.png){kind=icon}
Return
Regularizing autoencoders with wavelet transform for sequence anomaly detection
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2022.109084.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Nowadays, systems or entities are usually monitored by devices, generating large amounts of time series. Detecting anomalies in them help prevent potential losses, thus arousing much research interest. Existing studies have adopted autoencoders to detect anomalies, where reconstruction errors are used to indi-cate outliers. However, sometimes autoencoders may also reconstruct anomalies well due to the learned general features in latent spaces. To solve the above problem, we propose to regularize autoencoders to grasp specific features of normal sequences. Specifically, spectral unique patterns are captured by sta-tistical analysis on discrete wavelet transform (DWT) coefficients of input sequences, restricting latent spaces to reflect unique patterns of normal sequences in both time and frequency domains. Furthermore, a Weight Controller calculating sample-adaptive regularization weights is designed to fully utilize the regularization effect. Extensive experiments on three public benchmarks demonstrate the effectiveness and superiority of the proposed model compared with state-of-the-art algorithms. (c) 2022 Elsevier Ltd. All rights reserved.
Keywords:
Sequence anomaly detection
Autoencoder
Discrete wavelet transform
Frequency domain regularization
Sample -adaptive regularization weight
Journal
IF:
7.6
Papers:
1.4W
Citations:
4.5W
Organization
Cited Papers
Principles of time-frequency feature extraction for change detection in non-stationary signals: Applications to newborn EEG abnormality detection.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
ShareSaveAn automated system for epilepsy detection using EEG brain signals based on deep learning approach
PREAI
ShareSaveARAE: Adversarially robust training of autoencoders improves novelty detectionNEURAL NETWORKS
OAAI
NEURAL NETWORKSIF6.3
OAAIShareSave
ShareSaveHybrid multi-mode machine learning-based fault diagnosis strategies with application to aircraft gas turbine enginesNEURAL NETWORKS
NEURAL NETWORKSIF6.3
PREAI
ShareSave
View more