Description

Cities today must address the challenge of sustainable mobility, and traffic state forecasting plays a key role in mitigating traffic congestion. For example, predicting path travel time is a crucial issue in navigation and route planning applications. Furthermore, the pervasive penetration of information and communication technologies makes vehicles data an important source of real-time data for intelligent transportation system applications. The problem of forecasting traffic prediction vehicles traffic jam data is available. A comparison of deep learning methods is presented to demonstrate the capabilities of the neural network approaches LSTM (Long Short Term Memory) in solving the traffic forecasting problem. Different tests are proposed in order to not only evaluate the developed Machine learning (Linear regression) models, but also to analyse how the penetration the traffic forecasting result reduce the loss value and high prediction performance.