Ship trajectory anomaly detection method based on encoder-decoder architecture composed of Transformer_LSTM modules

ObjectiveIn order to improve the accuracy and efficiency of ship trajectory anomaly detection, and solve the problems of traditional anomaly detection methods such as limited feature characterization ability, insufficient compensation accuracy, gradient disappearance and overfitting, an unsupervised...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Kexin LI, Jian GUO, Ranchong LI, Yujun WANG, Zongming LI, Kun MIU
Formato:	Artigo
Idioma:	Inglês
Publicado em:	Editorial Office of Chinese Journal of Ship Research 2024-02-01
coleção:	Zhongguo Jianchuan Yanjiu
Assuntos:	anomaly detection deep learning encoder-decoder transformer longshort-term memory (lstm) trajectory reconstruction
Acesso em linha:	http://www.ship-research.com/en/article/doi/10.19693/j.issn.1673-3185.03291
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!