Peak traffic forecasting using nonparametric approaches

Abstract

States of traffic situations can be classified into peak and nonpeak periods. The complexity of peak traffic brings more difficulty to forecasting models. Travel time index (TTI) is a fundamental measure in transportation. How to master the characteristics and provide accurate real-time forecasts is essential to intelligent transportation systems (ITS). Cooperating with state space approach, least squares support vector machines (LS-SVMs) are investigated to solve such a practical problem in this paper. To the best of our knowledge, it is the first time to apply the technique and analyze the forecast performance in the domain. For comparison purpose, other two nonparametric predictors are selected because of their effectiveness proved in past research. Having good generalization ability and guaranteeing global minima, LS-SVMs perform better than the others. Providing sufficient improvement in stability and robustness reveals that the approach is practically promising.