Machine learning algorithms for privacy preserving in vehicular ad hoc network

Abstract

Machine learning (ML) will improve the outcomes through the use of methods that categorize the information into the predetermined set. This work is to present an estimation and assessment of machine learning techniques for achieving privacy preservation in vehicular ad hoc networks (VANETs). This method generates two distinct group keys for prime and secondary users. Road side units (RSUs) are deployed to broadcast one group key from the trusted authority (TA) to the primary users, and secondary users are utilized to transmit the other group key. The main aim of this network is developed to avoid vulnerable attacks and to enhance the privacy of this network, Naïve Bayesian classifier (BC), support vector machine (SVM), K-nearest neighbor (KNN), artificial neural networks (ANN), Bayesian network (BN) methods are utilized in correlation with the proposed deep neural networks (DNN) with the black widow optimization (BWO) for protection preserving. These learning characterization procedures are assessed concerning delay, network lifetime, throughput, delivery ratio, and drop and this proposed calculation (DNN-BWO) shows improved results than the current methodologies.