Regularizing autoencoders with wavelet transform for sequence anomaly detection

作者：

Highlights：

• Unsupervised model for sequence anomaly detection.

• Propose a novel spectral regularizer to restrict latent spaces of autoencoders.

• Statistical analysis on DWT coefficients to mine unique features of normal sequences.

• Design a Weight Controller to gain sample-adaptive regularization weights.

摘要

•Unsupervised model for sequence anomaly detection.•Propose a novel spectral regularizer to restrict latent spaces of autoencoders.•Statistical analysis on DWT coefficients to mine unique features of normal sequences.•Design a Weight Controller to gain sample-adaptive regularization weights.

论文关键词：Sequence anomaly detection,Autoencoder,Discrete wavelet transform,Frequency domain regularization,Sample-adaptive regularization weight

论文评审过程：Received 30 June 2022, Revised 19 August 2022, Accepted 28 September 2022, Available online 2 October 2022, Version of Record 13 October 2022.

论文官网地址：https://doi.org/10.1016/j.patcog.2022.109084