A Multi-level Random Forest Model-Based Intrusion Detection Using Fuzzy Inference System for Internet of Things Networks

• Published in: International journal of computational intelligence systems 2023-03, Vol.16 (1), p.1-22, Article 31
• Main Authors: Awotunde, Joseph Bamidele, Ayo, Femi Emmanuel, Panigrahi, Ranjit, Garg, Amik, Bhoi, Akash Kumar, Barsocchi, Paolo
• Format: Article
• Language: English
• Subjects: Artificial Intelligence; Computational Intelligence; Control; Engineering; Fuzzy inference system; Intrusion detection; Mathematical Logic and Foundations; Mechatronics; Multi-level feature selection; NSL-KDD dataset; Random forest; Research Article; Robotics
• ISSN: 1875-6883; 1875-6883
• DOI: 10.1007/s44196-023-00205-w

Intrusion detection ( ID ) methods are security frameworks designed to safeguard network information systems. The strength of an intrusion detection method is dependent on the robustness of the feature selection method. This study developed a multi-level random forest algorithm for intrusion detection using a fuzzy inference system. The strengths of the filter and wrapper approaches are combined in this work to create a more advanced multi-level feature selection technique, which strengthens network security. The first stage of the multi-level feature selection is the filter method using a correlation-based feature selection to select essential features based on the multi-collinearity in the data. The correlation-based feature selection used a genetic search method to choose the best features from the feature set. The genetic search algorithm assesses the merits of each attribute, which then delivers the characteristics with the highest fitness values for selection. A rule assessment has also been used to determine whether two feature subsets have the same fitness value, which ultimately returns the feature subset with the fewest features. The second stage is a wrapper method based on the sequential forward selection method to further select top features based on the accuracy of the baseline classifier. The selected top features serve as input into the random forest algorithm for detecting intrusions. Finally, fuzzy logic was used to classify intrusions as either normal, low, medium, or high to reduce misclassification. When the developed intrusion method was compared to other existing models using the same dataset, the results revealed a higher accuracy, precision, sensitivity, specificity, and F1-score of 99.46%, 99.46%, 99.46%, 93.86%, and 99.46%, respectively. The classification of attacks using the fuzzy inference system also indicates that the developed method can correctly classify attacks with reduced misclassification. The use of a multi-level feature selection method to leverage the advantages of filter and wrapper feature selection methods and fuzzy logic for intrusion classification makes this study unique.