Correlation analysis of road sections for short-time estimation and forecasting

For the short-time traffic state estimation and forecasting, road section grouping are necessary. However, previous researches on this problem are lack of quantitative analysis. To solve this problem, a section correlation analyzing method with traffic flow microwave data is proposed based on metric multidimensional scaling theory. With a dissimilarity matrix, scalar product matrix was calculated. Subsequently, section traffic flow reconstructing matrix could be got with principal components factor analysis, which could display section groups in low dimension. The proposed method is verified to be acceptable and effective.