Hybrid Feature Selection for Anomaly Detection in IoT Network Intrusion Detection Systems

Open AccessArticle

Hybrid Feature Selection for Anomaly Detection in IoT Network Intrusion Detection Systems

Volume 11, Issue 2, Page No 17–29, 2026

Author’s Name: Mya Soe Soe Moe* 1Email, Win Mar Oo 2Email
1 Faculty of Computer Science, University of Computer Studies Mandalay, Myanmar
2 University of Computer Studies Mandalay, Myanmar
*whom correspondence should be addressed. E-mail: myasoesoe.moe@gmail.com

Adv. Sci. Technol. Eng. Syst. J. 11(2), 17–29 (2026); crossref symbol DOI: 10.25046/aj110203

Keywords: IoT security, Intrusion detection system, Hybrid feature selection, Anomaly detection, Machine learning, Network traffic

Received: 26 February 2026, Revised: 15 March 2026, Accepted: 17 March 2026, Published Online: 5 April 2026
(This article belongs to Section Artificial Intelligence in Computer Science (CAI))
229 Downloads
Export Citations

The rapid growth of Internet of things (IoT) devices have heightened the need for effective Intrusion Detection System (IDS) to combat evolving cyber threats. The IoT networks has the security challenges due to the heterogeneous and high-dimensional nature of network traffic data, redundant features, and class imbalance which hinder detection accuracy and efficiency. Effective IDS requires robust feature selection mechanisms to enhance detection accuracy and reduce computational complexity. The research proposes a hybrid feature section method that combines filter and embedded techniques through a weighted scheme. Chi-square and Mutual Information scores are fused with a weighting mechanism and interests with Random Forest feature importance for anomaly detection in IoT environments. The proposed hybrid feature selection approach is evaluated on three benchmark IoT intrusion detection datasets, ACI-IoT2023, BoT-IoT, and TON-IoT datasets using five supervised classifiers: Random Forest, Decision Tree, K-Nearest Neighbour, Support Vector Machine, and Naïve Bayes classifiers. The study evaluated the proposed system for both binary and multiclass classification scenario. Experimental results demonstrated that the proposed feature selection with Random Forest classifier achieves the highest performance 99.93%, 99.98%, 99.01% in accuracy on each dataset respectively.

