EUVIMEDEUVIMED entdecken
Crossref

TFT-GCN: A Time-Frequency Based Model for Time Series Anomaly Detection

Zhenchang Xia, Xusheng Xu, Libing Wu, Bingyi Liu, Long Yuan, Bolong Zheng

IEEE Transactions on Knowledge and Data Engineering · 2026-09 · 38 (9) · 6196-6207

DOI: 10.1109/tkde.2026.3707947 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Knowledge and Data Engineering, 2026-09. Verfasst von Zhenchang Xia und 5 weiteren Autor:innen. Die Arbeit nennt 36 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Wuhan City Joint Innovation Laboratory for Next-Generation Wireless Communication Industry Featuring Satellite-Terrestrial Integration.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Time series anomaly detection is essential for maintaining the stability and operational efficiency of industrial systems. However, most existing approaches emphasize temporal dependency modeling while paying limited attention to spectral characteristics embedded in the data. This limitation prevents models from effectively capturing both localized patterns and global trends, thereby reducing the accuracy of anomaly detection. To overcome these challenges, we introduce TFT-GCN, a novel anomaly detection model that integrates temporal and spectral analysis modules to simultaneously extract local and global information. Specifically, in the frequency-domain branch, we adapt the attention mechanism to extract critical information about frequency combinations, enabling the efficient extraction of global trends. In the time-domain branch, we introduce a cross-variable graph convolutional network, which not only models both homogeneous and heterogeneous interactions between series but also increases resilience to noise. Additionally, we incorporate a multi-scale attention mechanism that efficiently captures local dependencies across varying time scales to prevent the model from focusing too much on features at a single time scale. By combining the complementary strengths of temporal and spectral analyses, TFT-GCN offers a powerful framework for identifying anomalies. Experimental results on seven benchmark datasets verify that TFT-GCN surpasses most existing methods, highlighting its superior performance and robustness in time series anomaly detection.

Förderung

  • National Natural Science Foundation of China
  • Wuhan City Joint Innovation Laboratory for Next-Generation Wireless Communication Industry Featuring Satellite-Terrestrial Integration

Zitieren

APA

Xia, Z., Xu, X., Wu, L., Liu, B., Yuan, L., & Zheng, B. (2026). TFT-GCN: A Time-Frequency Based Model for Time Series Anomaly Detection. IEEE Transactions on Knowledge and Data Engineering, 38(9), 6196-6207. https://doi.org/10.1109/tkde.2026.3707947

Vancouver

Xia Z, Xu X, Wu L, Liu B, Yuan L, Zheng B. TFT-GCN: A Time-Frequency Based Model for Time Series Anomaly Detection. IEEE Transactions on Knowledge and Data Engineering. 2026;38(9):6196-6207. doi:10.1109/tkde.2026.3707947

BibTeX
@article{Xia2026,
  author = {Xia, Zhenchang and Xu, Xusheng and Wu, Libing and Liu, Bingyi and Yuan, Long and Zheng, Bolong},
  title = {TFT-GCN: A Time-Frequency Based Model for Time Series Anomaly Detection},
  journal = {IEEE Transactions on Knowledge and Data Engineering},
  year = {2026},
  volume = {38},
  number = {9},
  pages = {6196--6207},
  doi = {10.1109/tkde.2026.3707947}
}
Kostenlos starten →