of Technical Vocational Educational Training (TVET) almost halted completely., as most providers were insufficiently prepared to respond to the containment measures applied to stop the spread of the virus. In this paper., we report on our preliminary work towards developing a resilient maritime TVET ecosystem by enabling remote learning and examination using Assisted Reality (AR) technologies. We present a novel framework for remote maritime TVET., incorporating AR devices., and evaluate our approach in real world conditions., in a class of more than 28 students of the Rotterdam Mainport Institute. We attempt to qualitatively and quantitatively measure the effect such systems have on the students learning process and report on the results.
Benchmarking moving object functionalities of DBMSs using real‑world spatiotemporal workload
2022 23rd IEEE International Conference on Mobile Data Management (MDM), 2022 · 2 citations
Abstract
The sudden rise of GPS-enabled mobile devices has given birth to research related to the analysis and visualization of big mobility data that are stored in large spatio-temporal databases. Therefore, this research is focused on evaluating and comparing widely-used database systems that are employed in the analysis of spatio-temporal data. Specifically, three database systems are evaluated and compared with each other, namely PostGIS, MobilityDB, and MongoDB, in their ability to perform range, temporal aggregate, distance and nearest-neighbor queries. To this end, a subset of the BerlinMOD benchmark queries is employed for evaluation purposes over vessel tracking data. The experimental results presented in this paper are only preliminary in an attempt to drive future research in the field of industrial use case surveillance.
Data Driven Digital Twins for the Maritime Domain
Progress in marine science and technology, 2022 · 1 citation
Abstract
Digital twins are computational models that replicate the structure, behaviour and overall characteristics of a physical asset in the digital world. In the maritime domain, conventional approaches have relied on mathematical modeling (e.g., linearised equations of motion) and heavy computations for estimating ship resistance and propulsion, seakeeping and maneuverability and overall hull form optimization, treating the vessel as a point body. For instance, the ability to predict a vessel’s future track in confined or congested waters presents a significant challenge due to the fact that as time passes, these models often fall out of sync with their digital counterparts due to changes that happen to the ship (e.g., foulding affecting maneuverability). In addition to this, mostly due to computational resources required, in real world deployments models are simplified, thus reducing their overall prediction accuracy. In our work, we implement AI-enabled coupled abstractions of the asset-twin system, which rely on machine learning methods for constant learning of the evolving over time behavior of a vessel based on historical trip data and information related to vessel’s structure and loading capacity. The evaluation results indicate that the inclusion of vessel and journey specific information is beneficial for the predictions.
FRAME 2022
2022
Abstract
The 2nd International Workshop on Flexible Resource and Application Management on the Edge (FRAME 2022) is dedicated to the so-called Cloud/Edge Continuum, where Cloud and Edge infrastructures can work together to fulfill requirements from a variety of NextGen applications. Clouds provide appropriate levels of performance to large groups of different users, whereas Edge resources act as a first layer of computing capacity that is closer to the user, to reduce the service latency. With respect to Clouds, Edge infrastructures typically are composed of heterogeneous and constrained resources and introduce new challenges from the viewpoint of security, orchestration and resource management. Tackling these new issues calls for innovative combinations of tools and abstractions, where AI and machine learning techniques complement algorithmic orchestration and optimization, bringing about new levels of distributed adaptivity and self-management. As real-time data-driven decisions can be promptly taken on the spot, without the need to wait for data to travel to the Cloud and back, also interactive and time-sensitive services like the immersive data processing of Extended Reality (XR) applications can be partially extended toward the edge, thus exploiting a better computation to communication tradeoff and smoother connections to improve their QoE and remote collaboration. The FRAME'22 workshop proceedings are available at: https://dl.acm.org/citation.cfm?id=3526059.
Abstract
A bstract The sudden increase of wearable devices has led to the generation of an abundance of data. As a result, researchers can use such data to perform analyses and generate recommendations. A crucial factor in the research field of nutrition and dietetics is the accurate measurement of metabolic rate, as it can be used to estimate several other variables, e.g. calorie expenditure. Nonetheless, limited studies have been conducted to examine the use of machine learning models for metabolic rate prediction based on data generated from wearable devices. Therefore, in this paper, a neural network architecture is proposed, able to predict a subject’s metabolic rate exploiting only such data. Experimental results demonstrated that the proposed methodology can outperform conventional algorithms in prediction accuracy of real-world data. Furthermore, results indicated that the trivial time taken for the network to predict the metabolic rate makes it suitable for wearable devices deployment.
COVID‑19 impact on global maritime mobility
CINECA IRIS Institutial research information system (University of Pisa), 2021 · 143 citations
Abstract
To prevent the outbreak of the Coronavirus disease (COVID-19), many countries around the world went into lockdown and imposed unprecedented containment measures. These restrictions progressively produced changes to social behavior and global mobility patterns, evidently disrupting social and economic activities. Here, using maritime traffic data collected via a global network of Automatic Identification System (AIS) receivers, we analyze the effects that the COVID-19 pandemic and containment measures had on the shipping industry, which accounts alone for more than 80% of the world trade. We rely on multiple data-driven maritime mobility indexes to quantitatively assess ship mobility in a given unit of time. The mobility analysis here presented has a worldwide extent and is based on the computation of: Cumulative Navigated Miles (CNM) of all ships reporting their position and navigational status via AIS, number of active and idle ships, and fleet average speed. To highlight significant changes in shipping routes and operational patterns, we also compute and compare global and local vessel density maps. We compare 2020 mobility levels to those of previous years assuming that an unchanged growth rate would have been achieved, if not for COVID-19. Following the outbreak, we find an unprecedented drop in maritime mobility, across all categories of commercial shipping. With few exceptions, a generally reduced activity is observable from March to June 2020, when the most severe restrictions were in force. We quantify a variation of mobility between −5.62 and −13.77% for container ships, between +2.28 and −3.32% for dry bulk, between −0.22 and −9.27% for wet bulk, and between −19.57 and −42.77% for passenger traffic. The presented study is unprecedented for the uniqueness and completeness of the employed AIS dataset, which comprises a trillion AIS messages broadcast worldwide by 50,000 ships, a figure that closely parallels the documented size of the world merchant fleet.
A Deep Learning Streaming Methodology for Trajectory Classification
ISPRS International Journal of Geo-Information, 2021 · 40 citations · Open Access
Abstract
Due to the vast amount of available tracking sensors in recent years, high-frequency and high-volume streams of data are generated every day. The maritime domain is no different as all larger vessels are obliged to be equipped with a vessel tracking system that transmits their location periodically. Consequently, automated methodologies able to extract meaningful information from high-frequency, large volumes of vessel tracking data need to be developed. The automatic identification of vessel mobility patterns from such data in real time is of utmost importance since it can reveal abnormal or illegal vessel activities in due time. Therefore, in this work, we present a novel approach that transforms streaming vessel trajectory patterns into images and employs deep learning algorithms to accurately classify vessel activities in near real time tackling the Big Data challenges of volume and velocity. Two real-world data sets collected from terrestrial, vessel-tracking receivers were used to evaluate the proposed methodology in terms of both classification and streaming execution performance. Experimental results demonstrated that the vessel activity classification performance can reach an accuracy of over 96% while achieving sub-second latencies in streaming execution performance.
A Comparison of Trajectory Compression Algorithms Over AIS Data
IEEE Access, 2021 · 36 citations · Open Access
Abstract
Today’s industry is flooded with tracking data originating from vessels across the globe that transmit their position at frequent intervals. These voluminous and high-speed streams of data has led researchers to develop novel ways to compress them in order to speed-up processing without losing valuable information. To this end, several algorithms have been developed that try to compress streams of vessel tracking data without compromising their spatio-temporal and kinematic features. In this paper, we present a wide range of several well-known trajectory compression algorithms and evaluate their performance on data originating from vessel trajectories. Trajectory compression algorithms included in this research are suitable for either historical data (offline compression) or real-time data streams (online compression). The performance evaluation is three-fold and each algorithm is evaluated in terms of compression ratio, execution speed and information loss. Experiments demonstrated that each algorithm has its own benefits and limitations and that the choice of a suitable compression algorithm is application-dependent. Finally, considering all assessed aspects, the Dead-Reckoning algorithm not only presented the best performance, but it also works over streaming data, which constitutes an important criterion in maritime surveillance.
Abstract
Nowadays, the increasing number of moving objects tracking sensors, results in the continuous flow of high-frequency and high-volume data streams. This phenomenon can especially be observed in the maritime domain since most of the vessels worldwide are now transmitting their positions periodically. Therefore, there is a strong necessity to extract meaningful information and identify mobility patterns from such tracking data in an automated fashion, eliminating the need for experts' input. To this end, a novel approach is presented in this paper, which fuses the research fields of computer vision and trajectory classification, in order to deliver a high-precision classification of mobility patterns. The experimental results demonstrate that the classification performance of the proposed approach can reach an f1-score of over 95%.
Maritime Network Analysis: Connectivity and Spatial Distribution
2021 · 15 citations · Open Access
A Decision Algorithm for Motion Planning of Car‑Like Robots in Dynamic Environments
Cybernetics & Systems, 2021 · 8 citations
Abstract
Motion planning in dynamic environments is essential for many applications such as in search and rescue missions and in servicing tasks. In this paper, I present a new approach for motion planning for an autonomous mobile robot which is requested to operate in a dynamic environment. The robot’s working environment is cluttered with static obstacles with a priori knowledge of their shapes and positions and with moving obstacles with unknown geometry and motion. In order to ensure a safe motion for the robot I propose a two-stage approach. First, using the Bump-Surface concept I construct a path by considering only the static obstacles of the environment. Then, the robot starts its motion on the given path. When the robot detects a potential danger situation (i.e., collision), a decision algorithm tries to evaluate the risk of collision and simultaneously to find the safest action for the robot. The proposed approach is evaluated in randomly generated simulated scenarios.
Online Distributed Maritime Event Detection & Forecasting over Big Vessel Tracking Data
2021 IEEE International Conference on Big Data (Big Data), 2021 · 6 citations
Abstract
We present a Maritime Situational Awareness (MSA) framework for detecting and forecasting maritime events (e.g., illegal fishing) over streams of Big maritime Data. The architecture of the MSA framework relies on the following state-of-the-art components: (i) the Maritime Event Detector which uses data-driven distributed techniques deployed on a computer cluster to detect maritime events of interest in an online, real-time fashion, (ii) the Complex Event Forecasting module, which implements state-of-the-art distributed Complex Event Forecasting techniques for maritime data, (iii) the Synopses Data Engine component, that creates synopses of maritime data improving the scalability of the framework and (iv) the streaming extension of a popular data science platform, namely RapidMiner Studio, that integrates all the above, allowing users to graphically design and rapidly implement Big Data analytics pipelines which can be deployed transparently on top of distributed architectures.
