Machine learning algorithms for privacy preserving in vehicular ad hoc network

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