基于信息熵动态拟合的路径通行时间预测方法
|
摘要
文章采用基于信息熵动态拟合方法实现通行时间预测。首先,基于已有行程时间研究方法对各路段交通状态和通行时间计算,随后采用最小二乘法获取待预测路径的历史典型相似路径样本,进而获取待预测路径的各路段的通行参数并外推计算获取其通行时间,最后,基于信息熵的理念对通行路况进行动态拟合。实验表明该方法的可行性和准确性,从而为交通出行路径的规划,提供稳定可靠的指导建议。
The paper uses the method of dynamic fitting of information entropy to achieve prediction. Firstly,historical data collection is carried out for urban roads,and the traffic state and transit time of each road section are calculated based on the existing travel time research method. Subsequently,the least squares method is used to obtain the historical similar samples of the path to be predicted,and then the traffic parameters of each road segment to be predicted are obtained and extrapolated to obtain the transit time. Finally,based on the concept of information entropy,the traffic conditions are dynamically fitted. Experiments showthe feasibility and accuracy of the method,and provide stable and reliable guidance for the planning of traffic routes.
The paper uses the method of dynamic fitting of information entropy to achieve prediction. Firstly,historical data collection is carried out for urban roads,and the traffic state and transit time of each road section are calculated based on the existing travel time research method. Subsequently,the least squares method is used to obtain the historical similar samples of the path to be predicted,and then the traffic parameters of each road segment to be predicted are obtained and extrapolated to obtain the transit time. Finally,based on the concept of information entropy,the traffic conditions are dynamically fitted. Experiments showthe feasibility and accuracy of the method,and provide stable and reliable guidance for the planning of traffic routes.
引文
[1]《中国公路学报》编辑部.中国交通工程学术研究综述·2016[J].中国公路学报,2016,29(6):1-161.
[2]刘燕.基于车流量检测的交通灯控制系统设计[J].智能计算机与应用,2018,8(1):148-150.
[3]HARMS I M,BROOKHUIS K A. Dynamic traffic management on a familiar road:Failing to detect changes in variable speed limits[J]. Transportation Research Part F:Psychology and Behaviour.2016,38:37-46
[4]LADINO A,KIBANGOU A Y,DE WIT C C,et al. A real time forecasting tool for dynamic travel time from clustered time series[J]. Transportation Research Part C:Emerging Technologies. 2017(80):216-238.
[5]CHEN Meng,YU Xiaohui,LIU Yang. Mining moving patterns for predicting next location[J]. Information Systems. 2015,54(C):156-168.
[6]晏雨婵,白璘,武奇生,等.基于多指标模糊综合评价的交通拥堵预测与评估[J/OL].计算机应用研究:1-7[2018-10-31]. http://kns.cnki.net/kcms/detail/51.1196.TP.20181011.1259.032.html.
[7]戴洪波,曾献辉.基于BP神经网络的高速公路短时交通流预测[J].智能计算机与应用,2015,5(4):36-38,41.
[8]HAO Peng,BAN Xuegang(Jeff),YU J W. Kinematic equationbased vehicle queue location estimation method for signalized intersections using mobile sensor data[J]. Journal of Intelligent Transportation Systems. 2015(3):256-272
[9]孙兆祖.路径行程时间及其可靠性研究[D].成都:西南交通大学,2017.
[10]王雪菲,丁维龙.一种面向高速公路大数据的短时流量预测[J/OL].计算机应用:1-7[2018-10-31]. http://kns. cnki. net/kcms/detail/51.1307.TP.20180920.1020.034.html.
[2]刘燕.基于车流量检测的交通灯控制系统设计[J].智能计算机与应用,2018,8(1):148-150.
[3]HARMS I M,BROOKHUIS K A. Dynamic traffic management on a familiar road:Failing to detect changes in variable speed limits[J]. Transportation Research Part F:Psychology and Behaviour.2016,38:37-46
[4]LADINO A,KIBANGOU A Y,DE WIT C C,et al. A real time forecasting tool for dynamic travel time from clustered time series[J]. Transportation Research Part C:Emerging Technologies. 2017(80):216-238.
[5]CHEN Meng,YU Xiaohui,LIU Yang. Mining moving patterns for predicting next location[J]. Information Systems. 2015,54(C):156-168.
[6]晏雨婵,白璘,武奇生,等.基于多指标模糊综合评价的交通拥堵预测与评估[J/OL].计算机应用研究:1-7[2018-10-31]. http://kns.cnki.net/kcms/detail/51.1196.TP.20181011.1259.032.html.
[7]戴洪波,曾献辉.基于BP神经网络的高速公路短时交通流预测[J].智能计算机与应用,2015,5(4):36-38,41.
[8]HAO Peng,BAN Xuegang(Jeff),YU J W. Kinematic equationbased vehicle queue location estimation method for signalized intersections using mobile sensor data[J]. Journal of Intelligent Transportation Systems. 2015(3):256-272
[9]孙兆祖.路径行程时间及其可靠性研究[D].成都:西南交通大学,2017.
[10]王雪菲,丁维龙.一种面向高速公路大数据的短时流量预测[J/OL].计算机应用:1-7[2018-10-31]. http://kns. cnki. net/kcms/detail/51.1307.TP.20180920.1020.034.html.