Open AccessPerformance Evaluation of Supervised Ensemble Cyber Situation Perception Models for Computer Network
Author(s) -
S.S. Olofintuyi,
Temidayo Oluwatosin Omotehinwa
Publication year - 2021
Publication title -
advances in multidisciplinary and scientific research journal
Language(s) - English
Resource type - Journals
ISSN - 2488-8699
DOI - 10.22624/aims/cisdi/2021/v12n1p1
Subject(s) - c4.5 algorithm , computer science , support vector machine , machine learning , artificial intelligence , decision tree , naive bayes classifier , artificial neural network , random forest , intrusion detection system , ensemble learning , bayesian network , precision and recall , data mining
The trend at which cyber threats are gaining access to companies, industries and other sectors of the economy is becoming alarming, and this is posting a serious challenge to network administrators, governments and other business owners. A formidable intrusion detection system is needed to outplay the activities of the cyberattacks. An ensemble system is believed to perform better than a single classifier. With this fact, five different Machine Learning (ML) ensemble algorithms are suggested at the perception phase of Situation Awareness (SA) model for threat detection and the algorithms include; Artificial Neural Network Based Decision Tree (ANN based DT), Bayesian Based Artificial Neural Network (BN based ANN), J48 Based Naïve Bayes Model (J48 based NB), Decision Tree based Bayesian Network (BN) and Random Forest based on Support Vector Machine (RF based SVM). The efficiency and effectiveness of all the aforementioned algorithms were evaluated based on precision, recall and accuracy. ANN based DT gave 98.87% accuracy, BN based ANN gave 99.72% accuracy, J48 based NB gave 98.90% accuracy, DT based BN gave 89.92% accuracy and FR based SVM gave 98.40% accuracy. The implication of these results is that BN based ANN is more suitable in the perception phase of SA for threats detection. Keywords- Cyber-threats, Ensemble Algorithms, Computer Network, Intrusion Detection System, Machine Learning