Open AccessAnomaly detection in multi-class time series
Author(s) -
Weihong Wang,
Ziying Wu,
Xuan Liu,
Lei Jia,
Xiaoguang Wang
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/2113/1/012062
Subject(s) - computer science , anomaly detection , cluster analysis , series (stratigraphy) , data mining , feature (linguistics) , key (lock) , artificial intelligence , time series , domain (mathematical analysis) , pattern recognition (psychology) , class (philosophy) , machine learning , time domain , wavelet transform , wavelet , signal processing , computer vision , mathematics , digital signal processing , paleontology , mathematical analysis , linguistics , philosophy , computer security , biology , computer hardware
For modern operation and maintenance systems, they are usually required to monitor multiple types and large quantities of machine’s key performance indicators (KPIs) at the same time with limited resources. In this paper, to tackle these problems, we propose a highly compatible time series anomaly detection model based on K-means clustering algorithm with a new Wavelet Feature Distance (WFD). Our work is inspired by some ideas from image processing and signal processing domain. Our model detects abnormalities in the time series datasets which are first clustered by K-means to boost the accuracy. Our experiments show significant accuracy improvements compared with traditional algorithms, and excellent compatibilities and operating efficiencies compared with algorithms based on deep learning.