Feature selection using genetic algorithm to improve classification in network intrusion detection system

Andrey Ferriyan, Achmad Husni Thamrin, Keiji Takeda, Jun Murai

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

In this paper, we present Genetic Algorithm based optimized feature selections for intrusion detection systems. We used one-point crossover for the Genetic Algorithm parameters instead of two-point crossover used by the previous research as it one-point crossover is faster. For evaluations, we used the NSL-KDD Cup 99 data set and we modified the data set by looking into to the recent attacks, hence making the data set more relevant to the current situations. Several classifiers were used on these data sets and we found that Random Forest gave the best results in terms of the classification rate and the training time. The results also showed that our parameters performed better in these two metrics and the classifications using our optimized features on the modified data sets gave mixed results compared to ones with the original features.

Original languageEnglish
Title of host publicationProceedings - International Electronics Symposium on Knowledge Creation and Intelligent Computing, IES-KCIC 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages46-49
Number of pages4
Volume2017-January
ISBN (Electronic)9781538607169
DOIs
Publication statusPublished - 2017 Dec 19
Event6th International Electronics Symposium on Knowledge Creation and Intelligent Computing, IES-KCIC 2017 - Surabaya, Indonesia
Duration: 2017 Sep 262017 Sep 27

Other

Other6th International Electronics Symposium on Knowledge Creation and Intelligent Computing, IES-KCIC 2017
CountryIndonesia
CitySurabaya
Period17/9/2617/9/27

Fingerprint

Intrusion detection
Feature extraction
Genetic algorithms
Classifiers

Keywords

  • feature selection
  • genetic algorithm
  • intrusion detection
  • random forest

ASJC Scopus subject areas

  • Artificial Intelligence
  • Signal Processing

Cite this

Ferriyan, A., Thamrin, A. H., Takeda, K., & Murai, J. (2017). Feature selection using genetic algorithm to improve classification in network intrusion detection system. In Proceedings - International Electronics Symposium on Knowledge Creation and Intelligent Computing, IES-KCIC 2017 (Vol. 2017-January, pp. 46-49). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/KCIC.2017.8228458

Feature selection using genetic algorithm to improve classification in network intrusion detection system. / Ferriyan, Andrey; Thamrin, Achmad Husni; Takeda, Keiji; Murai, Jun.

Proceedings - International Electronics Symposium on Knowledge Creation and Intelligent Computing, IES-KCIC 2017. Vol. 2017-January Institute of Electrical and Electronics Engineers Inc., 2017. p. 46-49.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ferriyan, A, Thamrin, AH, Takeda, K & Murai, J 2017, Feature selection using genetic algorithm to improve classification in network intrusion detection system. in Proceedings - International Electronics Symposium on Knowledge Creation and Intelligent Computing, IES-KCIC 2017. vol. 2017-January, Institute of Electrical and Electronics Engineers Inc., pp. 46-49, 6th International Electronics Symposium on Knowledge Creation and Intelligent Computing, IES-KCIC 2017, Surabaya, Indonesia, 17/9/26. https://doi.org/10.1109/KCIC.2017.8228458
Ferriyan A, Thamrin AH, Takeda K, Murai J. Feature selection using genetic algorithm to improve classification in network intrusion detection system. In Proceedings - International Electronics Symposium on Knowledge Creation and Intelligent Computing, IES-KCIC 2017. Vol. 2017-January. Institute of Electrical and Electronics Engineers Inc. 2017. p. 46-49 https://doi.org/10.1109/KCIC.2017.8228458
Ferriyan, Andrey ; Thamrin, Achmad Husni ; Takeda, Keiji ; Murai, Jun. / Feature selection using genetic algorithm to improve classification in network intrusion detection system. Proceedings - International Electronics Symposium on Knowledge Creation and Intelligent Computing, IES-KCIC 2017. Vol. 2017-January Institute of Electrical and Electronics Engineers Inc., 2017. pp. 46-49
@inproceedings{68e0fe567e8e4caf991206cf54a812d9,
title = "Feature selection using genetic algorithm to improve classification in network intrusion detection system",
abstract = "In this paper, we present Genetic Algorithm based optimized feature selections for intrusion detection systems. We used one-point crossover for the Genetic Algorithm parameters instead of two-point crossover used by the previous research as it one-point crossover is faster. For evaluations, we used the NSL-KDD Cup 99 data set and we modified the data set by looking into to the recent attacks, hence making the data set more relevant to the current situations. Several classifiers were used on these data sets and we found that Random Forest gave the best results in terms of the classification rate and the training time. The results also showed that our parameters performed better in these two metrics and the classifications using our optimized features on the modified data sets gave mixed results compared to ones with the original features.",
keywords = "feature selection, genetic algorithm, intrusion detection, random forest",
author = "Andrey Ferriyan and Thamrin, {Achmad Husni} and Keiji Takeda and Jun Murai",
year = "2017",
month = "12",
day = "19",
doi = "10.1109/KCIC.2017.8228458",
language = "English",
volume = "2017-January",
pages = "46--49",
booktitle = "Proceedings - International Electronics Symposium on Knowledge Creation and Intelligent Computing, IES-KCIC 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Feature selection using genetic algorithm to improve classification in network intrusion detection system

AU - Ferriyan, Andrey

AU - Thamrin, Achmad Husni

AU - Takeda, Keiji

AU - Murai, Jun

PY - 2017/12/19

Y1 - 2017/12/19

N2 - In this paper, we present Genetic Algorithm based optimized feature selections for intrusion detection systems. We used one-point crossover for the Genetic Algorithm parameters instead of two-point crossover used by the previous research as it one-point crossover is faster. For evaluations, we used the NSL-KDD Cup 99 data set and we modified the data set by looking into to the recent attacks, hence making the data set more relevant to the current situations. Several classifiers were used on these data sets and we found that Random Forest gave the best results in terms of the classification rate and the training time. The results also showed that our parameters performed better in these two metrics and the classifications using our optimized features on the modified data sets gave mixed results compared to ones with the original features.

AB - In this paper, we present Genetic Algorithm based optimized feature selections for intrusion detection systems. We used one-point crossover for the Genetic Algorithm parameters instead of two-point crossover used by the previous research as it one-point crossover is faster. For evaluations, we used the NSL-KDD Cup 99 data set and we modified the data set by looking into to the recent attacks, hence making the data set more relevant to the current situations. Several classifiers were used on these data sets and we found that Random Forest gave the best results in terms of the classification rate and the training time. The results also showed that our parameters performed better in these two metrics and the classifications using our optimized features on the modified data sets gave mixed results compared to ones with the original features.

KW - feature selection

KW - genetic algorithm

KW - intrusion detection

KW - random forest

UR - http://www.scopus.com/inward/record.url?scp=85046542002&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85046542002&partnerID=8YFLogxK

U2 - 10.1109/KCIC.2017.8228458

DO - 10.1109/KCIC.2017.8228458

M3 - Conference contribution

AN - SCOPUS:85046542002

VL - 2017-January

SP - 46

EP - 49

BT - Proceedings - International Electronics Symposium on Knowledge Creation and Intelligent Computing, IES-KCIC 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -