Voting Classifier-Based Machine Learning Technique for the Prediction of the Traffic Flow for the Intelligent Transportation System

A vital function of the intelligent transportation system is traffic flow prediction. This is an exact forecast of the amount of traffic in a certain location on a given day in the future. The study of traffic forecasting helps to lessen traffic while promoting more affordable, safe, and efficient forms of transportation. Although conventional models rely on shallow networks, the number of vehicles has increased exponentially in recent years, making these standard machine learning methods unsuitable for the present situations. The proposed research presents a voting classifier-based machine learning algorithm (ML) that combines many ML techniques, including random forest, naive Bayes, logistic regression, and SVM. The experimental findings demonstrate that, in comparison to the conventional methods, the suggested voting classifier achieved greater accuracy and precision rate.