DTS-MixNet: Dynamic Spatiotemporal Graph Mixed Network for Anomaly Detection in Multivariate Time Series

Anomaly detection in multivariate time series (MTS) remains challenging due to the presence of complex and dynamic spatiotemporal dependencies. To address this, we propose the <i>Dynamic Spatiotemporal Graph Mixed Network</i> (DTS-MixNet), which takes a sliding window data as input to predict the ne...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Chengxun Tan, Jiayi Hu, Jian Li, Minmin Miao, Wenjun Hu, Shitong Wang
Formato:	Artigo
Idioma:	Inglês
Publicado em:	MDPI AG 2025-09-01
coleção:	Big Data and Cognitive Computing
Assuntos:	multivariate time series anomaly detection graph neural networks spatiotemporal dependencies dynamic graph learning
Acesso em linha:	https://www.mdpi.com/2504-2289/9/10/245
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!