Pearson Correlation Attribute Evaluation-based Feature Selection for Intrusion Detection System

Yuna Sugianela; Tohari Ahmad

doi:10.1109/ICoSTA48221.2020.1570613717

Pearson Correlation Attribute Evaluation-based Feature Selection for Intrusion Detection System

Yuna Sugianela
, Tohari Ahmad

Institut Teknologi Sepuluh Nopember

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

30 Citations (Scopus)

Abstract

IDS helps to overcome the network attack by taking appropriate preventive measures. The data mining method has good adaptability to new attack types; however, it consumes much time for high dimensional data. Therefore, the system needs a reduction of that high dimension. In this paper, we use a correlation approach of the attribute to evaluate those high dimensional data. To achieve a better environment, we propose a cut-off value of correlation to select some best features to use in the classification process. The best cut-off value in our experiment is 0.2 in RF classification that reaches 99.36% accuracy. The selection feature can reduce the time consumed in the running system.

Original language	English
Title of host publication	Proceeding - ICoSTA 2020
Subtitle of host publication	2020 International Conference on Smart Technology and Applications: Empowering Industrial IoT by Implementing Green Technology for Sustainable Development
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728130835
DOIs	https://doi.org/10.1109/ICoSTA48221.2020.1570613717
Publication status	Published - Feb 2020
Event	2020 International Conference on Smart Technology and Applications, ICoSTA 2020 - Surabaya, Indonesia Duration: 20 Feb 2020 → …

Publication series

Name	Proceeding - ICoSTA 2020: 2020 International Conference on Smart Technology and Applications: Empowering Industrial IoT by Implementing Green Technology for Sustainable Development

Conference

Conference	2020 International Conference on Smart Technology and Applications, ICoSTA 2020
Country/Territory	Indonesia
City	Surabaya
Period	20/02/20 → …

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

Pearson's correlation
feature
intrusion detection system
network security
selection

Access to Document

10.1109/ICoSTA48221.2020.1570613717

Cite this

Sugianela, Y., & Ahmad, T. (2020). Pearson Correlation Attribute Evaluation-based Feature Selection for Intrusion Detection System. In Proceeding - ICoSTA 2020: 2020 International Conference on Smart Technology and Applications: Empowering Industrial IoT by Implementing Green Technology for Sustainable Development Article 9079263 (Proceeding - ICoSTA 2020: 2020 International Conference on Smart Technology and Applications: Empowering Industrial IoT by Implementing Green Technology for Sustainable Development). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICoSTA48221.2020.1570613717

Sugianela, Yuna ; Ahmad, Tohari. / Pearson Correlation Attribute Evaluation-based Feature Selection for Intrusion Detection System. Proceeding - ICoSTA 2020: 2020 International Conference on Smart Technology and Applications: Empowering Industrial IoT by Implementing Green Technology for Sustainable Development. Institute of Electrical and Electronics Engineers Inc., 2020. (Proceeding - ICoSTA 2020: 2020 International Conference on Smart Technology and Applications: Empowering Industrial IoT by Implementing Green Technology for Sustainable Development).

@inproceedings{db9387d5518143e0b13d88537fa6e883,

title = "Pearson Correlation Attribute Evaluation-based Feature Selection for Intrusion Detection System",

abstract = "IDS helps to overcome the network attack by taking appropriate preventive measures. The data mining method has good adaptability to new attack types; however, it consumes much time for high dimensional data. Therefore, the system needs a reduction of that high dimension. In this paper, we use a correlation approach of the attribute to evaluate those high dimensional data. To achieve a better environment, we propose a cut-off value of correlation to select some best features to use in the classification process. The best cut-off value in our experiment is 0.2 in RF classification that reaches 99.36\% accuracy. The selection feature can reduce the time consumed in the running system.",

keywords = "Pearson's correlation, feature, intrusion detection system, network security, selection",

author = "Yuna Sugianela and Tohari Ahmad",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 2020 International Conference on Smart Technology and Applications, ICoSTA 2020 ; Conference date: 20-02-2020",

