US National Research Council;Los Angeles, CA: SAGE Publications
摘要:
摘要： Travel time information is generally nonlinear and nonstationary in a dynamic environment, and therefore no consistent tendency can be easily observed. This research developed a novel approach that combined the empirical decomposition method for speed data analysis and gray theory for travel time prediction to predict the arrival time at each stop along a bus route. In addition, sensitivity analysis was performed for different numbers of stops. With an average prediction error of less than 3.5%, the experiments showed that the proposed prediction approach, which employed both historical and real-time speed data collected from the geographic positioning system, outperformed Chou's approach, which used only historical speed data. The proposed prediction method could be readily incorporated into a cell phone–based information retrieval system that indicated bus position en route as well as its arrival times at all stops. 出版者： Los Angeles, CA: SAGE Publications 出版日期： 2012-01 出處： Transportation research record, 2012-01, Vol.2324 (1), p.11-19 版權： 2012 National Academy of Sciences 識別號： ISSN: 0361-1981 識別號： EISSN: 2169-4052 識別號： DOI: 10.3141/2324-02
