Robust anomaly detection in time series through variational AutoEncoders and a local similarity score

Pedro Matias, Duarte Folgado, Hugo Gamboa, André V. Carreiro

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Citations (Scopus)

Abstract

The rise of time series data availability has demanded new techniques for its automated analysis regarding several tasks, including anomaly detection. However, even though the volume of time series data is rapidly increasing, the lack of labeled abnormal samples is still an issue, hindering the performance of most supervised anomaly detection models. In this paper, we present an unsupervised framework comprised of a Variational Autoencoder coupled with a local similarity score, which learns solely on available normal data to detect abnormalities in new data. Nonetheless, we propose two techniques to improve the results if at least some abnormal samples are available. These include a training set cleaning method for removing the influence of corrupted data on detection performance and the optimization of the detection threshold. Tests were performed in two datasets: ECG5000 and MIT-BIH Arrhythmia. Regarding the ECG5000 dataset, our framework has shown to outperform some supervised and unsupervised approaches found in the literature by achieving an AUC score of 98.79%. In the MIT-BIH dataset, the training set cleaning step removed 60% of the original training samples and improved the anomaly detection AUC score from 91.70% to 93.30%.

Original languageEnglish
Title of host publicationBIOSIGNALS 2021 - 14th International Conference on Bio-Inspired Systems and Signal Processing; Part of the 14th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2021
EditorsBethany Bracken, Ana Fred, Hugo Gamboa
PublisherSciTePress - Science and Technology Publications
Pages91-102
Number of pages12
Volume4
ISBN (Electronic)9789897584909
DOIs
Publication statusPublished - 2021
Event14th International Conference on Bio-Inspired Systems and Signal Processing, BIOSIGNALS 2021 - Part of the 14th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2021 - Virtual, Online
Duration: 11 Feb 202113 Feb 2021

Conference

Conference14th International Conference on Bio-Inspired Systems and Signal Processing, BIOSIGNALS 2021 - Part of the 14th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2021
CityVirtual, Online
Period11/02/2113/02/21

Keywords

  • Anomaly Detection
  • ECG
  • Time Series
  • Unsupervised Learning
  • Variational AutoEncoders

Fingerprint

Dive into the research topics of 'Robust anomaly detection in time series through variational AutoEncoders and a local similarity score'. Together they form a unique fingerprint.

Cite this