Enhancing traffic flow and congestion management in smart cities utilizing SVM-based linear regression approach

With the development of smart cities, it is essential to monitor traffic flow and manage congestion effectively to ensure smooth movement for people and address their social and economic needs. As these needs continue to change, roadside infrastructure faces challenges in meeting the demands of citizens in smart cities. Traffic congestion is a major issue in road networks and occurs when the number of vehicles exceeds the capacity of the roads. Emerging technologies like Vehicular Networks (VN) and Support Vector Machine (SVM)-based linear regression offer promising solutions for vehicle-to-vehicle communication and managing autonomous roadside infrastructure. SVM-based linear regression is a well-known and effective method for addressing various issues related to roadside infrastructure, traffic management, data integration, analytics, and environmental monitoring. The main goal of using SVM-based linear regression in this research is to help citizens and city authorities make informed decisions and better understand and control traffic. This study demonstrates the application of SVM-based linear regression in integrating autonomous roadside infrastructure, achieving a high accuracy rate of 92% and reducing errors by 8%, showing a notable improvement compared to previous methods.