Traffic condition estimation with pre-selection space time model

A pre-selection space time model was proposed to estimate the traffic condition at poor-data-detector, especially non-detector locations. The space time model is better to integrate the spatial and temporal information comprehensibly. Firstly, the influencing factors of the ＂cause nodes＂ were studied, and then the pre-selection ＂cause nodes＂ procedure which utilizes the Pearson correlation coefficient to evaluate the relevancy of the traffic data was introduced. Finally, only the most relevant data were collected to compose the space time model. The experimental results with the actual data demonstrate that the model performs better than other three models.