International Journal of Computer Networks and Applications (IJCNA) DOI: 10.22247/ijcna/2022/212336 Volume 9, Issue 2, March – April (2022) ISSN: 2395-0455 ©EverScience Publications 202 RESEARCH ARTICLE Analysis of Machine Learning Classifiers to Detect Malicious Node in Vehicular Cloud Computing A. Sheela Rini Department of Computer Science, Avinashilingam Institute for Home Science & Higher Education for Women, Coimbatore, Tamil Nadu, India sheelarini.a@gmail.com C. Meena Department of Computer Science, Avinashilingam Institute for Home Science & Higher Education for Women, Coimbatore, Tamil Nadu, India cccmeena@gmail.com Received: 31 January 2022 / Revised: 26 March 2022 / Accepted: 12 April 2022 / Published: 30 April 2022 Abstract – VANET or Vehicular networks are created using the principles of MANETS and are used by intelligent transport systems to offer efficient communication between the domains of vehicles. Increasing the number of vehicles requires communication between vehicles to be fast and secure, where cloud computing with VANET is more prominent. To provide a secure VANET communication environment, this paper proposes a malicious or hacked vehicle identification system. Malicious vehicles are identified using four steps. The first step uses a clustering algorithm for similar group vehicles. In the Second step, cluster heads are identified and elected. In the next step, Multiple Point Relays are selected. Finally, classifiers are used to identify hacked vehicles. However, the existing system performance degrades as soon as the number of vehicles increases, resulting in increased cost during Cluster head election, inability to produce stable clusters, and the need for accurate and fast classification in high traffic scenarios. This work improves clustering algorithms and examines several classification algorithms to solve these issues. The classifiers analyzed are Decision Tree (DT), Support Vector Machine (SVM), K-Nearest Neighbour (KNN) and Naïve-Bayes (NB). A Hybrid classifier that combines SVM and KNN classifiers is also analyzed for its effectiveness to detect malicious vehicles. From the experimental results, it could be observed that the detection accuracy is high while using the hybrid classifier. Index Terms – VANET, Malicious Node, SVM, Decision Tree, Naïve-Bayes, KNN. 1. INTRODUCTION The increased number of vehicles on the roads requires effective methods to improve road safety, driver & passenger comfort and efficient transportation. One breakthrough in road safety technology is real-time communication using VANET (Vehicular Ad hoc NETwork), where vehicles exchange information [1,2]. It is a part of an intelligent transport system and combines the concepts of MANETs with cloud computing to address various issues involving vehicular applications involving safety and comfort application [3]. During communication, VANETs face several challenges related to low process capability, mainly due to limited resource availability like memory, computation power, and bandwidth. However, the increase in the number of vehicles demands a communication environment that can handle fast and secure message sharing and high storage capacity[4]. This necessity can be handled efficiently using Vehicular cloud computing or VCC, which combines VANETs with cloud computing [5]. The VCC uses the cloud’s advantages that allow sharing of available resources among the neighbouring vehicles within a transmission range. The basic components of VCC include RSUs (Road-Side Units), moving vehicles, computer-controlled devices, radio transceivers for exchanging messages, sensors for sensing surrounding environments, GPS (Global Positioning System) and cloud servers. VCC provides various advantages like driver/traveller safety efficiency in managing safety and comfort applications. The VCC has three types of communication models: the cluster-based model, Road Side Unit model and Vehicle-to- Vehicle (V2V) model. The scope of this work is a cluster- based communication model, as this is the latest and most advanced architecture used. Cluster-based communication groups similar nodes based on different characteristics of VCCs. Examples of such characteristics include velocity, direction and density. In each cluster one vehicle is designated as Cluster Head (CH), and the rest are so-called Cluster Members (CMs). This model’s working is very similar to the client/server architecture, where the CMs act as the clients and the CHs act as the server. All the CHs are interconnected with one another, and the communication only occurs through CHs. The cluster-based communication model in VCC offers