Efficient IoT Intrusion Detection Using Mutual Information And Pca-Based Feature Reduction With Ensemble Machine Learning
Từ khóa
DOI:
https://doi.org/10.66890/JSTIC.2026.11.01.104Tóm tắt
The rapid proliferation of Internet of Things (IoT) devices has significantly expanded the attack surface for cyber threats, making robust Intrusion Detection Systems (IDS) indispensable. This paper presents an efficient machine learning-based IDS for IoT networks leveraging Mutual Information (MI) for feature selection and Principal Component Analysis (PCA) for dimensionality reduction, applied to the IoT-23 dataset. MI identifies six discriminative features from eight preprocessed attributes, which PCA further transforms into four principal components preserving 99% of the total data variance. Four ensemble classifiers—Random Forest (RF), XGBoost, Bagging-SVM (BG-SVM), and AdaBoost—are evaluated under Bayesian hyperparameter optimization with 5-fold cross-validation. All models achieve accuracy exceeding 99.7%, with RF attaining peak performance at 99.834% accuracy, 99.589% precision, 99.753% recall, and 99.671% F1-score. Compared with the notable reference deep learning ensemble proposed in [14] on the identical dataset, the proposed method surpasses in accuracy (+0.584%), recall (+4.753%), and F1-score (+1.671%) while requiring significantly lower computational resources. The results confirm the effectiveness of MI-PCA feature engineering for lightweight, high-accuracy intrusion detection in resource-constrained IoT environments.
##plugins.themes.default.displayStats.downloads##
Tài liệu tham khảo
[1] S. Balaji, K. Nathani, and R. Santhakumar, “IoT technology, applications and challenges: A contemporary survey,” Wirel. Pers. Commun., vol. 108, no. 1, pp. 363–388, Sep. 2019, doi: 10.1007/S11277-019-06407-W.
[2] “IoT connections worldwide 2034,” Statista. Accessed: May 05, 2026. [Online]. Available: https://www.statista.com/statistics/1183457/iot-connected- devices-worldwide/
[3] F. Hussain, S. G. Abbas, M. Husnain, U. U. Fayyaz, F. Shahzad, and G. A. Shah, “IoT DoS and DDoS attack detection using ResNet,” in Proc. 23rd IEEE Int. Multi-Topic Conf. (INMIC), Nov. 2020, doi: 10.1109/INMIC50486.2020.9318216.
[4] A. Alfahaid, E. Alalwany, A. M. Almars, F. Alharbi, E. Atlam, and I. Mahgoub, “Machine learning-based security solutions for IoT networks: A comprehensive survey,” Sensors, vol. 25, no. 11, May 2025, doi: 10.3390/S25113341.
[5] B. Aydin, H. Aydin, and S. Gormus, “Intrusion detection sys- tems in IoT: A detailed review of threat categories, detection strategies, and future technologies,” J. Inf. Secur. Appl., vol. 95, p. 104291, Dec. 2025, doi: 10.1016/J.JISA.2025.104291.
[6] M. M. Rahman, S. Al Shakil, and M. R. Mustakim, “A survey on intrusion detection system in IoT networks,” Cyber Secur. Appl., vol. 3, p. 100082, Dec. 2025, doi: 10.1016/J.CSA.2024.100082.
[7] “IoT-23 dataset: A labeled dataset of malware and benign IoT traffic,” Stratosphere Laboratory. Accessed: May 05, 2026. [Online]. Available: https://www.stratosphereips.org/datasets- iot23
[8] V. T. Pham, H. L. Nguyen, H. C. Le, and M. T. Nguyen, “Machine learning-based intrusion detection system for DDoS attack in the Internet of Things,” in Proc. Int. Conf. Syst. Sci. Eng. (ICSSE), 2023, pp. 375–380, doi: 10.1109/IC- SSE58758.2023.10227227.
[9] V. T. Pham, K. T. Nguyen, C. T. Nguyen, and H. C. Le, “Ef- ficient hierarchical ML-based IoT intrusion detection system leveraging PSO and sequential forward feature selection,” Lect. Notes Data Eng. Commun. Technol., vol. 230, pp. 318–327, 2024, doi: 10.1007/978-3-031-75596-5 29.
