SCAT: A Spectral-Convolutional Anomaly Transformer for Multivariate Time Series Anomaly Detection
Electronics · 02.02.2026 · 15 (3) · 628
DOI: 10.3390/electronics15030628 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 02.02.2026. Verfasst von Shuqin Zhang und 2 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Key Research and Development Program of Henan, Zhongyuan University of Technology Graduate Research Innovation Project.
Abstract (Originalsprache)
Time series anomaly detection plays a vital role in the supervision of complex systems, including spacecraft operations, industrial production lines, and Internet of Things infrastructures. However, the existing methods face two key challenges: (1) fixed-threshold frequency filters fail to adapt to non-stationary noise, often leading to the loss of critical anomaly signals; and (2) deep models struggle to balance local feature extraction and global temporal dependency, resulting in limited robustness and generalization. To address these problems, we propose the Spectral-Convolutional Anomaly Transformer (SCAT), a unified framework integrating spectral domain adaptive filtering and spatio-temporal gated learning. Specifically, the Spectral Energy Gating Unit (SEGU) dynamically suppresses noise through learnable frequency masking, while Spatio-Temporal Gated Fusion (ST-Gate) combines multi-scale causal convolution and ConvGRU to harmonize local and long-term patterns. A joint optimization strategy further enhances the discrimination between normal and anomalous sequences. Our experiments on five public benchmarks (SMAP, MSL, PSM, SMD, SWaT) showed that SCAT attained an average improvement of 2.46 percentage points on the F1-score relative to leading baseline approaches, demonstrating strong adaptability and robustness in complex noisy environments.
Förderung
- Key Research and Development Program of Henan
- Zhongyuan University of Technology Graduate Research Innovation Project
Zitieren
APA
Zhang, S., Chen, S., & Li, J. (2026). SCAT: A Spectral-Convolutional Anomaly Transformer for Multivariate Time Series Anomaly Detection. Electronics, 15(3), 628. https://doi.org/10.3390/electronics15030628
Vancouver
Zhang S, Chen S, Li J. SCAT: A Spectral-Convolutional Anomaly Transformer for Multivariate Time Series Anomaly Detection. Electronics. 2026;15(3):628. doi:10.3390/electronics15030628
BibTeX
@article{Zhang2026,
author = {Zhang, Shuqin and Chen, Shaoqiang and Li, Jun},
title = {SCAT: A Spectral-Convolutional Anomaly Transformer for Multivariate Time Series Anomaly Detection},
journal = {Electronics},
year = {2026},
volume = {15},
number = {3},
pages = {628},
doi = {10.3390/electronics15030628}
}
EUVIMED