Clustered Ensemble Feature Selection with M-GRU Classification for Efficient Intrusion Detection System of Industrial Systems

Résumé

Abstract In today's scenario, infrastructures, such as the power grid and nuclear power plant, the industrial control system (ICS) is crucial. Yet, there is growing worry that ICS systems are susceptible to threats or attacks, and that even minor changes or manipulation could cause major damage to industrial operations. In this paper, an efficient intrusion detection system with clustered ensemble feature selection and Multi-Level Modified Gated Recurrent Unit (M-GRU) classification model is proposed. Clustered ensemble feature selection approach is to find the best feature subset. The features are ranked based on scores from base algorithms and aggregated using aggregation algorithms. Diverse base algorithms are elected using clustering technique. The features designated are fed into a multi class classification algorithm Multi-Level Modified Gated Recurrent Unit (M-GRU). NSL-KDD training and testing dataset is used in this work for feature selection and classification. The results infer that the proposed feature selection method with classification model improves accuracy and lowers false alarm rate compared to other models.

Citer ce document

Accès au document

Ce document est hébergé sur son dépôt institutionnel d'origine.

Auteur(s)

Statistiques

Consultations : 1

Téléchargements : 0