Data Driven Fleet Monitoring and Circular Economy
2021 · 6 citations · Open Access
Abstract
The maritime industry is intensively embracing green thinking. According to the International Maritime Organization’s (IMO) Greenhouse Gas (GHG ) strategy, the total annual GHG emissions from international shipping should be reduced by at least 50% by 2050 compared to 2008. Shipping adopts policies to comply with the set target, including ship redesign, structural retrofit, use of low-carbon material, and the installation of emission abatement technologies. All these approaches pave the way to circularity in the maritime economy, abandoning the linear model in vessel lifetime and adopting lean management, re-manufacturing, and re-usability of the asset. To this end, in the SmartShip project, we give prominence to data-driven ship monitoring by delivering an Information and Communication Technology (ICT) & Internet of Things (IoT)-enabled holistic cloud-based maritime performance and monitoring system. This system is considering the entire lifecycle of a ship, aiming to optimize energy efficiency, emissions reduction, fuel consumption, while, at the same time, include circular economy concepts in the maritime field. Our approach supports a cost-effective strategy where data analysis drives decisions in ship operation and maintenance.
Semi‑supervised trajectory classification using convolutional auto‑encoders
2021 · 6 citations
Abstract
Massive volumes of high-frequency and high-volume data are constantly being generated by the vast amount of available tracking sensors of moving objects. This phenomenon can be strongly observed in the maritime domain since most of the vessels transmit their location periodically. Automated methodologies able to extract meaningful information from vessel data is of utmost importance since it can reveal abnormal or illegal vessel activities in due time. Supervised deep learning approaches such as convolutional neural networks (CNNs) require a large-scale annotated image dataset. Thus, semi- and unsupervised feature learning algorithms which learn image features from unlabelled data are able to mitigate this problem. To this end, in this work we propose a semi-supervised convolutional autoencoder (CAE) model for trajectory classification which is able to provide high-precision classification of mobility patterns. Experimental results demonstrated that the vessel activity classification performance can reach an F1-score of over 94%.
Detecting representative trajectories from global AIS datasets
2021 · 5 citations · Open Access
Abstract
With real time vessel surveillance data now becoming available at an increasing rate, there is a growing interest in applications that can forecast future vessel positions and routes, especially in congested and busy areas. Since vessels move in “free space”, a prerequisite to effectively forecasting vessels' future locations is accurately discovering representative tracks (common paths followed by several vessels). Towards this direction, this work introduces a novel data driven framework that is capable of detecting spatial representations of complete trajectories (from port to port) from massive Automatic Identification System (AIS) datasets. Along these lines, we present a novel approach for forecasting representative tracks from noisy and non-uniform datasets (number of points, sampling rates, coverage gaps etc.) at a global scale. Our technique models the entire space where the vessels traveled in the past, detecting the set of frequently followed locations. This gives our proposed method the ability to forecast the most likely movement from a given query location towards a destination port. Finally, we present extensive experiments with real-world data, so as to demonstrate the effectiveness of our proposed method.
Developing a Robotic Hybrid Network for Coastal Surveillance: the INFORE Experience
OCEANS 2021: San Diego – Porto, 2021 · 5 citations
Abstract
INFORE EU H2020 project has the objective of developing a real-time, interactive extreme-scale analytics and forecasting system capable of handling and analysing massive data streams. The system is validated in three different real-world use cases, In this paper we describe one of them, presenting the development of the INFORE system for a coastal surveillance Maritime Situational Awareness (MSA) application. The MSA INFORE system exploits the synergy between global view (AIS data, ESA Sentinel satellite data), providing contextual information over a wider area, and local view produced by a sensorised hybrid robotic network. The network is composed of an RGB/thermal camera onshore and of two Wave Gliders robots equipped with passive sonars. We focus on the development of this network, describing the cooperative autonomy framework to control the robots. The framework enables the robots to make decisions on their navigation for improving vessel detection and tracking. The INFORE MSA network demonstrates the benefits that the synergy between machine learning, AI and autonomous robots can bring in this kind of monitoring systems. The developed autonomy strategies increase the quality of the information produced by robots. These high-quality real-time observations are fused with the global view in the INFORE MSA and decision-support platform. Data fusion from multimodal data sources results crucial for the detection of complex events (e.g. illegal fishing), which can then be communicated to decision-makers. Different modules of the systems are ready and under testing. The whole system will be validated in a trial in 2022.
Processing Big Data in Motion: Core Components and System Architectures with Applications to the Maritime Domain
2021 · 2 citations · Open Access
Abstract
Abstract Rapidly extracting business value out of Big Data that stream in corporate data centres requires continuous analysis of massive, high-speed data while they are still in motion. So challenging a goal entails that analytics should be performed in memory with a single pass over these data. In this chapter, we outline the challenges of Big streaming Data analysis for deriving real-time, online answers to application inquiries. We review approaches, architectures and systems designed to address these challenges and report on our own progress within the scope of the EU H2020 project INFORE. We showcase INFORE into a real-world use case from the maritime domain and further discuss future research and development directions.
A data‑driven methodology for maritime Patterns of Life discovery
Institution of Engineering and Technology eBooks, 2021
Abstract
A data-driven methodology suitable for discovering maritime traffic patterns (maritime analytics) and revealing “roads of sea” is discussed. The proposed solution exploits the MapReduce paradigm to perform parallel distributed processing of large vessel tracking datasets, collected through the automatic identification system (AIS), and analyzes vessels' navigational patterns in a computationally efficient and accurate way. Unsupervised machine learning algorithms are employed to distinguish the spatiotemporal characteristics of vessel routes and distill global maritime “Patterns of Life.” A “Pattern of Life” emerges through an aggregated analysis of spatiotemporal directed port-to-port connections bearing thus the burden of post-processing analysis. Within this context, Patterns of Life are perceived as an enabler for numerous maritime applications. This work presents an overview of the ROute exTrActor (ROTA) approach, while focus is given toward the technical design aspects and challenges of this scheme. The merits of this work can be helpful to a wide spectrum of maritime services such as understanding and predicting vessels' activities, evaluating shipping's impact on the environment, detecting dangerous situations and providing risk reports, assessing the vessel's navigation performance and performing voyage optimization.
Maritime network analysis : connectivity and spatial distribution
HAL (Le Centre pour la Communication Scientifique Directe), 2021
COVID‑19 detection from chest X‑Ray images using Deep Learning and Convolutional Neural Networks
2020 · 111 citations
Abstract
The COVID-19 pandemic in 2020 has highlighted the need to pull all available resources towards the mitigation of the devastating effects of such ”Black Swan” events. Towards that end, we investigated the option to employ technology in order to assist the diagnosis of patients infected by the virus. As such, several state-of-the-art pre-trained convolutional neural networks were evaluated as of their ability to detect infected patients from chest X-Ray images. A dataset was created as a mix of publicly available X-ray images from patients with confirmed COVID-19 disease, common bacterial pneumonia and healthy individuals. To mitigate the small number of samples, we employed transfer learning, which transfers knowledge extracted by pre-trained models to the model to be trained. The experimental results demonstrate that the classification performance can reach an accuracy of 95% for the best two models.
MongoDB Vs PostgreSQL: A comparative study on performance aspects
GeoInformatica, 2020 · 69 citations · Open Access
Abstract
Abstract Several modern day problems need to deal with large amounts of spatio-temporal data. As such, in order to meet the application requirements, more and more systems are adapting to the specificities of those data. The most prominent case is perhaps the data storage systems, that have developed a large number of functionalities to efficiently support spatio-temporal data operations. This work is motivated by the question of which of those data storage systems is better suited to address the needs of industrial applications. In particular, the work conducted, set to identify the most efficient data store system in terms of response times, comparing two of the most representative of the two categories (NoSQL and relational), i.e. MongoDB and PostgreSQL. The evaluation is based upon real, business scenarios and their subsequent queries as well as their underlying infrastructures and concludes in confirming the superiority of PostgreSQL in almost all cases with the exception of the polygon intersection queries. Furthermore, the average response time is radically reduced with the use of indexes, especially in the case of MongoDB.
A distributed framework for extracting maritime traffic patterns
International Journal of Geographical Information Systems, 2020 · 64 citations · Open Access
Abstract
All the modern surveillance systems take advantage of the Automatic Identification System (AIS), a compulsory tracking system for many types of vessels. Ships that carry AIS transponders on board transmit their position and status in order to alert nearby vessels and ground stations, but this information can well be used to identify events of interest and support decision making. The detection of anomalies (i.e. unexpected sailing behavior) in vessels' trajectories is such an event, which is of utmost importance. Approaches for detecting such anomalies vary from extracting normality models to searching for individual cases, such as AIS switch-off or collision avoidance maneuvers. The current research work follows the former method; it employs sparse historic AIS data and polynomial interpolation in order to extract shipping lanes. It modifies the DB-Scan clustering algorithm in order to achieve more coherent trajectory clusters, which are then composed to create the shipping lanes. The proposed approach implements distributed processing on Apache Spark in order to improve processing speed and scalability and is evaluated using real-world AIS data collected from terrestrial AIS receivers. The evaluation shows that the biggest part (i.e. more than 90%) of any future vessel trajectory falls within the extracted shipping lanes.
COVID‑19 detection from chest X‑Ray images using Deep Learning and Convolutional Neural Networks
medRxiv, 2020 · 58 citations · Open Access
Abstract
A bstract The COVID-19 pandemic in 2020 has highlighted the need to pull all available resources towards the mitigation of the devastating effects of such “Black Swan” events. Towards that end, we investigated the option to employ technology in order to assist the diagnosis of patients infected by the virus. As such, several state-of-the-art pre-trained convolutional neural networks were evaluated as of their ability to detect infected patients from chest X-Ray images. A dataset was created as a mix of publicly available X-ray images from patients with confirmed COVID-19 disease, common bacterial pneumonia and healthy individuals. To mitigate the small number of samples, we employed transfer learning, which transfers knowledge extracted by pre-trained models to the model to be trained. The experimental results demonstrate that the classification performance can reach an accuracy of 95% for the best two models.
A Distributed Spatial Method for Modeling Maritime Routes
IEEE Access, 2020 · 55 citations · Open Access
Abstract
In this work we propose a novel spatial knowledge discovery pipeline capable of automatically unravelling the “roads of the sea” and maritime traffic patterns by analysing voluminous vessel tracking data, as collected through the Automatic Identification System (AIS). We present a computationally efficient and highly accurate solution, based on a MapReduce approach and unsupervised learning methods, capable of identifying the spatiotemporal dynamics of ship routes and most crucially their characteristics, thus deriving maritime “patterns of life” at a global scale, without the reliance on any additional information sources or a priori expert knowledge. Experimental results confirm high accuracy of results and superior performance in comparison to other methods, with the entire processing duration completing in less than 3 hours for more than a terabyte of non-uniform spatial data. Finally, to clearly demonstrate the applicability and impact of our proposed method, we evaluate its ability to detect real world “anomalies”, such as maritime incidents reported in the European Marine Casualty Information Platform. Numerical results show the advantages of our scheme in terms of accuracy, with an achieved anomaly detection accuracy of higher than 93%, by detecting 313 out of 335 relevant maritime incidents.
