Ship Anomalous Behavior Detection Based on BPEF Mining and Text Similarity

Journal of Marine Science and Engineering, Journal Year: 2025, Volume and Issue: 13(2), P. 251 - 251

Published: Jan. 29, 2025

Maritime behavior detection is vital for maritime surveillance and management, ensuring safe ship navigation, normal port operations, marine environmental protection, the prevention of illegal activities on water. Current methods detecting anomalous vessel behaviors primarily rely single time series data or feature point analysis, which struggle to capture relationships between behaviors, limiting anomaly identification accuracy. To address this challenge, we proposed a novel framework, called BPEF-TSD framework. It integrates pattern recognition algorithm, Smith–Waterman, text similarity measurement methods. Specifically, first introduced BPEF mining framework extract events from AIS data, then generated complete sequence chains through temporal combinations. Simultaneously, employed Smith–Waterman algorithm achieve local alignment test known sequences. Finally, evaluated overall based measure strategy, with vessels exceeding predefined threshold being flagged as anomalous. The results demonstrate that achieves over 90% accuracy in abnormal trajectories waters Xiamen Port, outperforming alternative such LSTM, iForest, HDBSCAN. This study contributes valuable insights enhancing safety advancing intelligent supervision while introducing research perspective big mining.

Language: Английский

A COLREGs compliance reinforcement learning approach for USV manoeuvring in track-following and collision avoidance problems

Ocean Engineering, Journal Year: 2024, Volume and Issue: 316, P. 119907 - 119907

Published: Dec. 2, 2024

Language: Английский