Citation

Ahmed, Rasel and Sen, Anik and Fahad, Nafiz and Hossen, Md. Jakir and Tasnim, Sazzad Hossain and Hossain, Samiha and Ahmed, Tanvir (2026) Fusion of machine learning techniques for robust anomaly detection in cybersecurity during data sharing. In: 5th International Conference on Mathematics, Engineering and Industrial Applications, ICoMEIA 2024, 26 October 2024 - 27 October 2024, Kedah, Malaysia.

Text 13.pdf - Published Version Restricted to Repository staff only Download (186kB)

Abstract

In cybersecurity, anomaly detection is essential for spotting anomalous trends and defending digital ecosystems from new dangers, especially when sharing data. This current study introduced a novel anomaly detection model which helps to detect anomalies during data sharing. This study used BETH dataset, known for its comprehensive sensor logs, to evaluate the performance of the proposed models. The ensemble models, which combine two single machine learning models. This current study used two ensemble models which are ensemble of (LR-KNN) and ensemble of (RF-SVM). The ensemble of LR-KNN and RF-SVM achieved 99.58% accuracy which surpassed the existing studies. In essence accuracy of the proposed ensemble models surpasses the existing studies which is why this current study offered significant improvements in anomaly detection.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Machine learning
Subjects:	Q Science > Q Science (General) > Q300-390 Cybernetics
Divisions:	Faculty of Engineering and Technology (FET) Faculty of Information Science and Technology (FIST) Faculty of Artificial Intelligence & Engineering (FAIE)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	04 May 2026 05:27
Last Modified:	07 May 2026 08:39
URII:	http://shdl.mmu.edu.my/id/eprint/15881

Downloads

Edit (login required)