Traffic state prediction using ISOMAP manifold learning

Traffic state prediction is an essential problem with considerable implications in the intelligent transportation system. This paper puts forward an approach for predicting urban road traffic states based on ISOMAP manifold learning. By establishing a distance measurement that represents the overall geometric structure based on the Isometric Feature Mapping (ISOMAP) algorithm, this approach utilizes all consistent information regarding the traffic flow, thus improving the prediction accuracy of the road traffic state. The experimental results indicate that, compared with a traditional prediction approach, the equality coefficient has a bigger increase in value and a much lower prediction error. The traffic state prediction approach based on ISOMAP manifold learning achieves a higher level of accuracy.