Citation

Balasubaramanian, Sundaravadivazhagan and Hossen, Md. Jakir and Wong, Wai Kit and Ng, Poh Kiat (2025) Hybrid Feature Engineering Framework for Efficient Threat Detection. In: 2025 Multimedia University Engineering Conference, MECON 2025, 21 July 2025 - 23 July 2025, Cyberjaya, Malaysia.

Text 7.pdf - Published Version Restricted to Repository staff only Download (1MB)

Abstract

Internet of Things (IoT) network expansion has created escalating cyber security challenges which demand present-day and energy-saving methods for threat identification. Traditional intrusion detection systems encounter multiple challenges while adapting their detection procedures in various IoT networks. The study presents an improved feature engineering structure which unites statistical and time-series and deep learning methods to make IoT security networks more robust. At CICIoT2023 the research both determines efficient features for detection performance and enhances runtime efficiency through dataset analysis. XGBoost classifiers achieve remarkable detection results with 97.10% accuracy and precision of 97.15% while recalling 96.92% of anomalies in the data along with an F1-score of 97.03% and AUC-ROC score of 99.1%. The proposed framework surpasses present deep learning along with feature engineering solutions to establish itself as an optimal real-time security system for IoT networks.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	IoT, cyber security
Subjects:	T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5101-6720 Telecommunication. Including telegraphy, telephone, radio, radar, television
Divisions:	Faculty of Engineering and Technology (FET)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	18 Mar 2026 08:19
Last Modified:	19 Mar 2026 02:08
URII:	http://shdl.mmu.edu.my/id/eprint/15587

Downloads

Edit (login required)