AGV routing and motion planning in a flexible manufacturing system using a fuzzy‑based genetic algorithm
The International Journal of Advanced Manufacturing Technology, 2020 · 43 citations
Real‑time maritime anomaly detection: detecting intentional AIS switch‑off
International Journal of Big Data Intelligence, 2020 · 39 citations
Abstract
Today, most of the maritime surveillance systems rely on the automatic identification system (AIS), which is compulsory for vessels of specific categories to carry. Anomaly detection typically refers to the problem of finding patterns in data that do not conform to expected behaviour. AIS switch-off is such a pattern that refers to the fact that many vessels turn off their AIS transponder in order to hide their whereabouts when travelling in waters with frequent piracy attacks or potential illegal activity, thus deceiving either the authorities or other piracy vessels. Furthermore, fishing vessels switch off their AIS transponders so as other fishing vessels do not fish in the same area. To the best of our knowledge limited work has focused on AIS switch-off in real-time. We present a system that detects such cases in real-time and can handle high velocity, large volume of streams of AIS messages received from terrestrial base stations. We evaluate the proposed system in a real-world dataset collected from AIS receivers and show the achieved detection accuracy.
Building navigation networks from multi‑vessel trajectory data
GeoInformatica, 2020 · 36 citations · Open Access
Classification of vessel activity in streaming data
2020 · 26 citations
Abstract
In this paper we motivate the need for real-time vessel behaviour classification and describe in detail our event-based classification approach, as implemented in our real-world industry strong maritime event detection service at MarineTraffic.com. A novel approach is presented for the classification of vessel activity from real-time data streams. The proposed solution splits vessel trajectories into multiple overlapping segments and distinguishes the ones in which a vessel is engaged in trawling or longlining operation (e.g. fishing activity) from other segments that a vessel is simply underway from its departure towards its destination. We evaluate the effectiveness of our tool on real-world data, demonstrating that it can practically achieve high accuracy results. We present our results and findings intended for both researchers and practitioners in the field of intelligent ship tracking and surveillance.
Real‑time maritime anomaly detection: detecting intentional AIS switch‑off
International Journal of Big Data Intelligence, 2020 · 16 citations
Abstract
Today, most of the maritime surveillance systems rely on the automatic identification system (AIS), which is compulsory for vessels of specific categories to carry. Anomaly detection typically refers to the problem of finding patterns in data that do not conform to expected behaviour. AIS switch-off is such a pattern that refers to the fact that many vessels turn off their AIS transponder in order to hide their whereabouts when travelling in waters with frequent piracy attacks or potential illegal activity, thus deceiving either the authorities or other piracy vessels. Furthermore, fishing vessels switch off their AIS transponders so as other fishing vessels do not fish in the same area. To the best of our knowledge limited work has focused on AIS switch-off in real-time. We present a system that detects such cases in real-time and can handle high velocity, large volume of streams of AIS messages received from terrestrial base stations. We evaluate the proposed system in a real-world dataset collected from AIS receivers and show the achieved detection accuracy.
Uncovering Hidden Concepts from AIS Data: A Network Abstraction of Maritime Traffic for Anomaly Detection
Lecture notes in computer science, 2020 · 12 citations · Open Access
Abstract
The compulsory use of Automatic Identification System (AIS) for many vessel types, which has been enforced by naval regulations, has opened new opportunities for maritime surveillance. AIS transponders are rich sources of information that everyone can collect using an RF receiver and provide real-time information about vessels’ position. Properly taking advantage of AIS data, can uncover potential illegal behavior, offer real-time alerts and notify the authorities for any kind of anomalous vessel behavior. In this article, we extend an existing network abstraction of maritime traffic, that is based on nodes (called way-points) that correspond to naval areas of long stays or major turns for vessels (e.g. ports, capes, offshore platforms etc.) and edges (called traversals) that correspond to the routes followed by vessels between two consecutive way-points. The current work, focuses on the connections of this network abstraction and enriches them with semantic information about the different ways that vessels employ when traversing an edge. For achieving this, it proposes an alternative of the popular density based clustering algorithm DB-Scan, which modifies the proximity parameter (i.e. epsilon) of the algorithm. The proposed alternative employs in tandem the difference in (i) speed, (ii) course and (iii) position for defining the distance between two consecutive vessel positions (two consecutive AIS signals received from the same vessel). The results show that this combination performs significantly better than using only the spatial distance and, more importantly, results in clusters that have very interesting properties. The enriched network model can be processed and further examined with data mining techniques, even in an unsupervised manner, in order to identify anomalies in vessels’ trajectories. Experimental results on a real dataset show the network’s potential for detecting trajectory outliers and uncovering deviations on a vessel’s route.
Optimal robot task scheduling based on adaptive neuro‑fuzzy system and genetic algorithms
The International Journal of Advanced Manufacturing Technology, 2020 · 9 citations
Abstract
The establishment of the Automatic Identification System (AIS) was revolutionary for Maritime Situational Awareness, as it allowed for the tracking of vessels carrying an AIS transponder, which is mandatory for, and not limited to, the majority of the commercial fleet. Despite the benefits of the widespread use of AIS for navigational safety and global maritime security, one cannot depend only on AIS sources in order to obtain the complete maritime situational awareness picture. In this paper we describe a multistage data-centric workflow that integrates satellite optical imagery and AIS data for automatic vessel detection that builds on (i) image processing techniques and (ii) Convolutional Neural networks. The experimental evaluation of our approach shows that our framework achieves an accuracy greater than 95%.
Single Ground Based AIS Receiver Vessel Tracking Dataset
Zenodo (CERN European Organization for Nuclear Research), 2020 · 6 citations · Open Access
Abstract
Nowadays, a multitude of tracking systems produce massive amounts of maritime data on a daily basis. The most commonly used is the Automatic Identification System (AIS), a collaborative, self-reporting system that allows vessels to broadcast their identification information, characteristics and destination, along with other information originating from on-board devices and sensors, such as location, speed and heading. AIS messages are broadcast periodically and can be received by other vessels equipped with AIS transceivers, as well as by on the ground or satellite-based sensors. Since becoming obligatory by the International Maritime Organisation (IMO) for vessels above 300 gross tonnage to carry AIS transponders, large datasets are gradually becoming available and are now being considered as a valid method for maritime intelligence [4].There is now a growing body of literature on methods of exploiting AIS data for safety and optimisation of seafaring, namely traffic analysis, anomaly detection, route extraction and prediction, collision detection, path planning, weather routing, etc., [5]. As the amount of available AIS data grows to massive scales, researchers are realising that computational techniques must contend with difficulties faced when acquiring, storing, and processing the data. Traditional information systems are incapable of dealing with such firehoses of spatiotemporal data where they are required to ingest thousands of data units per second, while performing sub-second query response times. Processing streaming data seems to exhibit similar characteristics with other big data challenges, such as handling high data volumes and complex data types. While for many applications, big data batch processing techniques are sufficient, for applications such as navigation and others, timeliness is a top priority; making the right decision steering a vessel away from danger, is only useful if it is a decision made in due time. The true challenge lies in the fact that, in order to satisfy real-time application needs, high velocity, unbounded sized data needs to be processed in constraint, in relation to the data size and finite memory. Research on data streams is gaining attention as a subset of the more generic Big Data research field. Research on such topics requires an uncompressed unclean dataset similar to what would be collected in real world conditions. This dataset contains all decoded messages collected within a 24h period (starting from 29/02/2020 10PM UTC) from a single receiver located near the port of Piraeus (Greece). All vessels identifiers such as IMO and MMSI have been anonymised and no down-sampling procedure, filtering or cleaning has been applied. The schema of the dataset is provided below: · t: the time at which the message was received (UTC) · shipid: the anonymized id of the ship · lon: the longitude of the current ship position · lat: the latitude of the current ship position · heading: (see: https://en.wikipedia.org/wiki/Course_(navigation)) · course: the direction in which the ship moves (see: https://en.wikipedia.org/wiki/Course_(navigation)) · speed: the speed of the ship (measured in knots) · shiptype: AIS reported ship-type · destination: AIS reported destination
Correction to: MongoDB Vs PostgreSQL: a comparative study on performance aspects
GeoInformatica, 2020 · 5 citations · Open Access
Abstract
The article “MongoDB Vs PostgreSQL: A comparative study on performance aspects”, written by Antonios Makris, Konstantinos Tserpes, Giannis Spiliopoulos, Dimitrios Zissis, Dimosthenis Anagnostopoulos, was originally published electronically on the publisher’s internet portal on 05 June 2020 without open access.
Automatic Maritime Object Detection Using Satellite imagery
Global Oceans 2020: Singapore – U.S. Gulf Coast, 2020 · 5 citations
Abstract
In this paper we present an approach for performing object classification and segmentation in satellite images for the Maritime domain. We employ neural network architectures for object classification and segmentation tasks in order to identify different classes of objects in satellite imagery for the maritime domain, such as vessels, land (e.g., port terminals), clouds, etc. We compare the accuracy of different neural network architectures and present the results of our experimental evaluation.
A Big Data framework for Modelling and Simulating high‑resolution hydrodynamic models in sea harbours
Global Oceans 2020: Singapore – U.S. Gulf Coast, 2020 · 4 citations
Abstract
The ability to reliably forecast sea states (most importantly sea level, wind and wave conditions) within or close to the entrance of ports is a critical tool for all involved stakeholders. In this paper we present our work on a prototype decision support system capable of providing accurate sea state forecasts based on three high-resolution hydrodynamic models, i.e. a spectral wave model (model A), a mild-slope equation wave model (model B) and a barotropic hydrodynamic circulation model (model H). We present an end to end novel data processing pipeline, capable of handling the challenges posed by the volume of related data and capable of providing high resolution wave forecasts by exploiting parallelization.
Experimental Comparison of Complex Event Processing Systems in the Maritime Domain
2020 · 4 citations
Abstract
Complex Event Processing (CEP) 's main purpose is recognizing interesting phenomena upon streams of data. So its only natural that it would find applications in the maritime domain, where detecting vessel activity plays an important role in monitoring movement at sea. In this study we briefly examine the field of Complex Event Processing; we present two CEP implementations, one based on machine learning techniques and a rule-based system modeled with Event Calculus. Finally, we evaluate their ability in modeling activities that involve multiple vessels, by comparing their results on real-life examples.
Modelling and simulating vessel emissions in real time based on terrestrial AIS data
Global Oceans 2020: Singapore – U.S. Gulf Coast, 2020 · 3 citations
Abstract
In this paper we present a complete framework for modelling and estimating vessel GHG emissions and related air pollutants (i.e. CO2 and SOx, NOx and PM) in ports, based on data collected from the Automatic Identification System (AIS). Our approach adopts a modified lambda architecture approach, which consists of a knowledge extraction batch processing step and a real time emissions calculation step. The approach makes it possible to automatically identify the berths or ports where emissions are high in a consistent and uniform way across the globe.
