| 283 | 10 | 194 |
| 下载次数 | 被引频次 | 阅读次数 |
为提高城市道路行程时间估计模型的准确度和有效性,本文利用浮动车数据,依据对传统模型思路的总结分别建立了基于路段长度比例和点速度调和平均值的两种行程时间初阶估计模型,并利用统计学中的同分布融合思想建立了行程时间融合模型,以修正初阶模型结果的精度,弥补传统估计模型中准确度低、效率不高的缺陷。最后选取成都市具有代表性的路网区域为算例,验证了初阶模型假设分布的正确性,同时计算出融合模型路径总时间的平均偏差仅为12%,说明了融合模型的准确度和有效性。
Abstract：To improve the accuracy of the model for estimating travel time of urban roads, based on we develop two kinds of initial estimation models of travel time based on the length ratio of the road and the mean value of the point velocity respectively. The two models employ the floating car data and the traditional model idea. Then a travel time fusion model is developed based on the same-distribution fusion ideas in statistics, which corrects the accuracy of the initial estimation models. This also improves the accuracy and efficiency of the tradition models. Finally, a representative road network area in Chengdu is selected as an example. The correctness of the hypothetical distribution of the initial estimation models are verified and the average deviation of the total path time of the fusion model is calculated to be only 12%, demonstrating the accuracy and validity of the fusion model.
[1]SHALABY A S,ABDULHAI B,BYON Y J.GISTT:GPS-GIS integrated system for travel time surveys[D].England:University of Toronto,2006.
[2]李慧兵,杨晓光,罗莉华.路段行程时间估计的浮动车数据挖掘方法[J].交通运输工程学报,2014,14(6):100-116.
[3]YANG J S.Travel time prediction using the GPS test vehicle and Kalman filtering techniques[C]//American Control Conference,Portland:IEEE,2005:2128-2133.
[4]HAGE R M,BETAILLE D,PEYRET F,et al.Unscented Kalman filter for urban network travel time estimation[J].Procedia-Social and Behavioral Sciences,2012,54(2290):1047-1057.
[5]ZHENG F,WAN Y,WU P.Link travel-time prediction using extended exponential Smoothing and Kalman filter in dynamic networks[C]//Eighth International Conference of Chinese Logistics and Transportation Professionals.Chengdu:ASCE,2009:3753-3759
[6]杨立娟.基于浮动车的城市道路行程时间采集与预测方法研究[D].长春:吉林大学,2007.
[7]HOFLEITNER A,HERRING R,ABBEEL P,et al.Learning the dynamics of arterial traffic from probe data using a dynamic bayesian network[J].IEEE Transactions on Intelligent Transportation Systems,2012,13(4):1679-1693.
[8]RAHMANI M,JENELIUS E,KOUTSOPOULOS H N.Non-parametric estimation of route travel time distributions from low-frequency floating car data[J].Transportation Research Part C Emerging Technologies,2015,58:343-362.
[9]武小云.基于GPS浮动车的城市交通路段行程时间实时估算方法研究[D].广州:华南理工大学,2010.
[10]王志建,马超锋,李梁.低频GPS数据和交叉口延误下的行程时间估计[J].西南交通大学学报,2015,50(2):361-367.
[11]CHANDIO A A,TZIRITAS N,ZHANG F,et al.An approach for map-matching strategy of GPS-trajectories based on the locality of road networks[J].Lecture Notes in Computer Science,2015,9502(1):234-246.
[12]渐猛.基于浮动车的道路交通状态判别方法研究[D].淄博:山东理工大学,2013.
基本信息:
中图分类号:U491
引用信息:
[1]罗霞,曹阳,刘博,等.基于浮动车数据的城市道路行程时间估计[J],2018,16(02):1-8.
基金信息:
成都市科技项目(2015-RK00-00208-ZF)