An Investigation about Traffic Prediction by Using ANN and SVM Algorithms

As urbanization increases, traffic congestion takes more time and causes costs. Estimating traffic density and planning has become necessary for people living in metropolitan cities and using traffic lines. This study also uses past congested traffic to Artificial Neural Network (ANN), and traffic density was estimated using Support Vector Machine (SVM). The study defines the different weather conditions and weather conditions as a model for the problem than many studies in the equivalent literature and can model the change according to the changing weather. It was tested in the model using 21000 data from 5 different points collected from the Istanbul Metropolitan Municipality Open Data Portal, and the MAE successfully detected the traffic density under 9km/h.