<![CDATA[The Internet of Things (IoT) enables a wide variety of intelligent devices to connect and interact. The rapid development of technology and protocols as well as the growth of networks, makes IoT a security risk. The increasing number of interconnected intelligent electronic equipment has an impact on the complexity of the network and the increase in the volume of network traffic resulting in high-dimensional data. The feature selection technique has been proven to reduce very large (high-dimensional) network traffic data in the Intrusion Detection System (IDS). The feature selection technique is also faced with the problem of imbalanced data. In real network traffic data tends to be imbalanced, where attack traffic is less than normal data. IoT as a complex network produces a large number of features. However, not all features are relevant for identifying normal traffic and attacks. The right feature selection technique is needed to produce optimal features. In this study, a wrapper-based feature selection technique is proposed using a subset evaluator classifier with the J48 algorithm. The dataset used is CICIDS-2017 MachineLearningCSV version. Of the 78 features analyzed using the proposed method, 15 features were generated as optimal features. Optimal features are used for anomaly detection using the Random Forest algorithm. The experimental results show that attack detection with optimal features produces an average accuracy of 99.87% on training and testing data.]]>
Copyrights © 2022
