Feature Space Reduction As Data Preprocessing For The Anomaly Detection

Bilik, Simon

Feature Space Reduction As Data Preprocessing For The Anomaly Detection

Files

415_eeict-2021_1.pdf(1.17 MB)

Date

2021

Authors

Bilik, Simon

Publisher

Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií

Abstract

In this paper, we present two pipelines in order to reduce the feature space for anomalydetection using the One Class SVM. As a first stage of both pipelines, we compare the performanceof three convolutional autoencoders. We use the PCA method together with t-SNE as the first pipelineand the reconstruction errors based method as the second. Both methods have potential for theanomaly detection, but the reconstruction error metrics prove to be more robust for this task. Weshow that the convolutional autoencoder architecture doesn’t have a significant effect for this task andwe prove the potential of our approach on the real world dataset.

Keywords

Anomaly detection, Convolutional autoencoder, PCA, t-SNE, CNN, OC-SVM

Citation

Proceedings I of the 27st Conference STUDENT EEICT 2021: General papers. s. 415-419. ISBN 978-80-214-5942-7
https://conf.feec.vutbr.cz/eeict/index/pages/view/ke_stazeni

Document type

Peer-reviewed

Document version

Published version

Language of document

en

Document licence