Application of SVR with Genetic optimization algorithm in urban traffic flow forecasting

Forecasting of inter-urban traffic flow has been one of the most important issues globally in the research on road traffic congestion. Due to traffic flow forecasting involves a rather complex nonlinear data pattern; there are lots of novel forecasting approaches to improve the forecasting accuracy. This investigation presents a short-term traffic forecasting model which combines the support vector regression (SVR) model with Genetic Optimization algorithms (SVRGA) to forecast inter-urban traffic flow. Additionally, a numerical example is employed to elucidate the forecasting performance of the proposed SVRGA model. Finally the results compare and their performance with time series models.

Keywords:

Traffic flow forecasting , Support vector regression (SVR) , Genetic Optimization algorithms (GA)