TY - GEN
T1 - A study on vehicle trip distribution forecasting based on BP neural network
AU - Meng, Xiang Hai
AU - Liu, Qing
AU - Du, Ying Chun
AU - Lu, Jian
PY - 2009
Y1 - 2009
N2 - Trip distribution is an important step of the four-phase method in transportation demand forecasting. It is affected by many factors. First, factors influencing vehicle trip distribution are analyzed and the results show that location potential, traffic impedance, trip production, and trip attraction play an important role. Second, an aggregation scale factor of the traffic zone is evaluated by fuzzy algorithm and the zone accessibility is calculated, and then, the location potential that is determined by the aggregation scale factor and zone accessibility is obtained. Third, traffic impedance based on travel time is determined based on analyzing the influences of traffic flow discontinuation, bicycles, pedestrians, and width of lanes. Finally, the trip distribution forecasting model based on the BP neural network which takes location potential, traffic impedance, trip production, and trip attraction as input parameters and the result of trip distribution as output parameters is established. The test shows that the forecasting result fits well with the survey data. Thus, the BP neural network model can be used for trip distribution forecasting with high prediction accuracy.
AB - Trip distribution is an important step of the four-phase method in transportation demand forecasting. It is affected by many factors. First, factors influencing vehicle trip distribution are analyzed and the results show that location potential, traffic impedance, trip production, and trip attraction play an important role. Second, an aggregation scale factor of the traffic zone is evaluated by fuzzy algorithm and the zone accessibility is calculated, and then, the location potential that is determined by the aggregation scale factor and zone accessibility is obtained. Third, traffic impedance based on travel time is determined based on analyzing the influences of traffic flow discontinuation, bicycles, pedestrians, and width of lanes. Finally, the trip distribution forecasting model based on the BP neural network which takes location potential, traffic impedance, trip production, and trip attraction as input parameters and the result of trip distribution as output parameters is established. The test shows that the forecasting result fits well with the survey data. Thus, the BP neural network model can be used for trip distribution forecasting with high prediction accuracy.
KW - BP neural network
KW - Impedance function
KW - Location potential
KW - Trip distribution
UR - https://www.scopus.com/pages/publications/71049135727
U2 - 10.1061/41064(358)161
DO - 10.1061/41064(358)161
M3 - 会议稿件
AN - SCOPUS:71049135727
SN - 9780784410646
T3 - Proceedings of the 9th International Conference of Chinese Transportation Professionals, ICCTP 2009: Critical Issues in Transportation System Planning, Development, and Management
SP - 1150
EP - 1155
BT - Proceedings of the 9th International Conference of Chinese Transportation Professionals, ICCTP 2009
PB - ASCE - American Society of Civil Engineers
T2 - 9th International Conference of Chinese Transportation Professionals, ICCTP 2009: Critical Issues in Transportation System Planning, Development, and Management
Y2 - 5 August 2009 through 9 August 2009
ER -