Intelligent intrusion Detection of computer networks using Random Forest Algorithm

Document Type : Original Article

Authors

1 Department of Computer Engineering, Faculty of Technology and Engineering, Yasouj University, Yasouj, Iran

2 Department of Electrical Engineering, Faculty of Technology and Engineering, Adiban Institute of Higher Education, Garmsar, Iran.

3 Department of Computer Engineering, Faculty of Technology and Engineering, Yasouj University, Yasouj, Iran.

Abstract

Intelligent intrusion detection systems are one of the important research fields in computer network security. The purpose of the intrusion detection system is to detect and identify attacks and detect security problems in computer systems and networks and notify security managers. The main algorithm used in this article is the random forest algorithm. To check the effectiveness of the proposed algorithm in intelligent intrusion detection, the NSL-KDD dataset has been used, which includes 125,973 samples and has 41 features. Since the random forest algorithm is a hybrid algorithm and is created from several decision trees, it achieves high accuracy in intelligent intrusion detection. By using this algorithm, we were able to increase the accuracy of intelligent intrusion detection by 99.89%.

References

Han, J., & Kamber, M. (2011). Pei. Data mining concepts and techniques. MK.
Liao, H. J., Lin, C. H. R., Lin, Y. C., & Tung, K. Y. (2013). Intrusion detection system: A comprehensive review. Journal of Network and Computer Applications, 36(1), 16-24. https://doi.org/10.1016/j.jnca.2012.09.004
Salo, F., Nassif, A. B., & Essex, A. (2019). Dimensionality reduction with IG-PCA and ensemble classifier for network intrusion detection. Computer Networks, 148, 164-175. https://doi.org/10.1016/j.comnet.2018.11.010
Senthil Murugan, N., & Usha Devi, G. (2018). Detecting streaming of Twitter spam using hybrid method. Wireless Personal Communications, 103(2), 1353-1374. https://doi.org/10.1007/s11277-018-5513-z
Khodayar M., Uzada A., (2013), intrusion detection in computer networks using combined machine learning techniques. 9th Science and Technology Advances Symposium, Second Commission of the National Conference of Computer Science and Engineering with a focus on national security and sustainable development, 12 pages.   
Zhang, Y ., Lee, W., Huang, Y., (2003). Intrusion Detection Techniques for Mobile Wireless Networks, Mobile Networks and Applications, 16 Pages.
 Viegas, E., Santin, A. O., Fransa, A., Jasinski, R., Pedroni, V. A., Oliveira, L. S. (2017). "Towards an Energy-Efficient Anomaly-Based Intrusion Detection Engine for Embedded Systems". IEEE Transactions on Computers. 66 (1): 163–177. doi:10.1109/TC.2016.2560839.
Maymandi, S., Mohammadi Shiv Kash, H., (2016). Investigating and analyzing intrusion detection solutions using data mining techniques,3-rd international conference on research in science and technology, 11 pages.   
Heydari H., (2013), a proposed algorithmic paper to detect intrusion in computer networks using the combination of particle swarm method and Bayesian model classification, place of publication: the first international conference on the latest developments in electrical, electronic and computer engineering 5 pages.              
Amini Khoei Z., Abdulla Puri A., 2015, title of the article Network traffic classification using improved random forest algorithm, place of publication: Journal of Computer Science, 15 pages.    
Venkatesan, N., & Priya, G. (2015). A study of random forest algorithm with implementation using WEKA. International journal of innovative research in computer science and engineering, 1(6), 156-162.              
Cutler, A., Cutler, D. R., & Stevens, J. R. (2012). Random Forests. Στο Ensemble Machine Learning (pp. 157–175). doi:10.1007/978-1-4419-9326-7_5
Transactions on Machine Intelligence
Volume 2, Issue 1
December 2019
Pages 48-58

Files

History

  • Receive Date: 22 January 2019
  • Revise Date: 14 March 2019
  • Accept Date: 10 July 2019

Share

How to cite

Statistics