A Real-Time Traffic Information Prediction Model Based on AOSVR and On-Line Learning

Acquiring the real-time information about traffic flow is one of the important steps toward the realization of ITS. In this paper, we propose a real-time traffic prediction model with warm start by integrating an accurate on-line support vector regression (AOSVR) with a corrected on-line learning algorithm that is used for improving computational rate. The forecasting implementation has showed that the proposed model is faster and more exact than AOSVR with both cold and warm start when it is applied to an actual real-time forecasting scheme