Single Ground Based AIS Receiver Vessel Tracking Dataset
Zenodo (CERN European Organization for Nuclear Research), 2020 · 3 citations · Open Access
Abstract
Nowadays, a multitude of tracking systems produce massive amounts of maritime data on a daily basis. The most commonly used is the Automatic Identification System (AIS), a collaborative, self-reporting system that allows vessels to broadcast their identification information, characteristics and destination, along with other information originating from on-board devices and sensors, such as location, speed and heading. AIS messages are broadcast periodically and can be received by other vessels equipped with AIS transceivers, as well as by on the ground or satellite-based sensors. Since becoming obligatory by the International Maritime Organisation (IMO) for vessels above 300 gross tonnage to carry AIS transponders, large datasets are gradually becoming available and are now being considered as a valid method for maritime intelligence [4].There is now a growing body of literature on methods of exploiting AIS data for safety and optimisation of seafaring, namely traffic analysis, anomaly detection, route extraction and prediction, collision detection, path planning, weather routing, etc., [5]. As the amount of available AIS data grows to massive scales, researchers are realising that computational techniques must contend with difficulties faced when acquiring, storing, and processing the data. Traditional information systems are incapable of dealing with such firehoses of spatiotemporal data where they are required to ingest thousands of data units per second, while performing sub-second query response times. Processing streaming data seems to exhibit similar characteristics with other big data challenges, such as handling high data volumes and complex data types. While for many applications, big data batch processing techniques are sufficient, for applications such as navigation and others, timeliness is a top priority; making the right decision steering a vessel away from danger, is only useful if it is a decision made in due time. The true challenge lies in the fact that, in order to satisfy real-time application needs, high velocity, unbounded sized data needs to be processed in constraint, in relation to the data size and finite memory. Research on data streams is gaining attention as a subset of the more generic Big Data research field. Research on such topics requires an uncompressed unclean dataset similar to what would be collected in real world conditions. This dataset contains all decoded messages collected within a 24h period (starting from 29/02/2020 10PM UTC) from a single receiver located near the port of Piraeus (Greece). All vessels identifiers such as IMO and MMSI have been anonymised and no down-sampling procedure, filtering or cleaning has been applied. The schema of the dataset is provided below: · t: the time at which the message was received (UTC) · shipid: the anonymized id of the ship · lon: the longitude of the current ship position · lat: the latitude of the current ship position · heading: (see: https://en.wikipedia.org/wiki/Course_(navigation)) · course: the direction in which the ship moves (see: https://en.wikipedia.org/wiki/Course_(navigation)) · speed: the speed of the ship (measured in knots) · shiptype: AIS reported ship-type · destination: AIS reported destination
Special Issue on High Performance Services Computing and Internet Technologies
Future Generation Computer Systems, 2020 · 1 citation
Abstract
Cloud Computing has undoubtedly been the most disruptive IT paradigm of the last two decades, spanning a wide area of technologies and implementations. Its emergence is already transforming the public sector with relevant e-Government use cases. The adoption of various cloud-related initiatives as part of national strategies is driving the need to use a common framework to better describe, analyse and compare those implementations, known as "Governmental Clouds". In addition, for any interoperability to be effective in the long run, a standard framework and common language to describe the relevant ontologies should exist. This paper aims to introduce and discuss a taxonomy of three different models based on the existing and emerging Cloud Computing governmental best practices and available use cases, addressing the lack of relevant concrete definitions.
A distributed framework for extracting maritime traffic patterns
Figshare, 2020 · Open Access
Abstract
All the modern surveillance systems take advantage of the Automatic Identification System (AIS), a compulsory tracking system for many types of vessels. Ships that carry AIS transponders on board transmit their position and status in order to alert nearby vessels and ground stations, but this information can well be used to identify events of interest and support decision making. The detection of anomalies (i.e. unexpected sailing behavior) in vessels’ trajectories is such an event, which is of utmost importance. Approaches for detecting such anomalies vary from extracting normality models to searching for individual cases, such as AIS switch-off or collision avoidance maneuvers. The current research work follows the former method; it employs sparse historic AIS data and polynomial interpolation in order to extract shipping lanes. It modifies the DB-Scan clustering algorithm in order to achieve more coherent trajectory clusters, which are then composed to create the shipping lanes. The proposed approach implements distributed processing on Apache Spark in order to improve processing speed and scalability and is evaluated using real-world AIS data collected from terrestrial AIS receivers. The evaluation shows that the biggest part (i.e. more than 90%) of any future vessel trajectory falls within the extracted shipping lanes.
Performance Evaluation of MongoDB and PostgreSQL for Spatio‑temporal Data
Zenodo (CERN European Organization for Nuclear Research), 2019 · 43 citations · Open Access
Abstract
Several modern day problems need to deal with large amounts of spatio-temporal data. As such, in order to meet the application requirements, more and more systems are adapting to the specificities of those data. The most prominent case is perhaps the data storage systems, that have developed a large number of functionalities to efficiently support spatio-temporal data operations. This work is motivated by the question of which of those data storage systems is better suited to address the needs of industrial applications. In particular, the work conducted, set to identify the most efficient data store system in terms of response times, comparing two of the most representative of the two categories (NoSQL and relational), i.e. MongoDB and PostgreSQL. The evaluation is based upon real, business scenarios and their subsequent queries as well as their underlying infrastructures, and concludes in confirming the superiority of PostgreSQL. Specifically, PostgreSQL is four times faster in terms of response time in most cases and presents an average speedup around 2 in first query, 4 in second query and 4,2 in third query in a five node cluster. Also, we observe that the average response time is significantly reduced at half with the use of indexes almost in all cases, while the reduction is significantly lower in PostgreSQL.
Automatic Fusion of Satellite Imagery and AIS data for Vessel Detection
2019 · 21 citations
Abstract
Being able to fuse information coming from different sources, such as AIS and satellite images is of major importance for maritime domain awareness, for example, to locate and identify vessels that may have purposely turned off their AIS transponder, preventing illegal activities. This paper presents a fully-automatic method for fusing AIS data and SAR satellite images for vessel detection. The proposed framework is based on the automatic annotation of satellite images by correlating them with AIS data producing train and test datasets which are provided as input to a convolutional neural network (CNN). The CNN was trained to detect the presence of ships in sectors of the image. Our automatic process allows the neural network to learn on a large amount of data, without the need for hand-labelled datasets. Our neural network, trained on our automatically-generated test set of images, achieved an accuracy of 88% at ship detection, and an area under ROC curve of 94,6%. Our estimate of real world accuracy is about 86-90%.
A distributed lightning fast maritime anomaly detection service
OCEANS 2019 - Marseille, 2019 · 13 citations
Abstract
For applications such as navigation and others, timeliness is a top priority; making the right decision steering a vessel away from danger, is only useful if it is a decision made in due time. Effectiveness of such time critical computing systems is dependent not only on the accuracy of the result produced, but also on the time in which it was computed. In this paper, we present a distributed architecture capable of detecting possible collisions, groundings, unexpected communication gaps and travel pattern deviations of ships fitted with Automatic Identification System transponders. Our results demonstrate that the proposed system can achieve good accuracy and sub second latency in real world conditions.
Context agnostic trajectory prediction based on λ
Future Generation Computer Systems, 2019 · 12 citations · Open Access
A comparison of supervised learning schemes for the detection of search and rescue (SAR) vessel patterns
GeoInformatica, 2019 · 10 citations · Open Access
Preliminary Inter‑comparison of AIS Data and Optimal Ship Tracks
TransNav the International Journal on Marine Navigation and Safety of Sea Transportation, 2019 · 9 citations · Open Access
Abstract
Presentation given at TransNav2019, the 13th International Conference on Marine Navigation and Safety of Sea Transportation, Gdynia (Poland), http://transnav2019.am.gdynia.pl/, and awarded with the "best presentation award". Related paper is: http://www.transnav.eu/Article_Preliminary_Inter-comparison_of_,49,874.html Funding: H-2020 AtlantOS and BigDataOcean, IT-HR Interreg GUTTA.
Interactive Extreme‑Scale Analytics: Towards Battling Cancer
IEEE Technology and Society Magazine, 2019 · 7 citations · Open Access
Abstract
A synergetic understanding of cancer evolution and the effect of combination drug therapies on the disease is the cornerstone for developing effective personalized treatments, which can radically improve patients' well-being and their quality of (work and social) life. By extension, improving the treatment of patients indirectly enhances the quality of life for families, friends, and careers. Moreover, personalizing effective therapeutic approaches reduces treatment duration, cutting down healthcare monetary costs, which can be redirected to other health and social services. Given that three out of four U.S. families will at some point experience a family member suffering from cancer (http://natamcancer.org/NAP_Native_American_Priorities.pdf), the potential impact of improved cancer treatment is of considerable socio-economic and organizational significance.
Energy Efficient Motion Design and Task Scheduling for an Autonomous Vehicle
Proceedings of the ... International Conference on Engineering Design, 2019 · 4 citations · Open Access
Abstract
Abstract This paper describes an approach for designing an energy efficient motion and task scheduling for an autonomous vehicle which is moving in complicated environments in industrial sector or in large warehouses. The vehicle is requested to serve a number of workstations while moving safely and efficiently in the environment. In the proposed approach, the overall problem is formulated as a constraint optimization problem by using the Bump-Surface concept. Then, a Pareto-based multi- objective optimization strategy is adopted, and a modified genetic algorithm is developed to determine the Pareto optimum solution. The efficiency of the developed method is investigated and discussed through simulated experiments.
BigDataOcean Project: Early anomaly detection from big maritime vessel traffic data
Zenodo (CERN European Organization for Nuclear Research), 2019 · 1 citation · Open Access
Abstract
This paper discusses the concept and results of the BigDataOcean project, and specifically the anomaly detection pilot. While in the past, surveillance had suffered from a lack of data, current tracking technologies have transformed the problem into one of an overabundance of information, with needs which go well beyond the capabilities of traditional processing and algorithmic approaches. The major challenge faced today is developing the capacity to identify patterns emerging within huge amounts of data, fused from various sources and detecting outliers in a timely fashion, to act proactively and minimise the impact of possible threats. Within this context we first define an “anomaly”, before proceeding to present the BigDataOcean anomaly detection service; a service for the classification and early detection of anomalous vessel patterns. The service makes use of state-of-the-art big data technologies and novel algorithms which form the basis for a service capable of real time anomaly detection.
