Short-Term Traffic Flow Predication Based on PSO-SVM

The accurate predication of short-term traffic flow is essential in ITS. On the basis of analyzing the parameter performance of support vector machine (SVM) for regression estimation, the paper proposes a short-term traffic flow predication model based on PSO-SVM. The parameter of SVM was optimized by using particle swarm optimization (PSO). The method takes advantage of the minimum structure risk of SVM and the quickly globally optimizing ability of PSO. As the proposed model can reduce the dimensionality of data space and preserve features of traffic flow time series, it can efficiently predict traffic flow. The simulation results of traffic flow collected from Chinese national highway G107 prove its validity. The average predication error is 3.4%.