Scholarlink

<p>Multivariate time series present significant methodological challenges for anomaly detection, primarily due to the intricate nature of their temporal dependencies and the dynamic interplay among variables. These complexities render traditional methods inadequate for precise and reliable anomaly detection. This paper confronts these challenges by introducing an innovative, unsupervised framework that concurrently integrates data encoding, preservation of temporal structure, and residual analysis. By modeling temporal dependencies through sinusoidal exponential decay functions, our approach identifies deviations from this model in the latent space as anomalies. We validate the effectiveness of our framework through extensive experiments on real-world datasets, benchmarking it against state-of-the-art approaches.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A temporal dependency preserving approach for anomaly detection on multivariate time series

  • 期刊论文

  • 发表日期：

    2025年5月10日

查看全文
  • Seif-Eddine Benkabou,
  • Khalid Benabdeslem,
  • Dou El Kefel Mansouri,
  • Souleyman Chaib,
  • Amin Mesmoudi,
  • Allel Hadjali

摘要

Multivariate time series present significant methodological challenges for anomaly detection, primarily due to the intricate nature of their temporal dependencies and the dynamic interplay among variables. These complexities render traditional methods inadequate for precise and reliable anomaly detection. This paper confronts these challenges by introducing an innovative, unsupervised framework that concurrently integrates data encoding, preservation of temporal structure, and residual analysis. By modeling temporal dependencies through sinusoidal exponential decay functions, our approach identifies deviations from this model in the latent space as anomalies. We validate the effectiveness of our framework through extensive experiments on real-world datasets, benchmarking it against state-of-the-art approaches.