Vessel Profile Indicators using Fuzzy Logic Reasoning and AIS
Zenodo (CERN European Organization for Nuclear Research), 2019 · Open Access
Abstract
Early vessel profiling and risk assessment is a critical component of advanced maritime tracking systems, required by a number of maritime stakeholders including custom controls, port authorities, coastguards and others. This paper reports on the development of a fuzzy logic reasoning tool for generating maritime vessel profile indicators through the Automatic Identification System (AIS). The report describes the need and the underlying statistical methods applied, which are based on Fuzzy Logic Reasoning, for finding potential profile indicators and classifying vessels to a degree of “risk”, thus requiring further examination and monitoring. Under conservative assumptions, some preliminary results about the probabilities and boundaries of potential indicators are presented and discussed.
Anonymised AIS dataset
Zenodo (CERN European Organization for Nuclear Research), 2019 · Open Access
Abstract
This dataset contains anonymised ships' information, of a number of vessels traveling towards the Port of Rotterdam collected though the Automatic Identification System by MarineTraffic.
Anonymised AIS dataset
Zenodo (CERN European Organization for Nuclear Research), 2019 · Open Access
Abstract
This dataset contains anonymised ships' information, of a number of vessels traveling towards the Port of Rotterdam collected though the Automatic Identification System by MarineTraffic.
Mission Design of Mobile Manipulators in Cluttered Environments for Service Applications
IGI Global eBooks, 2019
Abstract
The purpose of this paper is to present a mission design approach for a service mobile manipulator which is moving and manipulating objects in partly known indoor environments. The mobile manipulator is requested to pick up and place objects on predefined places (stations). The proposed approach is based on the Bump-Surface concept to represent robot's environment through a single mathematical entity. The solution of the mission design problem is searched on a higher dimension Bump-Surface in such a way that its inverse image into the actual robot environment satisfies the given objectives and constraints. The problem's objectives consist of determining the best feasible paths for both the mobile platform and for the manipulator's end-effector so that all the stations are served at the lowest possible cost. Simulation examples are presented to show the effectiveness of the presented approach.
Countering Real‑Time Stream Poisoning: An Architecture for Detecting Vessel Spoofing in Streams of AIS Data
2018 · 30 citations · Open Access
Abstract
Well poisoning is an ancient war stratagem which was frequently used as a "scorched earth tactic". Today this tactic has been adapted by malicious attackers to the digital world and evolved into "stream poisoning", in which corrupt or fallacious data is injected into a data lake, so as to corrupt the integrity of the information stored there. Numerous maritime surveillance systems nowadays rely on the Automatic Identification System (AIS), which is compulsory for vessels over 299 Gross Tones, for vessel tracking purposes. Ship AIS spoofing involves creating a nonexistent vessel or masquerading a vessel's true identity, resulting in hiding or transmitting false positional data, so that a vessel appears to behave legitimately, thus deceiving stakeholders and authorities. Due to the volume and velocity of data received traditional approaches fail to automatically detect these spoofing events in real time. We focus on an industrial use case of detecting spoofing events in AIS streams and validate our approach in real world conditions.
The DEBS 2018 Grand Challenge
2018 · 21 citations
Abstract
The ACM DEBS 2018 Grand Challenge is the eighth in a series of challenges which seek to provide a common ground and evaluation criteria for a competition aimed at both research and industrial event-based systems. The focus of the 2018 Grand Challenge is on the application of machine learning to spatio-temporal streaming data. The goal of the challenge is to make the naval transportation industry more reliable by providing predictions for vessels' destinations and arrival times. This paper describes the specifics of the data streams and queries that define the DEBS 2018 Grand Challenge. It also describes the benchmarking platform that supports testing of corresponding solutions.
A Stream Reasoning System for Maritime Monitoring
DROPS (Schloss Dagstuhl – Leibniz Center for Informatics), 2018 · 17 citations · Open Access
Abstract
We present a stream reasoning system for monitoring vessel activity in large geographical areas. The system ingests a compressed vessel position stream, and performs online spatio-temporal link discovery to calculate proximity relations between vessels, and topological relations between vessel and static areas. Capitalizing on the discovered relations, a complex activity recognition engine, based on the Event Calculus, performs continuous pattern matching to detect various types of dangerous, suspicious and potentially illegal vessel activity. We evaluate the performance of the system by means of real datasets including kinematic messages from vessels, and demonstrate the effects of the highly efficient spatio-temporal link discovery on performance.
Composite Event Patterns for Maritime Monitoring
2018 · 11 citations · Open Access
Abstract
Maritime monitoring systems support safe shipping as they allow for the real-time detection of dangerous, suspicious and illegal vessel activities. We have been developing a composite event recognition system for maritime monitoring in the Event Calculus, allowing both for verification and real-time performance. To increase the accuracy of the system, we have been collaborating with domain experts in order to construct effective patterns of maritime activity. We present some indicative patterns in the Event Calculus, and evaluate them using two forms of real kinematic vessel data.
Mining Vessel Trajectory Data For Patterns Of Search And Rescue
Zenodo (CERN European Organization for Nuclear Research), 2018 · 10 citations · Open Access
Abstract
The overall aim of this work is to explore the possibility of automatically detecting Search And Rescue (SAR) activity, even when a distress call has on yet been received. For this, we exploit a large volume of historical Automatic Identification System (AIS) data so as to detect SAR activity from vessel trajectories, in a scalable, data-driven supervised way, with no reliance on external sources of information (e.g. coast guard reports). Specifically, we present our approach which is based on a parallelised, nonparametric statistical method (Random Forests), which has proved capable of achieving prediction accuracy rates higher than 77%.
On Designing Near‑Optimum Paths on Weighted Regions for an Intelligent Vehicle
International Journal of Intelligent Transportation Systems Research, 2018 · 7 citations
Real Time Autonomous Maritime Navigation using Dynamic Visibility Graphs
2018 IEEE/OES Autonomous Underwater Vehicle Workshop (AUV), 2018 · 6 citations
Abstract
In recent years, there has been a growing interest in autonomous self-guided vessels, for a wide range of application domains such as scientific research, ocean resource exploration, transportation and other. In this paper we explore one of the most critical components of autonomous vessels, intelligent transportation and motion planning, and propose an automatic collision avoidance methodology, applicable to both unmanned surface or underwater vessels operating on the sea surface, using Dynamic Visibility Graphs while respecting the International Regulations for Preventing Collisions at Sea (known as COLREGS). The efficiency of the developed method is investigated and discussed through characteristic simulated experiments.
Optimal Task Placement in a Metamorphic Manipulator Workspace in the Presence of Obstacles
Mechanisms and machine science, 2018 · 4 citations
Time‑optimal trajectory planning for hyper‑redundant manipulators in 3D workspaces
Robotics and Computer-Integrated Manufacturing, 2017 · 79 citations
Intelligent security on the edge of the cloud
2017 International Conference on Engineering, Technology and Innovation (ICE/ITMC), 2017 · 27 citations
Abstract
Edge or Fog computing is a relatively new architectural deployment model, ideally fit for the unique requirements of the Internet of Things. This paper presents a novel solution, which leverages the architectural characteristics of edge computing for security reasons. Machine learning models (specifically Support Vector Machines) are employed on the edge of the cloud, to perform low footprint unsupervised learning and analysis of sensor data for anomaly detection purposes. To this end, a proof of concept system is developed, capable of detecting anomalies in real world vessel sensor streams (big data) in a smart port environment. We report on early results, that validate the potential of the solution. The quality and performance of the model is investigated in real world conditions.
A Big Data Driven Approach to Extracting Global Trade Patterns
Lecture notes in computer science, 2017 · 26 citations
Knowledge extraction from maritime spatiotemporal data: An evaluation of clustering algorithms on Big Data
2017 · 12 citations
Abstract
In this paper we attempt to define the major trade routes which vessels of trade follow when travelling across the globe in a scalable, data-driven unsupervised way. For this, we exploit a large volume of historical AIS data, so as to estimate the location and connections of the major trade routes, with minimal reliance on other sources of information. We address the challenges posed due to the volume of data by leveraging distributed computing techniques and present a novel MapReduce based algorithmic approach, capable of handling skewed and nonuniform geospatial data. In the direction, we calculate and compare the performance (execution time and compression ratio) and accuracy of several mature clustering algorithms and present preliminary results.
Maritime data technology landscape and value chain exploiting oceans of data for maritime applications
2017 International Conference on Engineering, Technology and Innovation (ICE/ITMC), 2017 · 9 citations
Abstract
Maritime areas covers a large percentage of our world, being most of this area unexplored. Despite this, the sea has one of the most valuable and mostly exploited “economic platforms” of mankind, with applications in different sectors (as fishing industry, transportation cargo, etc.). Although this situation and the great evolution in technology can contribute to better know of the sea, this has not been happening. Given that a systematic collection of maritime data has already been carried out, yet is still dispersed and not used in its entirety. This is one of the objectives of the H2020 BigDataOcean project (http://www.bigdataocean.eu/site/), collecting the various data sources and thus being able to treat them together in order to obtain better results. This paper presents the analysis of the current landscape of big data, starting from the identification of existing ones, used tools and methodologies to be integrated in the project services, and platform with the aim of retrieving and analyzing the maritime data is presented. Then, the requirement engineering methodology is presented, being the methodology used during the project to identify the stakeholders, data sources, data value chain and the technologic gaps, resulting the in the identification of the first iteration of the requirements.
Distributing N‑Gram Graphs for Classification
Communications in computer and information science, 2017 · 4 citations
Adaptive neuro fuzzy inference system for vessel position forecasting
2017 International Conference on Engineering, Technology and Innovation (ICE/ITMC), 2017 · 1 citation
Abstract
In this work, we present a novel approach for short-term vessel movement predictions in real world maritime conditions, based on an Adaptive Neuro Fuzzy Inference System. The proposed system uses real world vessel position recordings, reported by the Automatic Identification System and is capable of highly accurate future vessel position forecasting (Latitude and Longitude). The obtained results of the Adaptive Neuro Fuzzy Inference System model are compared with those of related statistical geospatial time series forecasting models, such as ARIMA and Artificial Neural Networks in order to validate the effectiveness of the proposed approach.
Special issue on ``Software architectures and systems for real time data stream analytics''
Journal of Systems and Software, 2017
Accessible museum collections for the visually impaired
2016 · 65 citations
Abstract
This paper describes an affordable approach and prototype system that can enhance the accessibility of museum exhibits to visually impaired users. The approach supports the navigation in exhibition halls and the tactual exploration of exhibit replicas using touch-sensitive audio descriptions and touch gestures on a mobile device. The required technology includes 3D printed exhibits, attached touch sensors, Arduino boards, and a respective mobile app. A preliminary usability evaluation with ten users (blind, visually impaired and blindfolded) revealed a positive user experience with satisfactory and similar performance.
A distributed approach to estimating sea port operational regions from lots of AIS data
2016 · 32 citations
Abstract
Seaports play a vital role in the global economy, as they operate as the connection corridors to all other modes of transport and as engines of growth for the wider region. But ports today are faced with numerous unique challenges and for them to remain competitive, significant investments are required. In support of greater transparency in policy making, decisions regarding investment need to be supported by data-driven intelligence. It is often an overlooked fact that seaports do not remain static over time; such spatial units often evolve according to environmental patterns both in size but also connectivity and operational capacity. As such any valid decision making regarding port investment and policy making, essentially needs to take into account port evolution over time and space. In this work, we leverage the huge amounts of vessel data that are progressively becoming available through the Automatic Identification System (AIS) and distributed machine learning to define a seaport's extended area of operation. Specifically, we present our adaptation of the well-known KDE algorithm to the map-reduce paradigm, and report results on the port of Shanghai.
