Design of Feature Selection Algorithm Based on MOEA for IDSs in VANETs
Junwei Liang, Maode Ma · 2020
Intrusion detection systems (IDSs) is crucial for the security of Vehicle Ad Hoc Networks (VANETs), as it can accurately detect both the inner and outer attacks. However, the redundant features and the sparse samples of fatal attacks in VANETs datasets cause the heavy time-consumption and imbalanced problems respectively. In this paper, a feature selection algorithm based on a many-objective optimization algorithm (FS-MOEA) is proposed for IDSs in VANETs, in which Non-dominant Sorting Genetic Algorithm-III (NSGA-III) serves as the many-objective evolutionary algorithm. Two improvements, called Bias and Weighted (B&W) niche-preservation and Analytic Hierarchy Process (AHP) prioritizing, are further designed in FS-MOEA. B&W niche-preservation is used to counterbalance the imbalanced problem among the different classes of datasets by assigning rare classes higher priorities in the niching selection process. AHP prioritizing is employed to search the optimal feature subset from the non-dominant feature subsets in the Pareto Front of FS-MOEA. Experimental results show that the proposed FS-MOEA can not only improve the performance of IDSs in VANETs by decreasing the redundancy and irrelevances of features but also alleviate the negative impact of the imbalanced problem.