MSIF-SSTR: A “Quick smuggler” smuggling speedboat trajectory recognition method based on multi-source information fusion

Abstract

Cooperating with maritime administrative departments to identify smuggling activities and enhance the control ability of nearshore vessels holds significant practical significance. However, existing research mostly relies on basic AIS data and simple features, making it difficult to deal with complex vessel behaviors. Especially when identifying covert and flexible smuggling activities, it is prone to misjudgment and has limited effectiveness. In real-world enforcement, distinguishing truly suspicious “Quick Smuggler” smuggling from benign high-speed transit requires modeling subtle, deep-level spatio-temporal cues that couple motion dynamics with external conditions (e.g., wind, wave, visibility) and context. Simple linear mappings and shallow temporal encoders often overfit speed bursts or local detours, causing elevated false alarms. By contrast, dilated-convolutional receptive fields in TCNs capture multi-scale temporal dependencies efficiently, while KAN layers provide adaptive nonlinear function bases to fit complex, locally varying trajectory patterns. This synergy is particularly suited to covert nighttime operations under shifting sea states, where genuine smuggling exhibits trajectory micro-structures and weather-conditioned behaviors that are hard to emulate by normal craft. To address these challenges, this study proposes a Multi-Source Information Fusion-based “Quick Smuggler” Smuggling Speedboat Trajectory Recognition method (MSIF-SSTR). First, we construct the HN_BF dataset, comprising real-world nighttime radar trajectories from the Qiongzhou Strait and corresponding meteorological data. Next, parallel TCN networks are employed to separately extract motion features, and meteorological features, enabling the model to better capture global temporal dependencies during feature extraction. Finally, the fused features are fed into an LSTM for classification, while a Kolmogorov-arnold networks (KAN) module replaces traditional fully connected layers to improve the representation of complex trajectory patterns. Experimental results demonstrate that MSIF-SSTR achieves F1-scores exceeding 94.2% on the HN_BF dataset, outperforming state-of-the-art methods with higher computational efficiency. Field applications confirm the model’s robustness.