Online Multivariate Time Series Anomaly Detection Method Based on Contrastive Learning

被引:0
|
作者
Dong, Xiyao [1 ]
Liu, Hui [1 ]
Du, Junzhao [1 ]
Wang, Zhengkai [1 ]
Wang, Cheng [1 ]
机构
[1] Xidian Univ, Sch Comp Sci & Technol, Xian 710071, Peoples R China
来源
ADVANCED INTELLIGENT COMPUTING TECHNOLOGY AND APPLICATIONS, PT XIII, ICIC 2024 | 2024年 / 14874卷
基金
中国国家自然科学基金;
关键词
Anomaly detection; Autocorrelation; Contrastive learning; Online learning;
D O I
10.1007/978-981-97-5618-6_39
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
With the swift progression of industrial automation and Internet of Things technologies, the importance of multivariate time series anomaly detection has markedly increased, serving as a vital tool for identifying abnormal behaviors within complex datasets to prevent potential risks. Traditional anomaly detection methods often struggle to deal with multivariable and unlabeled data environments, especially in the context of real-time dynamic data streams, where traditional models require frequent retraining to adapt to new anomaly patterns. To address this challenge, our work proposes an online anomaly detection model for multivariate time series based on a contrastive learning framework:ODAnomaly, utilizing a dual autocorrelation mechanism to effectively extract features of normal data and distinguish anomalous data. The model features an online learner that uses gradient updates and Pearson correlation coefficients to rapidly adapt to new anomaly patterns, boosting its real-time learning efficiency. A contrastive loss function, informed by homoscedastic uncertainty, aids in anomaly detection through data representation. This approach reduces reliance on extensively labeled data and enhances the model's adaptability and accuracy in real-time data streams. It provides an efficient and cost-effective solution for advancing multivariate time series anomaly detection in both research and practical applications.
引用
收藏
页码:468 / 479
页数:12
相关论文
共 50 条
  • [41] Learning Sparse Latent Graph Representations for Anomaly Detection in Multivariate Time Series
    Han, Siho
    Woo, Simon S.
    PROCEEDINGS OF THE 28TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, KDD 2022, 2022, : 2977 - 2986
  • [42] Deep learning for anomaly detection in multivariate time series: Approaches, applications, and challenges
    Li, Gen
    Jung, Jason J.
    INFORMATION FUSION, 2023, 91 : 93 - 102
  • [43] Active-MTSAD: Multivariate Time Series Anomaly Detection With Active Learning
    Wang, Wenlu
    Chen, Pengfei
    Xu, Yibin
    He, Zilong
    2022 52ND ANNUAL IEEE/IFIP INTERNATIONAL CONFERENCE ON DEPENDABLE SYSTEMS AND NETWORKS (DSN 2022), 2022, : 263 - 274
  • [44] Anomaly detection model for multivariate time series based on stochastic Transformer
    Huo W.
    Liang R.
    Li Y.
    Tongxin Xuebao/Journal on Communications, 2023, 44 (02): : 94 - 103
  • [45] Semisupervised anomaly detection of multivariate time series based on a variational autoencoder
    Ningjiang Chen
    Huan Tu
    Xiaoyan Duan
    Liangqing Hu
    Chengxiang Guo
    Applied Intelligence, 2023, 53 : 6074 - 6098
  • [46] Clustering-based anomaly detection in multivariate time series data
    Li, Jinbo
    Izakian, Hesam
    Pedrycz, Witold
    Jamal, Iqbal
    APPLIED SOFT COMPUTING, 2021, 100
  • [47] Clustering-based anomaly detection in multivariate time series data
    Li, Jinbo
    Izakian, Hesam
    Pedrycz, Witold
    Jamal, Iqbal
    Applied Soft Computing, 2021, 100
  • [48] Adversarial Transformer-Based Anomaly Detection for Multivariate Time Series
    Yu, Xinying
    Zhang, Kejun
    Liu, Yaqi
    Zou, Bing
    Wang, Jun
    Wang, Wenbin
    Qian, Rong
    IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2025, 21 (03) : 2471 - 2480
  • [49] Semisupervised anomaly detection of multivariate time series based on a variational autoencoder
    Chen, Ningjiang
    Tu, Huan
    Duan, Xiaoyan
    Hu, Liangqing
    Guo, Chengxiang
    APPLIED INTELLIGENCE, 2023, 53 (05) : 6074 - 6098
  • [50] TiCTok: Time-Series Anomaly Detection With Contrastive Tokenization
    Kang, Minseo
    Lee, Byunghan
    IEEE ACCESS, 2023, 11 : 81011 - 81020