Distance and Clustered Feature Selection for the Pattern Recognition of Intrusion Detection in Communication Networks

Authors

  • N. Chitra Research Scholar, Department of Electronics and Communication Engineering, SOE, Presidency University, Bangalore, India
  • Safinaz S. Associate Professor, Department of Electronics and Communication Engineering, SOE,Presidency University, Bangalore, India

Keywords:

Distance-clustered feature selection, classifier, feature selection, mutual Information, true positive rate, accuracy, intrusion detection System, C4, 5 classifier

Abstract

Information related to various types of sensor networks, satellite networks, and communication networks stores a large pool of data in the cloud increasing its usage. As more people access the data, traffic increases and intrusion into the system and detection are unavoidable and can be avoided using intrusion detection system (IDS) to avoid attacks. The effectiveness of IDS is improved by giving the input which has no noise or attacks so that the performance can be improvised. The feature selection concept which reduces the noise and gives the better objects can be deployed in the IDS which make the system to work smoothly in the network. The proposed algorithm Distance- clustered feature selection is based on the distance between the features and proves the effectiveness of Distance- clustered feature selection (DCFS) using C4.5 classifiers, taking the KDDCUP 99 dataset as input. Modified mutual information feature selection algorithm (MMIFSA), dynamic mutual information feature selection algorithm(DMIFSA), and redundant penalty feature mutual information algorithm (RPFMI) models are simulated using the KDDCUP 99 dataset, and their outcomes in comparison with Distance- clustered feature selection are observed. The distance- clustered feature selection outcomes, when compared with the other mutual information-based feature selection algorithms, proved to be more effective. Various performance metrics to build the distance- clustered feature selection model are evaluated and has shown better improvement in TPR and accuracy of 99.948%, indicating the proposed algorithm is effective and all the parameters are improved compared to other algorithms.

Downloads

Download data is not yet available.

References

Ambusaidi, Mohammed A. "Using Mutual Information for Feature Selection in a Network Intrusion Detection System." The Third International Conference on Digital Security and Forensics (DigitalSec2016). 2016.

Amiri, F., et al. "Yazdani. N,“Mutual information-based feature selection for intrusion detection systems,”." Journal of network and computer applications 34.4 (2011): 1184-1199.

Battiti, Roberto. "Using mutual information for selecting features in supervised neural net learning." IEEE Transactions on neural networks 5.4 (1994): 537-550.

Estévez, Pablo A., et al. "Normalized mutual information feature selection." IEEE Transactions on neural networks 20.2 (2009): 189-201.

Estévez, Pablo A., et al. "Normalized mutual information feature selection." IEEE Transactions on neural networks 20.2 (2009): 189-201.

Estévez, Pablo A., et al. "Normalized mutual information feature selection." IEEE Transactions on neural networks 20.2 (2009): 189-201.

Cup, Kdd. "Intrusion Detection Dataset Task Description." University of California Department of Information and Computer Science (1999).

Peng, Hanchuan, Fuhui Long, and Chris Ding. "Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy." IEEE Transactions on pattern analysis and machine intelligence 27.8 (2005): 1226-1238.

Bharill, Neha, and Aruna Tiwari. "A review of clustering techniques and developments." (2017).

Song, Jingping, et al. "Modified mutual information-based feature selection for intrusion detection systems in decision tree learning." Journal of computers 9.7 (2014): 1542-1546.

NagaJyothi, Grande, and Sriadibhatla SriDevi. "Distributed arithmetic architectures for fir filters-a comparative review." 2017 International conference on wireless communications, signal processing and networking (WiSPNET). IEEE, 2017.

Song, Jingping, Zhiliang Zhu, and Chris Price. "Feature grouping for intrusion detection system based on hierarchical clustering." Availability, Reliability, and Security in Information Systems: IFIP WG 8.4, 8.9, TC 5 International Cross-Domain Conference, CD-ARES 2014 and 4th International Workshop on Security and Cognitive Informatics for Homeland Defense, SeCIHD 2014, Fribourg, Switzerland, September 8-12, 2014. Proceedings 9. Springer International Publishing, 2014.

Karthick Raghunath, K. M., et al. "Utilization of IoT-assisted computational strategies in wireless sensor networks for smart infrastructure management." International Journal of System Assurance Engineering and Management (2022): 1-7.

Avanija, J., et al. "Designing a Fuzzy Q-Learning Power Energy System Using Reinforcement Learning." International Journal of Fuzzy System Applications (IJFSA) 11.3 (2022): 1-12.

Zhao, Fei, et al. "A filter feature selection algorithm based on mutual information for intrusion detection." Applied Sciences 8.9 (2018): 1535.

Kartika S. (2016). Analysis of “SystemC” design flow for FPGA implementation. International Journal of New Practices in Management and Engineering, 5(01), 01 - 07. Retrieved from http://ijnpme.org/index.php/IJNPME/article/view/41

Mohammad Hassan, Machine Learning Techniques for Credit Scoring in Financial Institutions , Machine Learning Applications Conference Proceedings, Vol 3 2023.

Downloads

Published

30.11.2023

How to Cite

Chitra, N. ., & S., S. . (2023). Distance and Clustered Feature Selection for the Pattern Recognition of Intrusion Detection in Communication Networks. International Journal of Intelligent Systems and Applications in Engineering, 12(6s), 69–75. Retrieved from https://ijisae.org/index.php/IJISAE/article/view/3940

Issue

Vol. 12 No. 6s (2024)

Section

Research Article

License

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.

IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.