Empowering autonomous systems with AI-enabled V2X communication based signal analysis using sliding window integrated ensemble machine learning model

Abstract

Due to the rapid growth of the smart automotive industry, there has been a strong rise in interest in Internet of Vehicles (IoV) technology recently. Establishing rapid and reliable Vehicle-to-Everything (V2X) connections between several different cars and smart devices are another challenge. This research suggests unique method for autonomous vehicle communication that combines an ensemble of machine learning approaches with sliding window-based fourier transform signal processing. Here, a sliding window-based Fourier transform is used to handle the vehicle communication data together with ensemble reinforcement, spatial gradient, and radial encoder neural networks. Data throughput, energy use, QoS(quality of service), and communication costs are all considered in the experimental study. The outcomes demonstrate the viability of the strategy: applying ML techniques to V2X data allowed for prediction of majority of simulated incidents. Existence of a large number of FPs prevents the use of automated safety systems as a result, drivers must avoid collisions manually.