Detection of intrusions in clustered vehicle networks using invasive weed optimization using a deep wavelet neural networks

Abstract

A VANET is a kind of IMS, or intelligent transportation system, that connects moving vehicles. Guaranteeing timely and accurate information sharing between vehicles and infrastructure helps make roads safer and more efficient. Wireless connections are used for data transmission in VANET, making security a critical design challenge. At the same time, the energy constrained ability of the vehicles in VANET creates energy efficiency as a challenging problem. In this aspect, this study presents an effective invasive weed optimization algorithm based energy efficient clustering with deep wavelet neural network based intrusion detection (IWOEEC-DWNN) technique for VANET. The clustered VANET is the target of the IWOEEC-DWNN approach, which seeks to detect any intrusions that may occur. In addition, the IWOEEC-DWNN method builds clusters through an IWO-based cluster technique's optimum cluster head (CH) selection and cluster design. In addition, the DWNN model is employed as a classification model to determine the occurrence of intrusions in the VANET. The design of IWOEEC-DWNN technique considerably helps to accomplish security and energy efficiency. Extensive computations were performed to test the efficacy of the IWOEEC-DWNN method, and the findings showed that it was superior to competing methods on a number of different metrics.

Keywords

• Vehicular adhoc networks
• Energy efficiency
• Clustering
• Intrusion detection
• Deep learning