Unsupervised Multivariate Time Series Data Anomaly Detection in Industrial IoT: A Confidence Adversarial Autoencoder Network

Anomaly detection of multivariate time series (MTS) is crucial in industrial intelligent systems. To address the challenges of absence of anomaly labels, fast inference time, multi-source and multi-modality in anomaly detection, researchers have primarily investigated unsupervised reconstruction-dri...

Full description

Saved in:
Bibliographic Details
Published in:IEEE open journal of the Communications Society Vol. 5; pp. 7752 - 7766
Main Authors: Shan, Jiahao, Cai, Donghong, Fang, Fang, Khan, Zahid, Fan, Pingzhi
Format: Journal Article
Language:English
Published: New York IEEE 2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
adversarial training
Anomalies
Anomaly detection
autoencoder
Data preprocessing
Datasets
Decoding
Errors
Industrial applications
Industrial Internet of Things
Labels
Long short term memory
Multivariate analysis
Multivariate time series (MTS)
Reconstruction
Support vector machines
Time series
Time series analysis
Training
Transformers
Unsupervised learning
ISSN:2644-125X, 2644-125X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Anomaly detection of multivariate time series (MTS) is crucial in industrial intelligent systems. To address the challenges of absence of anomaly labels, fast inference time, multi-source and multi-modality in anomaly detection, researchers have primarily investigated unsupervised reconstruction-driven methods. However, the existing reconstruction-driven methods mainly focus on minimizing reconstruction errors while neglecting the importance of training methods that increase errors between normal and abnormal classes. Furthermore, accurately constructing the feature space of normal and abnormal classes during the reconstruction process remains a challenge. In this paper, we propose an innovative model, namely the confidence adversarial autoencoder (CAAE). The proposed CAAE combines a confidence network, based on window credibility judgment, with an autoencoder to provide credibility support for anomaly detection. We further introduce fake labels to provide the confidence network with a discriminative knowledge for identifying reconstructed data. Additionally, we implement the confidence adversarial training method to generate fake labels to construct an adversarial loss aiming to expand the decision boundary of anomaly scores. Extensive experimental results on publicly available time series datasets are provided to demonstrate the efficiency of our proposed CAAE. It reveals that excellent generalization ability and superior average performance are achieved on different datasets compared with the state-of-the-art methods.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2644-125X
2644-125X
DOI:10.1109/OJCOMS.2024.3511951