TY - JOUR
T1 - Robust Group Anomaly Detection for Quasi-Periodic Network Time Series
AU - Yang, Kai
AU - Dou, Shaoyu
AU - Luo, Pan
AU - Wang, Xin
AU - Poor, H. Vincent
N1 - Funding Information:
This work was supported in part by the Fundamental Research Funds for the Central Universities of China, in part by the National Natural Science Foundation of China under Grant 61771013, and in part by the Fundamental Research Funds of Shanghai Jiading District.
Publisher Copyright:
© 2013 IEEE.
PY - 2022
Y1 - 2022
N2 - Many real-world multivariate time series are collected from a network of physical objects embedded with software, electronics, and sensors. The quasi-periodic signals generated by these objects often follow a similar repetitive and periodic pattern, but have variations in the period, and come in different lengths caused by timing (synchronization) errors. Given a multitude of such quasi-periodic time series, can we build machine learning models to identify those time series that behave differently from the majority of the observations? In addition, can the models help human experts to understand how the decision was made? We propose a sequence to Gaussian Mixture Model (seq2GMM) framework. The overarching goal of this framework is to identify unusual and interesting time series within a network time series database. We further develop a surrogate-based optimization algorithm that can efficiently train the seq2GMM model. Seq2GMM exhibits strong empirical performance on a plurality of public benchmark datasets, outperforming state-of-the-art anomaly detection techniques by a significant margin. We also theoretically analyze the convergence property of the proposed training algorithm and provide numerical results to substantiate our theoretical claims.
AB - Many real-world multivariate time series are collected from a network of physical objects embedded with software, electronics, and sensors. The quasi-periodic signals generated by these objects often follow a similar repetitive and periodic pattern, but have variations in the period, and come in different lengths caused by timing (synchronization) errors. Given a multitude of such quasi-periodic time series, can we build machine learning models to identify those time series that behave differently from the majority of the observations? In addition, can the models help human experts to understand how the decision was made? We propose a sequence to Gaussian Mixture Model (seq2GMM) framework. The overarching goal of this framework is to identify unusual and interesting time series within a network time series database. We further develop a surrogate-based optimization algorithm that can efficiently train the seq2GMM model. Seq2GMM exhibits strong empirical performance on a plurality of public benchmark datasets, outperforming state-of-the-art anomaly detection techniques by a significant margin. We also theoretically analyze the convergence property of the proposed training algorithm and provide numerical results to substantiate our theoretical claims.
KW - Group anomaly detection
KW - gaussian mixture model
KW - timing errors
UR - http://www.scopus.com/inward/record.url?scp=85129593320&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85129593320&partnerID=8YFLogxK
U2 - 10.1109/TNSE.2022.3170364
DO - 10.1109/TNSE.2022.3170364
M3 - Article
AN - SCOPUS:85129593320
SN - 2327-4697
VL - 9
SP - 2833
EP - 2845
JO - IEEE Transactions on Network Science and Engineering
JF - IEEE Transactions on Network Science and Engineering
IS - 4
ER -