The week's pick
Random Articles
Reseach Article
An Optimized Feature-based Lightweight Intrusion Detection System with Dual Classifiers
| International Journal of Applied Information Systems |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 13 - Number 2 |
| Year of Publication: 2026 |
| Authors: Omolola M. Bobade, Chukwuemeka C. Ugwu, Adebayo O. Adetunmbi, Olumide O. Obe |
10.5120/ijais2026452047
|
Omolola M. Bobade, Chukwuemeka C. Ugwu, Adebayo O. Adetunmbi, Olumide O. Obe . An Optimized Feature-based Lightweight Intrusion Detection System with Dual Classifiers. International Journal of Applied Information Systems. 13, 2 ( Mar 2026), 44-54. DOI=10.5120/ijais2026452047
Abstract
As network environments grow increasingly complex, so too do the patterns and sophistication of cyberattacks, necessitating more effective and intelligent security mechanisms. Machine learning-based intrusion detection systems (ML-IDS) have emerged as promising tools; however, they frequently encounter challenges such as low detection accuracy and high false positive rates. This study presents an enhanced ML-IDS that integrates Support Vector Machine (SVM) and Decision Tree (DT) classifiers, evaluated on the benchmark UNSW-NB15 dataset. The preprocessing pipeline involved converting categorical attributes into numerical representations, followed by Min-Max normalization to ensure uniform feature scaling. Feature selection and extraction were performed using Information Gain and Principal Component Analysis to reduce dimensionality and retain the most informative features. The classifiers were trained on the first top ten features for both to distinguish between normal and malicious traffics. Experimental results show that C4.5 DT outperforms SVM on both reduced feature reduction methods as it returns accuracy, precision, recall, and F1-score of 99.99%, 99.99%, 100% and 100% respectively on PCA, and 99.26%, 98.83%, 99.83% and 99.33% on IG feature selection. SVM returns the highest accuracy, recall, and F1-Score of 79.39%, 90.08% and 83.46% on PCA against 72.56%, 71.01%, and 82.00% on IG.
References
- Kaur, T., Malhotra, V., and Singh, D. 2014. Comparison of network security tools-firewall, intrusion detection system and Honeypot. Int. J. Enhanced Res. Sci. Technol. 3(2): 200-204.
- Adetunmbi, A.O., Falaki S. O., Adewale O. S., and Alese B. K. 2008. Network Intrusion Detection Based on Rough Set and K-Nearest Neighbor. International Journal of Computing and ICT Research, 2, 60-66.
- Kendall, K. 1999. A Database of Computer Attacks for the Evaluation of Intrusion Detection Systems. Master’s Thesis. Massachusetts Institute of Technology, Cambridge, MA
- Verwoerd, T., and Hunt, R. 2002. Intrusion detection techniques and approaches. Computer communications, 25(15), 1356-1365.
- Olayinka, T. C., Ugwu, C. C., Okhuoya, O. J., Adetunmbi, A. O., and Popoola, O. S. 2022. Combating network intrusions using machine learning techniques with multilevel feature selection method. In 2022 IEEE Nigeria 4th International Conference on Disruptive Technologies for Sustainable Development (NIGERCON) (pp. 1-5). IEEE.
- Popoọla, O. S., Ayogu, I. I., Mebawondu, Ọ. J., Ugwu, C. C., and Adetunmbi, A. O. 2022. An evolutionary approach towards achieving enhanced intrusion detection system. In 2022 IEEE Nigeria 4th International Conference on Disruptive Technologies for Sustainable Development (NIGERCON) (pp. 1-5). IEEE.
- Mebawondu, O. J., Popoọla, O. S., Ayogu, I. I., Ugwu, C. C., and Adetunmbi, A. O. 2022. Network intrusion detection models based on Naives Bayes and C4. 5 algorithms. In 2022 IEEE Nigeria 4th international conference on disruptive technologies for sustainable development (NIGERCON) (pp. 1-5). IEEE.
- Hozouri, A., Mirzaei, A., & Effatparvar, M. (2025). A comprehensive survey on intrusion detection systems with advances in machine learning, deep learning and emerging cybersecurity challenges. Discover Artificial Intelligence, 5(1), 314.
- Lin, Y., Zhang, Y., and Ou, Y. 2010. The Design and Implementation of Host-Based Intrusion Detection System. Third International Symposium on Intelligent Information Technology and Security Informatics.
- Larriva-Novo X, Sánchez-Zas C, Villagrá VA, Marín-Lopez A, Berrocal J. (2023). Leveraging explainable artificial intelligence in real-time cyberattack identification: intrusion detection system approach. Appl Sci.13(15):8587.
- Arreche O, Guntur T, Abdallah M. (2024) XAI-IDS: toward proposing an explainable artificial intelligence framework for enhancing network intrusion detection systems. Appl Sci.14(10):4170.
- Dini, P., Elhanashi, A., Begni, A., Saponara, S., Zheng, Q., & Gasmi, K. (2023). Overview on intrusion detection systems design exploiting machine learning for networking cybersecurity. Applied Sciences, 13(13), 7507.
- Singh, S., Silakari, S., and Patel, R., 2011. An efficient feature reduction technique for intrusion detection system. International Conference on Machine Learning and Computing Singapore, 3(8): 147-153
- Boulaiche, A., Bouzayani, H., and Adi, K. 2012. A Quantitative Approach for Intrusion Detection and Prevention based on Statistical N-gram Models. 3rd International Conference on Ambient Systems, Networks and Technology (ANT). Pp. 450-457
- Al-mamory, S. O., and Jassim, F. S. 2015. On the designing of two grains levels network intrusion detection system. Karbala International Journal of Modern Science, 1(1), 15-25.
- Obimbo, C, Zhou, H. and Wilson, R. 2011. Multiple SOFMs Working Cooperatively in a Vote-Based Ranking System for Network Intrusion Detection. Procedia Computer Science. 6(12): 219-224
- Duque, S., and bin Omar, M. N. 2015. Using data mining algorithms for developing a model for intrusion detection system (IDS). Procedia Computer Science, 61, 46-51.
- Aladesote, O. I., Alese, B. K., and Dahunsi, F. 2014. Intrusion detection technique using hypothesis testing. In Proceedings of the World Congress on Engineering and Computer Science (Vol. 1, No. 2, pp. 978-988).
- Rai, K., Devi, M. S., and Guleria, A. 2016. Decision tree-based algorithm for intrusion detection. International Journal of Advanced Networking and Applications, 7(4), 2828.
- Sarumi, O. A., Adetunmbi, A. O., and Adetoye, F. A. 2020. Discovering computer networks intrusion using data analytics and machine intelligence. Scientific African, 9, e00500.
- Mebawondu, J. O., Alowolodu, O. D., Mebawondu, J. O., and Adetunmbi, A. O. 2020. Network intrusion detection system using supervised learning paradigm. Scientific African, 9, e00497.
- Ugwu, C. C., Obe, O. O., Popoọla, O. S., and Adetunmbi, A. O. 2021. A distributed denial of service attack detection system using long, short-term memory with Singular Value Decomposition. In 2020 IEEE 2nd International conference on Cyberspac (CYBER NIGERIA) (pp. 112-118). IEEE.
- Olasehinde, O. O. 2020. A Stacked Ensemble Intrusion Detection Approach for the Protection of Information System. Int. J. Inf. Secur. Res, 10, 910-923.
- Moustafa, N., and Slay, J. 2015. UNSW-NB15: a comprehensive data set for network intrusion detection systems (UNSW-NB15 network data set). In 2015 military communications and information systems conference (MilCIS) (pp. 1-6). IEEE.
Index Terms
Keywords