Review: Detection of abnormal movements of ships based on AIS data in water transport using machine learning methods

The table provides an insight into the scientific papers that dealt with the problem of anomalous movements of ships based on AIS data in water transport using machine learning methods. Anomaly detection in water transport refers to the process of identifying unusual or abnormal behavior in vessels or maritime activities. This can include detecting deviations from typical sailing patterns, unexpected changes in speed or direction, irregular stops or deviations from established routes, and other behaviors that do not conform to expected or normal maritime activities. Anomalies in water transport are significant as they can indicate potential safety hazards, security threats, or non-compliance with maritime regulations. Detecting and addressing anomalies is crucial for ensuring the safety, security, and efficiency of maritime traffic and transportation. Advanced anomaly detection methods, such as kinematic interpolation, Support Vector Machines (SVM), Random Forest, Neural Networks, k-means clustering, DBSCAN, Parallel Meta-Learning (PML) can be trained to detect anomalies by learning patterns from historical data and identifying deviations from these patterns. The aim of anomaly detection in water transport is to identify potential safety or security threats, such as illegal activities, accidents, or navigational errors, as well as to improve maritime situational awareness and operational efficiency. By leveraging machine learning methods, anomaly detection systems can help maritime authorities and operators identify and respond to abnormal vessel behavior in a timely manner, thereby enhancing overall maritime security and safety.