Realizing the short-term traffic prediction under various situations is important for the traffic to continue in a certain pattern or normal conditions. Most of the designed traffic forecasting models aim to present results for the future by taking into account all traffic conditions (accidents, weather conditions, road works, events, etc.). In this study, a traffic model has been developed in order for intelligent transportation systems to predict the traffic that will occur and make it easier to take action accordingly. In order to minimize the computational complexity in training phase, the Support Vector Regression (SVR) method, which is a Machine Learning (ML) method, has been preferred. The SVR model was trained using data collected from a busy intersection for Denizli province, and then short-term traffic prediction was performed. The hyper-parameter optimization of the model trained with four different directions and thirty-day data was made and the model accuracy was presented with several criteria. The results obtained by SVR model for traffic prediction are satisfactory in terms of prediction accuracy, similar to the typical traffic prediction models in the literature.
Short-term Traffic Prediction Based-on Support Vector Regression
25.10.2022
1576744 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Short-Term Traffic Flow Prediction Based on Lagrange Support Vector Regression
British Library Conference Proceedings | 2007
|British Library Conference Proceedings | 2020
|