Anomaly detection based on temporal convolution Autoencoders. Issue 1 (1st November 2022)

• Record Type: Journal Article
• Authors: Wu, Lihao; Liang, Jiahui
• Is Part Of: Journal of physics. Volume 2366: Issue 1(2022)
• Publication Date: 2022-11-01
• Subjects: Physics -- Congresses; 530.5
• DOI: 10.1088/1742-6596/2366/1/012041
• Languages: English
• ISSNs: 1742-6588

Abstract

Abstract: Due to the rapid growth of the number of sensors in modern industrial society, detecting outliers in time series has become very important. And unsupervised detection of outliers in time series is a very challenging task. For most detection tasks of time series outliers, the autoencoder is one of the main choices. And the recursive network is usually used in the self-coding network structure. However, recent studies have shown that the network structure using dilated causal convolution performs better than the recursive network in all kinds of sequence modeling. In this paper, the encoder and decoder are network structures based on extended causal convolution The time series are reconstructed and then compared with the original data to calculate the distance between them, so as to identify the outliers. We use the Temporal convolution autoencoders to evaluate anomaly data sets in multiple time series. Our results show that the Temporal convolution autoencoders has better anomaly detection ability. In addition, we learned that the combination of Feature Engineering and super parameters will also have a great impact on the results, so ablation experiments need to be carried out carefully.