Chinese Journal of Ship Research, Volume. 19, Issue 2, 223(2024)
Ship trajectory anomaly detection method based on encoder-decoder architecture composed of Transformer_LSTM modules
Figures & Tables(9)
![[in Chinese]](/Images/icon/loading.gif){kind=icon}
Table 1. Comparison of abnormal detection results of multiple models
View tableView in ArticleTable 1. Comparison of abnormal detection results of multiple models
模型 准确率 精确率 召回率 F1分数 假阳率 LOF 0.5134 0.8845 0.3617 0.5134 0.3171 DBSCAN 0.5983 0.8887 0.4510 0.5983 0.3760 IForest 0.6504 0.9302 0.5000 0.6504 0.2727 VAE 0.7453 0.8786 0.6471 0.7453 0.2392 LSTM 0.7517 0.8809 0.6555 0.7517 0.2352 VAE_LSTM 0.8884 0.9481 0.8070 0.8719 0.1667 Transformer_LSTM 编解码器 0.9318 0.9347 0.9720 0.9530 0.1429
Tools
Get Citation
Copy Citation Text
Kexin LI, Jian GUO, Ranchong LI, Yujun WANG, Zongming LI, Kun MIU. Ship trajectory anomaly detection method based on encoder-decoder architecture composed of Transformer_LSTM modules[J]. Chinese Journal of Ship Research, 2024, 19(2): 223
Paper Information
Category: Weapon, Electronic and Information System
Received: Mar. 1, 2023
Accepted: --
Published Online: Mar. 18, 2025
The Author Email:
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20