[10] P. Nimbalkar and D. Kshirsagar, “Feature selection for in- trusion detection system in Internet-of-Things (IoT),” ICT Express, vol. 7, no. 2, pp. 177–181, Jun. 2021, doi: 10.1016/J.ICTE.2021.04.012.
[11] V. T. Pham, K. T. Nguyen, C. T. Nguyen, and H. C. Le, “GAT- SFFS: A novel feature selection method using graph atten- tion networks and sequential forward approach for machine learning-based IoT intrusion detection system,” in Proc. Int. Conf. Adv. Technol. Commun. (ATC), 2024, pp. 573–578, doi: 10.1109/ATC63255.2024.10908143.
[12] O. D. Okey et al., “MLCFSM: Multi-layer common feature se- lection methods for robust intrusion detection in IoT network,” in Proc. NIGERCON, 2024, p. 187, doi: 10.1109/NIGER- CON62786.2024.10927398.
[13] G. Logeswari, K. Thangaramya, M. Selvi, and J. D. Roselind, “An improved synergistic dual-layer feature selection algo- rithm with two type classifier for efficient intrusion detection in IoT environment,” Sci. Rep., vol. 15, no. 1, pp. 8050, Mar. 2025, doi: 10.1038/s41598-025-91663-z.
[14] V. Dutta, M. Chora´s, M. Pawlicki, and R. Kozik, “A deep learning ensemble for network anomaly and cyber-attack de- tection,” Sensors, vol. 20, no. 16, pp. 1–20, Aug. 2020, doi: 10.3390/S20164583.
[15] I. Ullah and Q. H. Mahmoud, “Design and development of RNN anomaly detection model for IoT networks,” IEEE Access, vol. 10, pp. 62722–62750, 2022, doi: 10.1109/AC- CESS.2022.3176317.
[16] S. W. Nourildean, W. Mefteh, and A. M. Frihida, “Intrusion detection system-based ensemble machine learning to improve IoT network against cyber attacks,” J. Supercomput., vol. 82, no. 6, pp. 370, Apr. 2026, doi: 10.1007/S11227-026-08529-Y.
[17] M. U. Tanveer, K. Munir, M. Amjad, S. A. J. Zaidi, A. Bermak, and A. U. Rehman, “Ensemble-Guard IoT: A lightweight en- semble model for real-time attack detection on imbalanced dataset,” IEEE Access, vol. 12, pp. 168938–168952, 2024, doi: 10.1109/ACCESS.2024.3495708.
[18] J. Hu, X. Wang, and Y. Liu, “Enhancing network intrusion detection: A comparative analysis of machine learning models on complex network traffic data,” in Proc. 2nd Int. Conf. IoT Cloud Comput. Technol. (IoTCCT), vol. 1, Dec. 2024, pp. 364– 368, doi: 10.1145/3702879.3702942.
[19] J. R. Mettu and D. Singh, “A hybrid approach for feature extraction of multi-class dataset in IDS,” Comput. Fraud Secur., pp. 149–156, Dec. 2024, doi: 10.52710/CFS.84.
[20] J. Wang, X. Xiong, G. Chen, R. Ouyang, Y. Gao, and O. Alfar- raj, “Multi-criteria feature selection based intrusion detection for Internet of Things big data,” Sensors, vol. 23, no. 17, Aug. 2023, doi: 10.3390/S23177434.
[21] N. Abdalgawad, A. Sajun, Y. Kaddoura, I. A. Zualkernan, and F. Aloul, “Generative deep learning to detect cyberattacks for the IoT-23 dataset,” IEEE Access, vol. 10, pp. 6430–6441, 2022, doi: 10.1109/ACCESS.2021.3140015.
[22] T. M. Cover and J. A. Thomas, Elements of Information Theory. Hoboken, NJ, USA: Wiley, 2005, doi: 10.1002/047174882X.
[23] O. Sagi and L. Rokach, Eds., Ensemble Machine Learning. New York, NY, USA: Springer, 2012, doi: 10.1007/978-1- 4419-9326-7.
