Detail publikace

Feature space reduction as data preprocessing for the anomaly detection

BILÍK, Š.

Originální název

Feature space reduction as data preprocessing for the anomaly detection

Typ

článek ve sborníku mimo WoS a Scopus

Jazyk

angličtina

Originální abstrakt

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

Klíčová slova

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

Autoři

BILÍK, Š.

Vydáno

30. 4. 2021

Nakladatel

Brno University of Technology, Faculty of Electrical Engineering and Communication

Místo

Brno

ISBN

978-80-214-5942-7

Kniha

Proceedings I of the 27th Conference STUDENT EEICT 2021

Strany od

415

Strany do

419

Strany počet

5

URL

https://www.fekt.vut.cz/conf/EEICT/archiv/sborniky/EEICT_2021_sbornik_1.pdf

BibTex

@inproceedings{BUT171163,
  author="Šimon {Bilík}",
  title="Feature space reduction as data preprocessing for the anomaly detection",
  booktitle="Proceedings I of the 27th Conference STUDENT EEICT 2021",
  year="2021",
  pages="415--419",
  publisher="Brno University of Technology, Faculty of Electrical Engineering and Communication",
  address="Brno",
  isbn="978-80-214-5942-7",
  url="https://www.fekt.vut.cz/conf/EEICT/archiv/sborniky/EEICT_2021_sbornik_1.pdf"
}