Enhancing V2x Communication in Intelligent Vehicles Using Deep Learning Models

The surge in Vehicle-to-Everything (V2X) communication marks a pivotal evolution in intelligent transportation systems, enhancing safety, efficiency, and sustainability in urban mobility.This thesis introduces a groundbreaking framework that harnesses deep learning models to elevate V2X communication in intelligent vehicles.This framework focuses on adapting and optimizing communication protocols via an innovative algorithm.It specifically targets the prevalent challenges of latency, reliability, and scalability by dynamically predicting and managing communication patterns using advanced deep learning techniques.A key innovation of this study is the development of an adapted algorithm that real-time optimizes data transmission paths and schedules, considering the dynamic nature of urban traffic environments.