This paper addresses short-term Collision-Risk-Aware ship route planning while utilizing a deep learning-based Vessel Collision Risk Assessment and Forecasting (VCRA/F) framework to quantify risks. Lacking a clear boundary between risky and viable routes, we propose a Pareto-optimal search for alternative routes, balancing collision risk and voyage time. Our main contribution is a novel framework that integrates VCRA/F for Pareto-optimal route queries in dynamic environments. We model maritime routes using a hexagon-based graph network on the sea. Our experiments on real-world AIS data validate the effectiveness of Skyline-VCRA/F while highlighting areas for further improvement.

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.

Abstract Predictive analytics over mobility data is of great importance since it can assist an analyst to predict events, such as collisions, encounters, traffic jams, etc. A typical example is anticipated location prediction, where the goal is to predict the future location of a moving object, given a look-ahead time. What is even more challenging is to be able to accurately predict collective behavioural patterns of movement, such as co-movement patterns as well as their course over time. In this paper, we address the problem of Online Prediction of Co-movement Patterns. Furthermore, in order to be able to calculate the accuracy of our solution, we propose a co-movement pattern similarity measure, which facilitates the comparison between the predicted clusters and the actual ones. Finally, we calculate the clusters’ evolution through time (survive, split, etc.) and compare the cluster evolution predicted by our framework with the actual one. Our experimental study uses two real-world mobility datasets from the maritime and urban domain, respectively, and demonstrates the effectiveness of the proposed framework.

The wide spread of the Automatic Identification System (AIS) and related tools has motivated several maritime analytics operations. One of the most critical operations for the purpose of maritime safety is the so-called Vessel Collision Risk Assessment and Forecasting (VCRA/F), with the difference between the two lying in the time horizon when the collision risk is calculated: either at current time by assessing the current collision risk (i.e., VCRA) or in the (near) future by forecasting the anticipated locations and corresponding collision risk (i.e., VCRF). Accurate VCRA/F is a difficult task, since maritime traffic can become quite volatile due to various factors, including weather conditions, vessel manoeuvres, etc. Addressing this problem by using complex models introduces a trade-off between accuracy (in terms of quality of assessment / forecasting) and responsiveness. In this paper, we propose a deep learning-based framework that discovers encountering vessels and assesses/predicts their corresponding collision risk probability, in the latter case via state-of-the-art vessel route forecasting methods. Our experimental study on a real-world AIS dataset demonstrates that the proposed framework balances the aforementioned trade-off while presenting up to 70% improvement in R2 score, with an overall accuracy of around 96% for VCRA and 77% for VCRF.

The massive-scale data generation of positioning (tracking) messages, collected by various surveillance means, has posed new challenges in the field of mobility data analytics in terms of extracting valuable knowledge out of this data. One of these challenges is online maritime awareness, where the goal is to monitor and ensure the safety of a fleet, including, among others, collision risk assessment. To address this challenge, we present VesselVision, a system that estimates, tracks, and visualizes vessels' collision risk. In particular, our system offers a unified solution that tracks vessels that are detected to be in encountering process and assess their corresponding collision risk over streaming AIS position data in an online fashion. The functionality of our system is demonstrated over popular real-world AIS datasets.

The wide spread of Automatic Identification System (AIS) and tools based on it has motivated several maritime analytics operations. One of the most critical operations for the purpose of maritime safety is the so-called Vessel Collision Risk Assessment (VCRA). Accurate VCRA is a challenging task as maritime traffic is quite volatile, often affected by external factors, such as weather, etc. Addressing this problem by using complex models introduces a trade-off between accuracy quality and responsiveness. On the other hand, Machine Learning (ML) methods can better address this tradeoff. In this paper, we study the VCRA problem from the ML perspective, by proposing an architecture based on the Multi-Layered Perceptron (MLP) model. Our preliminary experimental study over a large-scale AIS dataset shows that the proposed methodology outperforms the kinematic equations-based approach.

In this demo paper we present ST_VISIONS, an easy-to-use Python library for interactive visualizations of spatial and spatio-temporal datasets. By automating the low-level details of the underlying visualization library (Bokeh), ST_VISIONS allows data scientists to create interactive, map-based visualizations, by writing Python code at a higher level of abstraction. Consequently, we accelerate the task of visualization from different sources, while we support interactive filtering, colorization, as well as multiple graphs, for various types of spatial and spatio-temporal data.

The massive-scale data generation of positioning (tracking) messages, collected by various surveillance means, has posed new challenges in the field of mobility data analytics in terms of extracting valuable knowledge out of this data. One of these challenges is online cluster analysis, where the goal is to unveil hidden patterns of collective behaviour from streaming trajectories, such as co-movement and co-stationary (aka anchorage) patterns. Towards this direction, in this paper, we demonstrate MaSEC (Moving and Stationary Evolving Clusters), a system that discovers valuable behavioural patterns as above. In particular, our system provides a unified solution that discovers both moving and stationary evolving clusters on streaming vessel position data in an online mode. The functionality of our system is evaluated over two real-world datasets from the maritime domain.

The advent of GPS technologies generates location data-streams and accentuates the importance of developing practical tools that can process and analyze the vast amounts of location data at a given moment in a meaningful way. Profiling the trajectory of a moving object with respect to the trajectories of its surrounding objects, for example, can elicit its mobility behaviour and analyze it in order to inform domain experts with critical knowledge in real time. For instance, clustering multiple moving objects with respect to their spatial and temporal dimension to identify co-movement patterns. In this paper, we propose a novel graph-based online co-movement pattern mining algorithm, called EvolvingClusters, which can be used to discover different collective movement behaviours (like the well-known flocks and convoys) in a unified way based on the activity of multiple concurrent objects through time and space. We evaluate EvolvingClusters using real-world and synthetic datasets from multiple mobility domains. Our study demonstrates the effectiveness of the proposed algorithm as well as its value towards a tool to profile semantically rich behaviour and with capabilities to observe and categorize multiple moving objects in real-time.