LPCVAE: A Conditional VAE with Long-Term Dependency and Probabilistic Time-Frequency Fusion for Time Series Anomaly Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cheng, Hanchang, Mu, Weimin, Liu, Fan, Zhu, Weilin, Ma, Can
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914302659657728
author Cheng, Hanchang
Mu, Weimin
Liu, Fan
Zhu, Weilin
Ma, Can
author_facet Cheng, Hanchang
Mu, Weimin
Liu, Fan
Zhu, Weilin
Ma, Can
contents Time series anomaly detection(TSAD) is a critical task in signal processing field, ensuring the reliability of complex systems. Reconstruction-based methods dominate in TSAD. Among these methods, VAE-based methods have achieved promising results. Existing VAE-based methods suffer from the limitation of single-window feature and insufficient leveraging of long-term time and frequency information. We propose a Conditional Variational AutoEncoder with Long-term dependency and Probabilistic time-frequency fusion, named LPCVAE. LPCVAE introduces LSTM to capture long-term dependencies beyond windows. It further incorporates a Product-of-Experts (PoE) mechanism for adaptive and distribution-level probabilistic fusion. This design effectively mitigates time-frequency information loss. Extensive experiments on four public datasets demonstrate it outperforms state-of-the-art methods. The results confirm that integrating long-term time and frequency representations with adaptive fusion yields a robust and efficient solution for TSAD.
format Preprint
id arxiv_https___arxiv_org_abs_2510_10915
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LPCVAE: A Conditional VAE with Long-Term Dependency and Probabilistic Time-Frequency Fusion for Time Series Anomaly Detection
Cheng, Hanchang
Mu, Weimin
Liu, Fan
Zhu, Weilin
Ma, Can
Machine Learning
Artificial Intelligence
Emerging Technologies
Time series anomaly detection(TSAD) is a critical task in signal processing field, ensuring the reliability of complex systems. Reconstruction-based methods dominate in TSAD. Among these methods, VAE-based methods have achieved promising results. Existing VAE-based methods suffer from the limitation of single-window feature and insufficient leveraging of long-term time and frequency information. We propose a Conditional Variational AutoEncoder with Long-term dependency and Probabilistic time-frequency fusion, named LPCVAE. LPCVAE introduces LSTM to capture long-term dependencies beyond windows. It further incorporates a Product-of-Experts (PoE) mechanism for adaptive and distribution-level probabilistic fusion. This design effectively mitigates time-frequency information loss. Extensive experiments on four public datasets demonstrate it outperforms state-of-the-art methods. The results confirm that integrating long-term time and frequency representations with adaptive fusion yields a robust and efficient solution for TSAD.
title LPCVAE: A Conditional VAE with Long-Term Dependency and Probabilistic Time-Frequency Fusion for Time Series Anomaly Detection
topic Machine Learning
Artificial Intelligence
Emerging Technologies
url https://arxiv.org/abs/2510.10915