An Industrial Control Intrusion Detection Method Combining Semi-supervised LDA and PSO-SVM

DOI

10.2991/cnci-19.2019.52How to use a DOI?

Keywords

PCA, LDA, industrial control system, intrusion detection, SVM

Abstract

In order to improve the accuracy of industrial control intrusion detection, this paper proposes a fusion semi-supervised LDA and PSO-SVM method, using the cumulative contribution rate ω to determine the principal component analysis (PCA) accounted for the proportion of semi-supervised LDA algorithm. The experimental results show that compared with a single PCA or LDA and PSO-SVM combination, this method of combining semi-supervised LDA and PSO-SVM has advantages, high accuracy of anomaly detection, and low false positive rate.

Copyright

© 2019, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Liu Zhan
AU  - Jie Ling
AU  - Peng Lin
PY  - 2019/05
DA  - 2019/05
TI  - An Industrial Control Intrusion Detection Method Combining Semi-supervised LDA and PSO-SVM
BT  - Proceedings of the 2019 International Conference on Computer, Network, Communication and Information Systems (CNCI 2019)
PB  - Atlantis Press
SP  - 363
EP  - 370
SN  - 2352-538X
UR  - https://doi.org/10.2991/cnci-19.2019.52
DO  - 10.2991/cnci-19.2019.52
ID  - Zhan2019/05
ER  -