Deep Contrastive One-Class Time Series Anomaly Detection

被引:0
|
作者
Wang, Rui [1 ]
Liu, Chongwei [1 ]
Mou, Xudong [1 ]
Gao, Kai [2 ]
Guo, Xiaohui [3 ]
Liu, Pin [4 ]
Wo, Tianyu [5 ]
Liu, Xudong [1 ,3 ]
机构
[1] Beihang Univ, Sch Comp Sci & Engn, Beijing, Peoples R China
[2] Univ New South Wales, Sydney, NSW, Australia
[3] Beihang Univ, Hangzhou Innovat Inst, Hangzhou, Peoples R China
[4] China Univ Geosci Beijing, Sch Informat Engn, Beijing, Peoples R China
[5] Beihang Univ, Coll Software, Beijing, Peoples R China
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The accumulation of time-series data and the absence of labels make time-series Anomaly Detection (AD) a self-supervised deep learning task. Single-normality-assumption-based methods, which reveal only a certain aspect of the whole normality, are incapable of tasks involved with a large number of anomalies. Specifically, Contrastive Learning (CL) methods distance negative pairs, many of which consist of both normal samples, thus reducing the AD performance. Existing multi-normality-assumption-based methods are usually two-staged, firstly pre-training through certain tasks whose target may differ from AD, limiting their performance. To overcome the shortcomings, a deep Contrastive One-Class Anomaly detection method of time series (COCA) is proposed by authors, following the normality assumptions of CL and one-class classification. It treats the original and reconstructed representations as the positive pair of negative-sample-free CL, namely "sequence contrast". Next, invariance terms and variance terms compose a contrastive one-class loss function in which the loss of the assumptions is optimized by invariance terms simultaneously and the "hypersphere collapse" is prevented by variance terms. In addition, extensive experiments on two real-world time-series datasets show the superior performance of the proposed method achieves state-of-the-art.
引用
收藏
页码:694 / 702
页数:9
相关论文
共 50 条
  • [21] Deep domain-adversarial anomaly detection with robust one-class transfer learning
    Chi, Jingkai
    Mao, Zhizhong
    KNOWLEDGE-BASED SYSTEMS, 2024, 300
  • [22] Anomaly detection in oil-producing wells: a comparative study of one-class classifiers in a multivariate time series dataset
    Wander Fernandes
    Karin Satie Komati
    Kelly Assis de Souza Gazolli
    Journal of Petroleum Exploration and Production Technology, 2024, 14 : 343 - 363
  • [23] Anomaly detection in oil-producing wells: a comparative study of one-class classifiers in a multivariate time series dataset
    Fernandes Jr, Wander
    Komati, Karin Satie
    Gazolli, Kelly Assis de Souza
    JOURNAL OF PETROLEUM EXPLORATION AND PRODUCTION TECHNOLOGY, 2024, 14 (01) : 343 - 363
  • [24] Contrastive autoencoder for anomaly detection in multivariate time series
    Zhou, Hao
    Yu, Ke
    Zhang, Xuan
    Wu, Guanlin
    Yazidi, Anis
    INFORMATION SCIENCES, 2022, 610 : 266 - 280
  • [25] Contrastive Time Series Anomaly Detection by Temporal Transformations
    Li, Bin
    Mueller, Emmanuel
    2023 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, IJCNN, 2023,
  • [26] Efficient Real-Time Anomaly Detection in IoT Networks Using One-Class Autoencoder and Deep Neural Network
    Ayad, Aya G.
    El-Gayar, Mostafa M.
    Hikal, Noha A.
    Sakr, Nehal A.
    ELECTRONICS, 2025, 14 (01):
  • [27] ONE-CLASS SUPPORT VECTOR MACHINES APPROACH TO ANOMALY DETECTION
    Hejazi, Maryamsadat
    Singh, Yashwant Prasad
    APPLIED ARTIFICIAL INTELLIGENCE, 2013, 27 (05) : 351 - 366
  • [28] Latent Feature Decentralization Loss for One-Class Anomaly Detection
    Hong, Eungi
    Choe, Yoonsik
    IEEE ACCESS, 2020, 8 : 165658 - 165669
  • [29] End-to-End Deep One-Class Learning for Anomaly Detection in UAV Video Stream
    Hamdi, Slim
    Bouindour, Samir
    Snoussi, Hichem
    Wang, Tian
    Abid, Mohamed
    JOURNAL OF IMAGING, 2021, 7 (05)
  • [30] Anomaly detection for medical images based on a one-class classification
    Wei, Qi
    Ren, Yinhao
    Hou, Rui
    Shi, Bibo
    Lo, Joseph Y.
    Carin, Lawrence
    MEDICAL IMAGING 2018: COMPUTER-AIDED DIAGNOSIS, 2018, 10575