year = "2020",

month = feb,

doi = "10.1109/ICoSTA48221.2020.1570613717",

language = "English",

series = "Proceeding - ICoSTA 2020: 2020 International Conference on Smart Technology and Applications: Empowering Industrial IoT by Implementing Green Technology for Sustainable Development",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "Proceeding - ICoSTA 2020",

address = "United States",

}

Sugianela, Y & Ahmad, T 2020, Pearson Correlation Attribute Evaluation-based Feature Selection for Intrusion Detection System. in Proceeding - ICoSTA 2020: 2020 International Conference on Smart Technology and Applications: Empowering Industrial IoT by Implementing Green Technology for Sustainable Development., 9079263, Proceeding - ICoSTA 2020: 2020 International Conference on Smart Technology and Applications: Empowering Industrial IoT by Implementing Green Technology for Sustainable Development, Institute of Electrical and Electronics Engineers Inc., 2020 International Conference on Smart Technology and Applications, ICoSTA 2020, Surabaya, Indonesia, 20/02/20. https://doi.org/10.1109/ICoSTA48221.2020.1570613717

Pearson Correlation Attribute Evaluation-based Feature Selection for Intrusion Detection System. / Sugianela, Yuna; Ahmad, Tohari.
Proceeding - ICoSTA 2020: 2020 International Conference on Smart Technology and Applications: Empowering Industrial IoT by Implementing Green Technology for Sustainable Development. Institute of Electrical and Electronics Engineers Inc., 2020. 9079263 (Proceeding - ICoSTA 2020: 2020 International Conference on Smart Technology and Applications: Empowering Industrial IoT by Implementing Green Technology for Sustainable Development).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Pearson Correlation Attribute Evaluation-based Feature Selection for Intrusion Detection System

AU - Sugianela, Yuna

AU - Ahmad, Tohari

PY - 2020/2

Y1 - 2020/2

N2 - IDS helps to overcome the network attack by taking appropriate preventive measures. The data mining method has good adaptability to new attack types; however, it consumes much time for high dimensional data. Therefore, the system needs a reduction of that high dimension. In this paper, we use a correlation approach of the attribute to evaluate those high dimensional data. To achieve a better environment, we propose a cut-off value of correlation to select some best features to use in the classification process. The best cut-off value in our experiment is 0.2 in RF classification that reaches 99.36% accuracy. The selection feature can reduce the time consumed in the running system.

AB - IDS helps to overcome the network attack by taking appropriate preventive measures. The data mining method has good adaptability to new attack types; however, it consumes much time for high dimensional data. Therefore, the system needs a reduction of that high dimension. In this paper, we use a correlation approach of the attribute to evaluate those high dimensional data. To achieve a better environment, we propose a cut-off value of correlation to select some best features to use in the classification process. The best cut-off value in our experiment is 0.2 in RF classification that reaches 99.36% accuracy. The selection feature can reduce the time consumed in the running system.

KW - Pearson's correlation

KW - feature

KW - intrusion detection system

KW - network security

KW - selection

UR - https://www.scopus.com/pages/publications/85084975259

U2 - 10.1109/ICoSTA48221.2020.1570613717

DO - 10.1109/ICoSTA48221.2020.1570613717

M3 - Conference contribution

AN - SCOPUS:85084975259

T3 - Proceeding - ICoSTA 2020: 2020 International Conference on Smart Technology and Applications: Empowering Industrial IoT by Implementing Green Technology for Sustainable Development

BT - Proceeding - ICoSTA 2020

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2020 International Conference on Smart Technology and Applications, ICoSTA 2020

Y2 - 20 February 2020

ER -

Sugianela Y, Ahmad T. Pearson Correlation Attribute Evaluation-based Feature Selection for Intrusion Detection System. In Proceeding - ICoSTA 2020: 2020 International Conference on Smart Technology and Applications: Empowering Industrial IoT by Implementing Green Technology for Sustainable Development. Institute of Electrical and Electronics Engineers Inc. 2020. 9079263. (Proceeding - ICoSTA 2020: 2020 International Conference on Smart Technology and Applications: Empowering Industrial IoT by Implementing Green Technology for Sustainable Development). doi: 10.1109/ICoSTA48221.2020.1570613717

Pearson Correlation Attribute Evaluation-based Feature Selection for Intrusion Detection System

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this