Collaborative CAD/CAE as a cloud service
International Journal of Systems Science Operations & Logistics, 2016 · 18 citations
Abstract
These days manufacturing and design teams continuously collaborate with colleagues across traditional office boundaries and manufacturing floors in an effort to meet with growing demand and competition at a global scale. An essential tool for this industry is computer-aided design and engineering (CAD/CAE) software, which, unfortunately, was never designed to address complex collaboration requirements. Now more than ever, there is a growing need for service-oriented collaborative CAD/CAE solutions, essentially moving away from the high performance single user and machine solutions of the past and towards more portable service-based multi-user systems. The aim of this paper is twofold; first, we examine the domains literature with the goal of documenting a complete set of software requirements, which will map the design of collaborative CAD/CAE solutions, and, second, we present our novel architecture and implementation details of a collaborative CAD/CAE system deployed as a cloud service. Our main focus is on the remote visualisation component of the solution and the practical architectural deployment capable of overcoming software performance, interoperability, modularity, compatibility, scalability and interface interactivity challenges. We validate our architecture in the field by deploying an industry-defined proof-of-concept visualisation system used for the determination and optimisation of the design parameters of professional footwear.
A pervasive role‑playing game for introducing elementary school students to archaeology
2016 · 16 citations
Abstract
This paper presents ongoing work on the design and prototyping of a pervasive, role-playing game for elementary school students. The game takes place in a designated space presented as an excavation site, in which students become acquainted with a number of principal roles and tasks taking place in archaeological fieldwork. The educational goals are to introduce students to fundamental archaeology concepts and to inform them about the historical background of a specific site and the discovered artifacts. The game apparatus consists of a mobile application (android), a number of small wireless sensors (beacons), tangible models of the antiquities and simplified prop tools of the archaeological equipment (3D printed). The paper outlines the main design concepts, technologies used and gameplay and reports on a preliminary evaluation.
Computing collision‑free motions for a team of robots using formation and non‑holonomic constraints
Robotics and Autonomous Systems, 2016 · 15 citations
Scalable and Distributed Sea Port Operational Areas Estimation from AIS Data
2016 · 10 citations
Abstract
Seaports are spatial units that do not remain static over time. They are constantly in flux, evolving according to environmental and connectivity patterns both in size and operational capacity. As such any valid decision making regarding port investment and policy making, essentially needs to take into account port evolution over time and space, thus, accurately defining a seaport's exact location, operational boundaries, capacity, connectivity indicators, environmental impact and overall throughput. In this work, we apply a data driven approach to defining a seaport's extended area of operation based on data collected though the Automatic Identification System (AIS). Specifically, we present our adaptation of the well-known KDE algorithm to the MapReduce paradigm, and report results on the port of Rotterdam.
Path Planning for Formation Control of Autonomous Vehicles
Advances in intelligent systems and computing, 2016 · 6 citations · Open Access
Foot Plantar Pressure Estimation Using Artificial Neural Networks
IFIP advances in information and communication technology, 2016 · 5 citations · Open Access
Dynamic graph management for streaming social media analytics
2016 · 3 citations
Abstract
We present a system for analytics on streaming social media that computes the most active posts, based on the age and the amount of comments for each post, and tracks the largest communities that comprise friends that are fond of the same content. To deal with high velocity data streams, we implemented an algorithm for incrementally updating graphs expressing social networks. The evaluation of our system is based on the datasets of the DEBS 2016 challenge.
Mission Design of Mobile Manipulators in Cluttered Environments for Service Applications
International Journal of Robotics Applications and Technologies, 2016 · 1 citation
Abstract
The purpose of this paper is to present a mission design approach for a service mobile manipulator which is moving and manipulating objects in partly known indoor environments. The mobile manipulator is requested to pick up and place objects on predefined places (stations). The proposed approach is based on the Bump-Surface concept to represent robot's environment through a single mathematical entity. The solution of the mission design problem is searched on a higher dimension Bump-Surface in such a way that its inverse image into the actual robot environment satisfies the given objectives and constraints. The problem's objectives consist of determining the best feasible paths for both the mobile platform and for the manipulator's end-effector so that all the stations are served at the lowest possible cost. Simulation examples are presented to show the effectiveness of the presented approach.
Real‑time vessel behavior prediction
Evolving Systems, 2015 · 76 citations · Open Access
A cloud based architecture capable of perceiving and predicting multiple vessel behaviour
Applied Soft Computing, 2015 · 74 citations
Path Planning and scheduling for a fleet of autonomous vehicles
Robotica, 2015 · 29 citations
Abstract
SUMMARY This paper presents a new solution approach for managing the motion of a fleet of autonomous vehicles (AVs) in indoor factory environments. AVs are requested to serve a number of workstations (WS) (following a specified desired production plan for materials requirements) while taking into account the safe movement (collisions avoidance) in the shop floor as well as time duration and energy resources. The proposed approach is based on the Bump-Surface concept to represent the 2D environment through a single mathematical entity. The solution of the combined problem of path planning and task scheduling is searched on a higher-dimension B-surface (in our case 3D) in such a way that its inverse image into the robot environment satisfies the given objectives and constraints. Then, a modified Genetic Algorithm (GA) is used to search for a near-optimum solution. The objective of the fleet coordination consists of determining the best feasible paths for the AVs so that all the WS are served at the lowest possible cost. The efficiency of the developed method is investigated and discussed through characteristic simulated experiments concerning a variety of operating environments.
Predicting Object Trajectories from High‑Speed Streaming Data
2015 IEEE Trustcom/BigDataSE/ISPA, 2015 · 9 citations
Abstract
Huge amounts of loosely structured and high velocity data are now being generated by ubiquitous mobile sensing devices, aerial sensory systems, cameras and radiofrequency identification readers, which are generating key knowledge into social media behaviors, intelligent transport patterns, military operational environments and space monitoring, safety systems etc. Machine learning models and data mining techniques can be employed to produce actionable intelligence, based on predictive and prescriptive analytics. However, more data is not leading to better predictions as the accuracy of the implicated learning models hugely varies in accordance to the complexity of the given space and related data. Especially in the case of open-ended data streams of massive scale, their efficiency is put to the challenge. In this work, we employ a variety of machine learning methods and apply them to geospatial time-series surveillance data, in an attempt to determine their capacity to learn a vessels behavioral pattern. We evaluate their effectiveness against metrics of accuracy, time and resource usage. The main concept of this study is to determine the most appropriate machine-learning model capable of learning a vessels behavior and performing predictions into a future point in time. Our aim is to document the prediction accuracy of a set of traditional forecasting models and then compare this to the prediction accuracy of streaming algorithms.
Towards a Foot Bio‑model for Performing Finite Element Analysis for Footwear Design Optimization using a Cloud Infrastructure
Computer-Aided Design and Applications, 2015 · 3 citations
Abstract
Computer-Aided Design and Applications is an international journal on the applications of CAD and CAM. It publishes papers in the general domain of CAD plus in emerging fields like bio-CAD, nano-CAD, soft-CAD, garment-CAD, PLM, PDM, CAD data mining, CAD and the internet, CAD education, genetic algorithms and CAD engines. The journal is aimed at all developers and users of CAD technology to ptovide CAD solutions for various stages of design and manufacturing. The journal publishes all about Computer-Aided Design and Computer-Aided technologies.
The Inherent Difficulties and Complexities of Voting Electronically
IGI Global eBooks, 2015
Abstract
Countries worldwide have been conducting trials and holding pilots to evaluate the benefits and detriments of introducing electronic voting; while some have successfully implemented state of the art voting solutions, others have decided to abandon such attempts altogether. Across the field, one can see a multitude of different approaches, revealing the wide diversification of political cultures, legal regulations, social requirements, and contexts, within which this technology must be deployed. The approaches adopted can thus seem to be contradictory or indeed diametrically opposed. The purpose of this chapter is thus twofold. Firstly, it attempts to provide an introduction to the field of electronic voting while reviewing the most recent advances and related literature. Secondly, it attempts to evaluate under a perspicacious vision the level of maturity of the technology.
Motion Planning and Scheduling with Stochastic Demands
Advances in intelligent systems and computing, 2015
Mission Design of a Team of Service Robots
Advances in computational intelligence and robotics book series, 2015
Abstract
The purpose of this chapter is to present an integrated approach for Mission Design of a team of Service Robots that is operating in partially known indoor environments such as libraries, hospitals, or warehouses. The robots are requested to serve a number of service stations while taking into account movement safety and other kinematical constraints. The Bump-Surface concept is used to represent the robots' environment through a single mathematical entity and an optimization problem is formulated representing an aggregation of paths length and movement constraints. Then a modified Genetic Algorithm with parallel populations is used for solving the problem of mission design of a team of service robots on the constructed Bump-Surface. Three simulation examples are presented to show the effectiveness of the presented approach.
EasyLexia: A Mobile Application for Children with Learning Difficulties
Procedia Computer Science, 2014 · 146 citations · Open Access
Abstract
Dyslexia is one of the most common learning disabilities experienced by children and adults. A large amount of research is currently being conducted in exploring the benefits of using Information & Communication Technologies as a learning platform for individuals and especially children with such learning difficulties. Given the potential benefits, we focused on developing a mobile application which could foster learning and help children improve some of their fundamental skills, such as reading comprehension, orthographic coding, short-term memory and mathematical problem solving. We attempted to design a stimulating and interactive experience for children, which could encourage the learning process. Our main focus was to assess the usability of the technology, evaluate how it affects the learning experience, its consequences and the benefits it offers to each user. In this paper we present the methodology, environment setup, design choices, implementation and the results of our preliminary evaluation and assessment of “EasyLexia”, a mobile application for children with learning difficulties. Preliminary results show the promising prospects mobile learning holds in such contexts.
EasyLexia 2.0: Redesigning our mobile application for children with learning difficulties
2014 · 13 citations
Abstract
Dyslexia is one of the most common learning difficulties affecting approximately 15 to 20 per cent of the world’s population. A large amount of research is currently being conducted in exploring the potential benefits of using Information & Communication Technologies as a learning platform for individuals and especially children with such difficulties. We focused on developing an application, which could improve children’s fundamental skills, such as reading comprehension, orthographic coding, short-term memory and mathematical problem solving through game playing. In search of stimulating and interactive learning experiences, we first designed and developed a mobile phone application for children with dyslexia. The main core of our research was to assess the usability of the technology and evaluate its effects. We have presented initial research results regarding EasyLexia, a mobile application for children with learning difficulties. In the meantime, tablets and touch screen portable devices were rising in popularity amongst students, leading us on to question whether bigger screens and more processing powered devices could enhance interactivity, usability and overall engagement. In this paper we improve upon our previous research, and present design choices and implementation details of a tablet based game for children with learning difficulties, whilst comparing our evaluation results to our previous research conclusions.
