Patch-Wise-Based Self-Supervised Learning for Anomaly Detection on Multivariate Time Series Data

Seungmin Oh, Le Hoang Anh, Dang Thanh Vu, Gwang Hyun Yu, Minsoo Hahn and Jinsul Kim ()
Additional contact information
Seungmin Oh: Department of Intelligent Electronics and Computer Engineering, Chonnam National University, 77, Yongbong-ro, Buk-gu, Gwangju 61186, Republic of Korea
Le Hoang Anh: Department of Intelligent Electronics and Computer Engineering, Chonnam National University, 77, Yongbong-ro, Buk-gu, Gwangju 61186, Republic of Korea
Dang Thanh Vu: Department of Intelligent Electronics and Computer Engineering, Chonnam National University, 77, Yongbong-ro, Buk-gu, Gwangju 61186, Republic of Korea
Gwang Hyun Yu: Department of Intelligent Electronics and Computer Engineering, Chonnam National University, 77, Yongbong-ro, Buk-gu, Gwangju 61186, Republic of Korea
Minsoo Hahn: Department of Computational and Data Science, Astana IT University, Astana 010000, Kazakhstan
Jinsul Kim: Department of Intelligent Electronics and Computer Engineering, Chonnam National University, 77, Yongbong-ro, Buk-gu, Gwangju 61186, Republic of Korea

Mathematics, 2024, vol. 12, issue 24, 1-17

Abstract: Multivariate time series anomaly detection is a crucial technology to prevent unexpected errors from causing critical impacts. Effective anomaly detection in such data requires accurately capturing temporal patterns and ensuring the availability of adequate data. This study proposes a patch-wise framework for anomaly detection. The proposed approach comprises four key components: (i) maintaining continuous features through patching, (ii) incorporating various temporal information by learning channel dependencies and adding relative positional bias, (iii) achieving feature representation learning through self-supervised learning, and (iv) supervised learning based on anomaly augmentation for downstream tasks. The proposed method demonstrates strong anomaly detection performance by leveraging patching to maintain temporal continuity while effectively learning data representations and handling downstream tasks. Additionally, it mitigates the issue of insufficient anomaly data by supporting the learning of diverse types of anomalies. The experimental results show that our model achieved a 23% to 205% improvement in the F1 score compared to existing methods on datasets such as MSL, which has a relatively small amount of training data. Furthermore, the model also delivered a competitive performance on the SMAP dataset. By systematically learning both local and global dependencies, the proposed method strikes an effective balance between feature representation and anomaly detection accuracy, making it a valuable tool for real-world multivariate time series applications.

Keywords: time series anomaly detection; multivariate time series; patch-wise learning; pre-trained model; self-supervised learning; channel dependencies (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/12/24/3969/pdf (application/pdf)
https://www.mdpi.com/2227-7390/12/24/3969/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:12:y:2024:i:24:p:3969-:d:1546035

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().