Automata Based Multivariate Time Series Analysis for Anomaly Detection over Sliding Time Windows

Engineering Proceedings

article

Arnold Hien¹  Nicolas Beldiceanu¹  Claude-Guy Quimper²  María-I. Restrepo¹ 

[1] Department of Automation, Production and Computer Sciences;Computer Science Department, Laval University

关键词: multivariate time series;    transducers;    sliding windows;    anomaly detection;   

DOI  :  10.3390/engproc2023039065

来源: mdpi

【 摘 要 】

We describe an optimal linear time complexity method for extracting patterns from sliding windows of multivariate time series that depends only on the length of the time series. The method is implemented as an open-source Java library and is used to detect anomalies in multivariate time series.

【 授权许可】

Unknown