Time Sub‑Optimal Path Planning for Hyper Redundant Manipulators Amidst Narrow Passages in 3D Workspaces
Mechanisms and machine science, 2014 · 4 citations
The Inherent Difficulties and Complexities of Voting Electronically
Advances in electronic government, digital divide, and regional development book series, 2014 · 1 citation
Abstract
Countries worldwide have been conducting trials and holding pilots to evaluate the benefits and detriments of introducing electronic voting; while some have successfully implemented state of the art voting solutions, others have decided to abandon such attempts altogether. Across the field, one can see a multitude of different approaches, revealing the wide diversification of political cultures, legal regulations, social requirements, and contexts, within which this technology must be deployed. The approaches adopted can thus seem to be contradictory or indeed diametrically opposed. The purpose of this chapter is thus twofold. Firstly, it attempts to provide an introduction to the field of electronic voting while reviewing the most recent advances and related literature. Secondly, it attempts to evaluate under a perspicacious vision the level of maturity of the technology.
Comparative study of in‑store mobile commerce applications and feature selection, targeted at enhancing the overall shopping experience
2014
Abstract
Various kinds of mobile applications have emerged as a result of these advances and are penetrating our everyday life, changing human behaviors, and generating important social and economic impacts (Xu et al. 2008). Among these efforts, mobile applications for shopping come at the intersection of ubiquitous computing and electronic commerce and are gaining attention from both communities (Xu et al. 2008). Prior work though has mostly focused on the transactional functions of mobile phones and information consumption on-the-go and less on the experiential aspect of shopping and how this can be improved via the use of wireless devices (Xu et al. 2008). Nowadays, there is a fundamental blurring of the boundaries between online and off-line shopping (Gish 2012). Smartphones are fundamentally changing how people shop, browse, use coupons, find locations, and enter local and near field promotions. Shopping behavior is changing and showrooming and snacking (shopping in a spare five minutes) are increasing (Gish 2012). The real and the virtual world are converging into a complete shopping experience. It is becoming typical user behavior for consumers when in stores to go for their handheld devices in search of additional product information, better prices, and location information in an attempt to speed up the overall shopping process and gain a better shopping experience.
Task scheduling and motion planning for an industrial manipulator
Robotics and Computer-Integrated Manufacturing, 2013 · 62 citations
The Results of Closed Intramedullary Nailing for Intra‑articular Distal Tibial Fractures
Journal of Orthopaedic Trauma, 2013 · 13 citations
Abstract
Therapeutic level IV. See instructions for authors for a complete description of levels of evidence.
Trust coercion in the name of usable public key infrastructure
Security and Communication Networks, 2013 · 4 citations
Abstract
ABSTRACT We are currently witnessing an alarmingly increasing array of attacks on secure infrastructures used for industrial and commercial purposes. The success of these attacks has relied heavily on an innovative stratagem. This stratagem makes use of digital certificates to devise malicious code or servers as trustworthy, ultimately deceiving end users. This has led to an escalating demand for forged or stolen valid digital certificates on the electronic black market. Certification authorities (CAs) themselves are now coming under fire. Virus reports have surfaced on malicious software whose sole purpose was to grab certificates from within certain CAs' infrastructures. The growing popularity of these attacks is putting in doubt the effectiveness of one of the pillars upon which security in the digital world is built, cryptography and digital signatures. What is to blame? In a phrase, “Trust by default”. To increase the usability of public key infrastructure interactions, a number of CAs are pre‐included in users' browsers and operating systems. These entities are trusted by default, and this trust is now being exploited. In this paper, we shall try to shed light on the true dimensions and implications of “trust by default” in public key infrastructure environments. We attempt to raise awareness about the severity of this kind of attacks, demystify the security challenges and identify unique security threats. We need to ring the alarm about trust‐related issues in online communications. We analyze the issue from an information and communication security perspective and explore the notion of trust relations in this context. We support the doctrine that trust should be built on informed judgment, and this can only be achieved through increased openness. Following this, we put forward for consideration a number of proposals that attempt to overcome the issue at hand, by increasing user‐side awareness and thus solution effectiveness, regarding digital certificate transactions. We present an experimental mechanism that is able to provide users with customized digital certificate repositories based on an open crowd sourcing method. Copyright © 2013 John Wiley & Sons, Ltd.
Continuous curvature constrained shortest path for a car‑like robot using S‑Roadmaps
2013 · 4 citations
Abstract
This paper proposes a new approach for motion planning for a car-like robot which is based on a surfaced roadmap concept. A major advantage of our approach is that, it enables the same roadmap to be efficiently utilized for car-like robots with different kinematical constraints or with different starting and ending points. Our approach first represents the 2D environment using the B-Surface concept. Then, build a roadmap onto the B-Surface which does not incorporate any kinematical constraints. The paths encoded in the roadmap consist of poly-geodesic segments. The roadmap assists in the optimization and smoothing of these paths using NURBS curves. We also demonstrate experimental results for a simple model of a car-like robot moving on 2D environments.
Design and Development Guidelines for Real‑Time, Geospatial Mobile Applications: Lessons from ‘MarineTraffic’
Lecture notes in computer science, 2013 · 2 citations
Mission Planning of Mobile Robots and Manipulators for Service Applications
IGI Global eBooks, 2013 · 1 citation
Abstract
The purpose of this chapter is to present a mission planning approach for a service robot, which is moving and manipulating objects in semi-structured and partly known indoor environments such as stores, hospitals, and libraries. The recent advances and trends in motion planning and scheduling of mobile robots carrying manipulators are presented. This chapter adds to the existing body of knowledge of motion planning for Service Robots (SRs), an approach that is based on the Bump-Surface concept. The Bump-Surface concept is used to represent the entire robot’s environment through a single mathematical entity. Criteria and constraints for the mission planning are adapted to the service robots. Simulation examples are presented to show the effectiveness of the presented approach.
Is cloud computing finally beginning to mature?
International Journal of Cloud Computing and Services Science (IJ-CLOSER), 2012 · 12 citations
Abstract
The buzz term that came into popularity in the beginning of 2006 to describe an innovative IT deployment architecture, originated from the metaphor that was used to represent the Internet in various network diagrams as early as the 1990s. In a short period of time after the term appeared, solutions were being rapidly marketed by many IT companies and various new buzz words came into vogue such as cloud in a can, cloud bursting, and we suddenly had “blue clouds”, “green clouds”, “white label services” and many others. We witnessed what is now being labeled as cloud washing, the attempts of many vendors to strap the term onto their traditional products, which became the source of huge disambiguation, conflicts and misunderstandings. Today, the term “cloud computing” is everywhere. A quick search on Google for the term “cloud computing” will return 267 million search results. Cloud computing is being marketed as the complex-free efficient method of accessing huge amounts of computing and storage as a service. Behind the curtains though, computing has often been called a huge leap of faith and concerns were fuelled when reports started to surface of random failures (e.g. power outages) and shortcomings of infrastructures. Small black clouds of uncertainty have appeared in the otherwise clear skies of computing
INTEGRATING PATH PLANNING, ROUTING, AND SCHEDULING FOR LOGISTICS OPERATIONS IN MANUFACTURING FACILITIES
Cybernetics & Systems, 2012 · 6 citations
Abstract
Abstract This article considers the following manufacturing/logistics problem: an autonomous vehicle (AV) is requested to serve a set of pickup and delivery (P/D) stations in the shop floor of a modern factory providing P/D tasks while moving safely (i.e., avoiding any collision with obstacles) in its environment. A two-sided time window associated with each P/D station brackets the service time to within a specified interval. A tour for AV is considered legal if it (a) is collision free, (b) passes through each P/D station exactly once, and (c) satisfies the service time restrictions imposed by the P/D stations. A legal tour always starts and ends at a depot. The problem is thereby dual NP-hard because it combines the characteristics of path planning and those of vehicle routing and scheduling problems. The objective is to determine the shortest possible legal tour for AV. A new method is introduced to solve the problem accomplished in two successive phases: first, AV's environment is mapped into a 2D B-spline surface embedded in 3D Euclidean space using a robust geometric model. Then, the generated surface is searched using a genetic algorithm for an optimum legal tour that satisfies the requirements of the vehicle's mission. The performance of the proposed method is investigated and discussed through characteristic simulated experiments. KEYWORDS: autonomous vehiclesobstacle avoidancepath planningpickup and deliveryroutingscheduling
Cryptographic Dysfunctionality‑A Survey on User Perceptions of Digital Certificates
Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, 2012 · 3 citations
Mission Planning of Mobile Robots and Manipulators for Service Applications
IGI Global eBooks, 2012 · 2 citations
Abstract
The purpose of this chapter is to present a mission planning approach for a service robot, which is moving and manipulating objects in semi-structured and partly known indoor environments such as stores, hospitals, and libraries. The recent advances and trends in motion planning and scheduling of mobile robots carrying manipulators are presented. This chapter adds to the existing body of knowledge of motion planning for Service Robots (SRs), an approach that is based on the Bump-Surface concept. The Bump-Surface concept is used to represent the entire robot’s environment through a single mathematical entity. Criteria and constraints for the mission planning are adapted to the service robots. Simulation examples are presented to show the effectiveness of the presented approach.
Cryptographic Dysfunctionality‑A Survey on User Perceptions of Digital Certificates
2012 · 1 citation
Abstract
In this paper we identify and define cryptographic dysfunctionality and within this context we perform a study to evaluate user perceptions of public key cryptography concepts. The study makes use of user testing, questionnaires and wrap-up interviews with 121 young, but experienced Internet users during their interactions with selected secure Internet locations. The results show that the vast majority of users are not familiar with fundamental concepts of cryptography, and that they are not capable of efficiently managing digital certificates. This case study serves as first evidence supporting our hypothesis that user interface design is deteriorating cryptographic solutions effectiveness due to usability issues.
Leveraging the e‑passport PKI to Achieve Interoperable Security for e‑government Cross Border Services
Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, 2012 · 1 citation
A Systems Theory Approach to Electronic Voting Complexity
IGI Global eBooks, 2012 · 1 citation
Abstract
Information and Communication Technologies are being evaluated as an efficient and effective way to modernize the electoral process. These initiatives have initially been met with skepticism, as a number of affecting fields operate in concert, to structure what is perceived as the dimensions of electronic voting. This chapter adds to the existing body of knowledge on e-voting, while attempting to exorcise complexity and reevaluate under a perspicacious vision, the conflictual issues, by adopting a methodology with the ability to tackle highly unstructured problem settings. For this, systems theory is employed to provide a framework for perceiving and analyzing highly complex systems in an interdisciplinary method, as well as for designing within and for them. In this context, electronic voting is identified as a ’soft’ ill-structured human activity system, and soft systems thinking is applied to bring about improvement by resolving complex issues and providing a clearer perspective of related interdependencies.
