Traffic Congestion Prediction using Soft Computing Approach in Cognitive Internet of Vehicles

Abstract

Traffic congestion is a significant problem in urban cities, causing delays, fuel wastage, and adverse environmental effects. . In response to this challenge, Cognitive Internet of Vehicles (CIoV) has evolved as a revolutionary solution, utilizing advanced technologies to enhance traffic management systems. This paper proposes an approach for predicting traffic congestion by integrating multiple parameters, leveraging data from the Mobile Adaptive Routing Algorithm (MARA). Soft computing techniques, such as Support Vector Machine (SVM) and Artificial Neural Network (ANN), are used to develop an accurate and reliable predictive model. The experimental findings show that the model's high accuracy and reliability in traffic congestion prediction.The dataset generated through this approach proves to be a useful resource for urban planners, encouraging them to make informed decisions aimed at mitigating congestion. This predictive model offers a possible solution to the growing problem of urban traffic congestion by enhancing traffic management efficiency, promoting smoother traffic flow, and reducing environmental impact.