Traffic Prediction System Using Machine Learning Algorithms

Abstract

Traffic congestion is defined as the state on transport which is characterized by slower speeds of vehicles this is also because of the bad condition of the roads, weather, concern zone, temperature, etc. This traffic flow prediction is mainly based on the realtime dataset which is collected with the help of various cameras and sensors. In recent day the deep learning concepts has dragged the attention for the detection of traffic flow predictions. In this paper, some of the common and familiar machine learning concepts like Deep Autoencoder (DAN), Deep Belief Network (DBN), and Random Forest (RF) are applied on the online dataset for the traffic flow predictions. The important attributes of weather, temperature, zone name, and day are used to predict the traffic flow of the particular zone. The performance of the proposed system can be evaluated by using accuracy, precision, and RMSE, and MSE value. Among the three methods, the DT technique produces a better result.