Abstract
Information and Communication Technologies are being evaluated as an efficient and effective way to modernize the electoral process. These initiatives have initially been met with skepticism, as a number of affecting fields operate in concert, to structure what is perceived as the dimensions of electronic voting. This chapter adds to the existing body of knowledge on e-voting, while attempting to exorcise complexity and reevaluate under a perspicacious vision, the conflictual issues, by adopting a methodology with the ability to tackle highly unstructured problem settings. For this, systems theory is employed to provide a framework for perceiving and analyzing highly complex systems in an interdisciplinary method, as well as for designing within and for them. In this context, electronic voting is identified as a ’soft’ ill-structured human activity system, and soft systems thinking is applied to bring about improvement by resolving complex issues and providing a clearer perspective of related interdependencies.
Securing e‑Government and e‑Voting with an open cloud computing architecture
Government Information Quarterly, 2011 · 190 citations
Fair digital signing: The structural reliability of signed documents
Computers & Security, 2011 · 2 citations
Leveraging the e‑passport PKI to Achieve Interoperable Security for e‑government Cross Border Services.
2011
Abstract
Public Key Infrastructure is identified as the essential architecture upon which security and trust are built, in order to provide authentication, identity verification, encryption and non-repudiation in electronic transactions. Cross border availability of e-government services requires such a security infrastructure to provide a horizontal level of service across all implicated entities. This paper identifies the unique characteristics of a necessary interoperable security infrastructure and towards this goal explores the restrictions of current authentication approaches. Following this, the ability of the electronic passport PKI solution to extend and meet the demands of an interoperable cross border e-id solution is explored, as the requirements of such an authentication mechanism correlate to the characteristics of the deployed e-passport infrastructure. Finally, this paper proposes leveraging the e-passport infrastructure, to build a secure cross border authentication mechanism.
Addressing cloud computing security issues
Future Generation Computer Systems, 2010 · 1833 citations
Mission design for a group of autonomous guided vehicles
Robotics and Autonomous Systems, 2010 · 50 citations
Time‑Optimal Task Scheduling for Two Robotic Manipulators Operating in a Three‑Dimensional Environment
Proceedings of the Institution of Mechanical Engineers Part I Journal of Systems and Control Engineering, 2010 · 21 citations
Abstract
The present paper introduces a method for determining the optimal task scheduling for a two-robot work cell. This problem is reminiscent of the classic Travelling Salesman Problem (TSP), but the measure to be optimized is the time instead of the distance. In addition, this is a much more complex problem, since it involves two robots (salesmen), which have to visit different task-points (cities) considering the multiplicity of the robots' inverse kinematics. The optimization problem addressed in this work concerns the determination of the (near-)optimum sequence of task-points that should be visited by each one of the two robots while ensuring minimum total cycle time and collision avoidance among their links. The proposed approach is based on genetic algorithms and a special encoding is used to incorporate the division of the task-points for both robots and the multiple solutions of the inverse kinematics. The method was tested in different scenarios and the experimental results demonstrated the efficiency and effectiveness of the proposed approach.
A multigrid method for the estimation of geometric anisotropy in environmental data from sensor networks
Computers & Geosciences, 2010 · 11 citations
Time‑optimal task scheduling for articulated manipulators in environments cluttered with obstacles
Robotica, 2009 · 27 citations
Abstract
SUMMARY This paper proposes a new approach for solving a generalization of the task scheduling problem for articulated robots (either redundant or non-redundant), where the robot's 2D environment is cluttered with obstacles of arbitrary size, shape and location, while a set of task-points are located in the robot's free-space. The objective is to determine the optimum collision-free robot's tip tour through all task-points passing from each one exactly once and returning to the initial task-point. This scheduling problem combines two computationally NP-hard problems: the optimal scheduling of robot tasks and the collision-free motion planning between the task-points. The proposed approach employs the bump-surface (B-Surface) concept for the representation of the 2D robot's environment by a B-Spline surface embedded in 3D Euclidean space. The time-optimal task scheduling is being searched on the generated B-Surface using a genetic algorithm (GA) with a special encoding in order to take into consideration the infinite configurations corresponding to each task-point. The result of the GA's searching constitutes the solution to the task scheduling problem and satisfies optimally the task scheduling criteria and objectives. Extensive experimental results show the efficiency and the effectiveness of the proposed method to determine the collision-free motion among obstacles.
Vehicle scheduling in 2D shop floor environments
Industrial Robot the international journal of robotics research and application, 2009 · 17 citations
Abstract
Purpose The purpose of this paper is to develop an efficient method for solving a vehicle scheduling problem (VSP) in 2D industrial environments. An autonomous vehicle is requested to serve a set of work centers in the shop floor providing transport and delivery tasks while avoiding collisions with obstacles during its travel. The objective is to find a minimum in length, collision‐free vehicle routing schedule that serves timely as many as possible work centers in the shop floor. Design/methodology/approach First, the vehicle's environment is mapped into a 2D B‐Spline surface embedded in 3D Euclidean space using a robust geometric model. Then, a modified genetic algorithm is applied on the generated surface to search for an optimum legal route schedule that satisfies the requirements of the vehicle's mission. Findings Simulation experiments show that the method is robust enough and can determine in a reasonable computation time a solution to VSP under consideration. Originality/value There is a gap in the literature for methods that face VSP in shop‐floor environments. This paper contributes to filling this gap by implementing a practical method that can be easily programmed and included in a modern service delivery system.
Time Optimum Motion Planning for a Set of Car‑Like Robots
IFAC Proceedings Volumes, 2009 · 2 citations
Path Planning of Holonomic and Non‑Holonomic Robots Using Bump‑Surfaces
Computer-Aided Design and Applications, 2008 · 9 citations
Abstract
Haptic perception of fine surface features is a fundamental modality to identify virtual objects.Roughness and stickiness, which are modeled as surface textures and friction respectively, are the main characteristics in terms of haptics.This research is aimed at the haptic rendering method of fine surface features based on the analysis of the surface profile.Functionally generated surface features are employed for the haptic rendering of surface textures and surface friction.Haptic rendering of anisotropic surface -surface having a dominant feature direction, and haptic rendering of heterogeneous surface -surface with a varied feature density, are investigated.Experimental measurements and prototype system implementations have been done to show the fidelity of the proposed surface feature modeling methods.
ENHANCING SECURITY IN THE INTEGRATION OF E‑GOVERNMENT ‑ The e‑School Initiative
2008 · 2 citations · Open Access
Abstract
This paper presents a security infrastructure design which is implemented to ensure safety in the e-School initiative that can escalate to meet the requirements of the entire electronic government system. The eSchool initiative offers a number of ways that increase the effectiveness of education, student involvement in the process and is an element of the e-Government effort in Greece. A combination of existing technologies comprises the security solution presented, including Public Key Infrastructure, Shibboleth, Smart cards and Lightweight Directory Access Protocol. In this system, Pki is responsible for binding a public key to an entity, Ldap is the repository of keys and certificates and SSO is a method of access control that enables a user to authenticate once and gain access to the resources of multiple independent web
Systematic Detection of Anisotropy in Spatial Data Obtained from Environmental Monitoring Networks
2008
Abstract
The efficient mapping of environmental hazards requires the development of methods for the analysis of the spatial distributions sampled from environmental monitoring networks. We focus on the detection of the geometric (elliptic) anisotropy parameters of spatially distributed variables represented by means of random fields. The geostatistical estimation of anisotropy parameters often relies on empirical methods or maximum likelihood approaches that are impractical for large data sets. We present a non-parametric, computationally fast method for the identification of the anisotropy parameters of scalar random fields. The method uses sample based estimates of the spatial derivatives that are related through closed form expressions to the anisotropy parameters. We investigate the performance of the method on synthetic samples on regular and irregular supports. We estimate the anisotropy of radioactivity distributions (gamma dose rates) obtained from the EURDEP (EUropean Radiological Data Exchange Platform).
Two‑dimensional motion‑planning for nonholonomic robots using the bump‑surfaces concept
Computing, 2007 · 13 citations
Motion planning for multiple non‑holonomic robots: a geometric approach
Robotica, 2007 · 13 citations
Abstract
SUMMARY In this paper, a geometrical approach is developed to generate simultaneously optimal (or near-optimal) smooth paths for a set of non-holonomic robots, moving only forward in a 2D environment cluttered with static and moving obstacles. The robots environment is represented by a 3D geometric entity called Bump-Surface, which is embedded in a 4D Euclidean space. The multi-motion planning problem (MMPP) is resolved by simultaneously finding the paths for the set of robots represented by monoparametric smooth C 2 curves onto the Bump-Surface, such that their inverse images onto the initial 2D workspace satisfy the optimization motion-planning criteria and constraints. The MMPP is expressed as an optimization problem, which is solved on the Bump-Surface using a genetic algorithm. The performance of the proposed approach is tested through a considerable number of simulated 2D dynamic environments with car-like robots.
Motion planning control for multiple car‑like robots using the Bump‑Surface concept
2007 · 1 citation
Abstract
This paper presents a new approach for intelligent control of multiple car-like robots moving in a 2D environment cluttered with both static and moving obstacles. The objective is to determine simultaneously the global near-optimum collision-free path for each robot. The proposed approach consists of three main phases: The space-time is formulated to represent the moving obstacles as time-depended obstacles. Then, the Bump-Surface concept is used to represent the 3D Space-Time by a 3D B-Spline surface embedded in 4D Euclidean space. The robots motions are represented by 3D B-Spline curves on the 3D Bump-Surface and the global optimal paths are being searched on the generated Bump-Surface using a genetic algorithm (GA). The performance of the proposed approach is investigated through a large number of experiments in various simulated 2D dynamic environments.
Energy‑Minimizing Motion Design for Nonholonomic Robots Amidst Moving Obstacles
Computer-Aided Design and Applications, 2006 · 4 citations
Abstract
Computer-Aided Design and Applications is an international journal on the applications of CAD and CAM. It publishes papers in the general domain of CAD plus in emerging fields like bio-CAD, nano-CAD, soft-CAD, garment-CAD, PLM, PDM, CAD data mining, CAD and the internet, CAD education, genetic algorithms and CAD engines. The journal is aimed at all developers and users of CAD technology to ptovide CAD solutions for various stages of design and manufacturing. The journal publishes all about Computer-Aided Design and Computer-Aided technologies.
Force fields with one stable equilibrium for micropart 2D manipulation
Elsevier eBooks, 2006 · 3 citations
Path planning in weighted regions using the Bump‑Surface concept
Elsevier eBooks, 2006 · 3 citations
MOTION PLANNING AMIDST MOVING OBSTACLES USING THE BUMP‑HYPERSURFACE CONCEPT
IFAC Proceedings Volumes, 2006