  1. T.M. Ghazal, M.K. Hasan, M.T. Alshurideh, H.M. Alzoubi, M. Ahmad, S.S. Akbar, B. Al Kurdi, I.A. Akour, “IoT for Smart Cities: Machine Learning Approaches in Smart Healthcare—A Review,” Future Internet, 13(8), 218, 2021, https://doi.org/10.3390/fi13080218.
  2. A. Zanella, N. Bui, A. Castellani, L. Vangelista, M. Zorzi, “Internet of Things for Smart Cities,” IEEE Internet of Things Journal, 1(1), 22–32, 2014, https://doi.org/10.1109/JIOT.2014.2306328.
  3. E. Gyamfi, A. Jurcut, “Intrusion detection in internet of things systems: A review on design approaches leveraging multi-access edge computing, machine learning, and datasets,” Sensors, 22(10), 1–33, 2022, https://doi.org/10.3390/s22103744.
  4. H. Wang, T.M. Khoshgoftaar, K. Gao, “A comparative study of filter-based feature ranking techniques,” in IEEE International Conference on Information Reuse and Integration, 43–48, 2010, https://doi.org/10.1109/IRI.2010.5558913.
  5. M.A.M. Hasan, M. Nasser, S. Ahmad, K.I. Molla, “Feature selection for intrusion detection using random forest,” Journal of Information Security, 7, 129–140, 2016, https://doi.org/10.4236/jis.2016.73009.
  6. D.S. Ahmed, “Anomaly-based network intrusion detection system for IoT using deep learning model,” Scientific Research Journal of Engineering and Computer Science, 3(5), 16–23, 2023, https://doi.org/10.47310/srjecs.2023.v03i02.010.
  7. G. Guo, X. Pan, H. Liu, F. Li, L. Pei, K. Hu, “An IoT intrusion detection system based on TON-IoT network dataset,” in IEEE 13th Annual Computing and Communication Workshop and Conference (CCWC), 333–338, 2023, https://doi.org/10.1109/CCWC57344.2023.10099144.
  8. G. Logeswari, J.D. Roselind, K. Tamilarasi, V. Nivethitha, “A comprehensive approach to intrusion detection in IoT environments using hybrid feature selection and multi-stage classification techniques,” IEEE Access, 13, 24970–24987, 2025.
  9. A.G. Ayad, N.A. Sakr, N.A. Hikal, “A hybrid feature selection model for anomaly-based intrusion detection in IoT networks,” in International Telecommunications Conference (ITC-Egypt), 1–7, 2024.
  10. F.A. Alotaibi, S. Mishra, “Cyber security intrusion detection and bot data collection using deep learning in the IoT,” International Journal of Advanced Computer Science and Applications, 15(3), 421–432, 2024.
  11. I. Kerrakchou, A.A. El Hassan, S. Chadli, M. Emharraf, M. Saber, “Selection of efficient machine learning algorithm on BoT-IoT dataset for intrusion detection in internet of things networks,” Indonesian Journal of Electrical Engineering and Computer Science, 31(3), 1784–1793, 2023, https://doi.org/10.11591/ijeecs.v31.i3.pp1784-1793.
  12. J. Han, J. Pei, M. Kamber, Data Mining: Concepts and Techniques, 3rd ed., Elsevier, 2011, ISBN 9780123814791.
  13. N. V. Chawla, K.W. Bowyer, L.O. Hall, W.P. Kegelmeyer, “SMOTE: Synthetic minority over-sampling technique,” Journal of Artificial Intelligence Research, 16, 321–357, 2002, https://doi.org/10.1613/jair.953.
  14. J. Li, M.S. Othman, H. Chen, L.M.M. Yusuf, “Optimizing IoT intrusion detection system: Feature selection versus feature extraction in machine learning,” Journal of Big Data, 11(1), 36, 2024, https://doi.org/10.1186/s40537-024-00892-y.
  15. S. Walling, S. Lodh, “Network intrusion detection system for IoT security using machine learning and statistical based hybrid feature selection,” Security and Privacy, 7(6), 2024, https://doi.org/10.1002/spy2.429.
  16. P.N. Tan, M. Steinbach, V. Kumar, Introduction to Data Mining, Pearson Education India, 2016.
  17. N. Hoque, D.K. Bhattacharyya, J.K. Kalita, “MIFS-ND: A mutual information-based feature selection method,” Expert Systems with Applications, 41(14), 6371–6385, 2014, https://doi.org/10.1016/j.eswa.2014.04.019.
  18. L. Breiman, “Random forests,” Machine Learning, 45(1), 5–32, 2001.
  19. X. Yuan, S. Liu, W. Feng, G. Dauphin, “Feature importance ranking of random forest-based end-to-end learning algorithm,” Remote Sensing, 15(21), 5203, 2023, https://doi.org/10.3390/rs15215203.
  20. P. Rani, R. Kumar, A. Jain, “A hybrid approach for feature selection based on correlation feature selection and genetic algorithm,” International Journal of Software Innovation, 10(1), 1–17, 2022, https://doi.org/10.4018/IJISMD.2021040102.
  21. V. Kantharaju, et al., “Machine learning based intrusion detection framework for detecting security attacks in internet of things,” Scientific Reports, 14(1), 30275, 2024, https://doi.org/10.1038/s41598-024-81535-3.
  22. A. Liaw, M. Wiener, “Classification and regression by random forest,” R News, 2(3), 18–22, 2002.
  23. J.R. Quinlan, “Induction of decision trees,” Machine Learning, 1(1), 81–106, 1986.
  24. T.M. Mitchell, Machine Learning, McGraw-Hill, 1997.
  25. T. Cover, P. Hart, “Nearest neighbor pattern classification,” IEEE Transactions on Information Theory, 13(1), 21–27, 1967, https://doi.org/10.1109/TIT.1967.1053964.
  26. C. Cortes, V. Vapnik, “Support-vector networks,” Machine Learning, 20, 273–297, 1995, https://doi.org/10.1007/BF00994018.
  27. C.J. Vargas, et al., “Intrusion detection in Internet of Things systems: A feature extraction with Naive Bayes classifier approach,” Journal of Machine and Computing, 4(1), 2024, https://doi.org/10.53759/7669/jmc202404003.
  28. Australian Centre for Internet of Things Security Research, “ACI-IoT 2023 Dataset,” 2023.
  29. N. Moustafa, J. Slay, “The BoT-IoT dataset: A comprehensive benchmark for IoT network intrusion detection,” 2020.
  30. N. Moustafa, et al., “TON-IoT: A multi-source dataset for evaluating federated and centralized intrusion detection systems in IoT,” 2021.

Citations by Dimensions

Citations by PlumX

Google Scholar

Crossref Citations

No. of Downloads Per Month
No. of Downloads Per Country

Journal Menu

Journal Browser


Special Issues

Special Issue on Digital Frontiers of Entrepreneurship: Integrating AI, Gender Equity, and Sustainable Futures
Guest Editors: Dr. Muhammad Nawaz Tunio, Dr. Aamir Rashid, Dr. Imamuddin Khoso
Deadline: 30 May 2026

Special Issue on Indigenous Knowledge Systems of the Tribal Communities of the Asia Pacific
Guest Editors: Dr. Anurag Hazarika
Deadline: 31 October 2026

Special Issue on Sustainable Technologies for a Resilient Future
Guest Editors: Dr. Debasis Mitra, Dr. Sourav Chattaraj, Dr. Addisu Assefa
Deadline: 30 April 2026