Please wait a minute...
浙江大学学报(工学版)  2018, Vol. 52 Issue (3): 453-460    DOI: 10.3785/j.issn.1008-973X.2018.03.006
土木与交通工程     
基于梯度提升回归树的城市道路行程时间预测
龚越1, 罗小芹1, 王殿海1, 杨少辉2
1. 浙江大学 建筑工程学院, 浙江 杭州 310058;
2. 中国城市规划设计研究院, 北京 100037
Urban travel time prediction based on gradient boosting regression tress
GONG Yue1, LUO Xiao-Qin1, WANG Dian-hai1, YANG Shao-hui2
1. College of Civil Engineering and Architecture, Zhejiang University, Hangzhou 310058, China;
2. China Academy of Urban Planning & Design, Beijing 100037, China
 全文: PDF(3128 KB)   HTML
摘要:

为了提高行程时间的预测精度,在考虑时间序列相关性的同时,分析相邻路段的空间相关性对于行程时间的影响,并提出基于梯度提升回归树模型的城市道路行程时间预测方法.对车牌识别设备获取的实际数据进行预处理,并提出相应的补全算法以解决数据缺失问题,建立完整的历史数据集.通过分析各影响因素与行程时间的相关性,构建特征向量.为了能更好地理解模型,通过梯度提升回归树模型输出各变量对于预测结果的重要度.利用实际数据对模型进行评估,预测行程时间的平均绝对误差百分比,约为10.0%.与SVM、ARIMA等方法相比,所提方法具有较高的精度.

Abstract:

A new method based on gradient boosting regression tress was proposed in order to improve the prediction accuracy of travel time, considering the correlation of the time series, and also took into account spatial correlation. First, massive data collected by license plate recognition equipment was preprocessed, and the missing data problem was solved by corresponding data completion algorithm. Then the travel time historical data set was established. By analyzing the correlation between the different influence factors and travel time, the feature vector was established. Moreover, in order to better understand the model, the importance of each feature vector was proposed by gradient boosting regression tress model. Finally, the actual data was used to evaluate the model, and the average absolute error percentage of the travel time is about 10.0%. Compared with SVM, ARIMA and other methods, the proposed method has higher accuracy.

收稿日期: 2017-05-06 出版日期: 2018-09-11
CLC:  U491  
基金资助:

国家自然科学基金资助项目(51338008,51408538);国家自然科学基金资助项目(61773337);浙江省自然科学基金资助项目(LY17F030009).

通讯作者: 王殿海,男,教授,博导.orcid.org/0000-0001-6066-2274.     E-mail: wangdianhai@zju.edu.cn
作者简介: 龚越(1992-),男,硕士生,从事交通控制研究.orcid.org/0000-0001-6694-7537.E-mail:gongyue@zju.edu.cn
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
作者相关文章  

引用本文:

龚越, 罗小芹, 王殿海, 杨少辉. 基于梯度提升回归树的城市道路行程时间预测[J]. 浙江大学学报(工学版), 2018, 52(3): 453-460.

GONG Yue, LUO Xiao-Qin, WANG Dian-hai, YANG Shao-hui. Urban travel time prediction based on gradient boosting regression tress. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2018, 52(3): 453-460.

链接本文:

http://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2018.03.006        http://www.zjujournals.com/eng/CN/Y2018/V52/I3/453

[1] 付凤杰, 龚越, 王殿海,等. 基于高清智能卡口路段行程时间的数据质量分析[J]. 浙江大学学报:工学版,2016,50(9):1761-1767. FU Feng-jie, GONG Yue, WANG Dian-hai, et al. Data quality analysis of link travel time based on HD smart gate[J]. Journal of Zhejiang University:Engineering Science, 2016,50(9):1761-1767.
[2] WILLIAMS B,DURVASULA P, BROWN D. Urban freeway traffic flow prediction:application of seasonal autoregressive integrated moving average and exponential smoothing models[J]. Transportation Research Record:Journal of the Transportation Research Board, 1998(1644):132-141.
[3] WILLIAMS B M, HOEL L A. Modeling and forecasting vehicular traffic flow as a seasonal ARIMA process:Theoretical basis and empirical results[J]. Journal of transportation engineering, 2003, 129(6):664-672.
[4] 胡继华, 李国源, 程智锋. 基于马尔科夫链的公交站间行程时间预测算法[J]. 交通信息与安全, 2014, 32(2):17-22. HU Ji-hua, LI Guo-yuan, CHEN Zhi-feng. Algorithm for predicting bus travel time between stops based on markov chain[J].Journal of Transport Information and Safety, 2014, 32(2):17-22.
[5] JI Y J, TANG D N, GUO W H, et al. Forecasting available parking space with largest Lyapunov exponents method[J]. Journal of Central South University, 2014, 21(4):1624-1632.
[6] 李进燕, 朱征宇, 刘琳, 等. 基于简化路网模型的卡尔曼滤波多步行程时间预测方法[J]. 系统工程理论与实践, 2013, 33(5):1289-1297. LI Jin-yan, ZHU Zheng-yu, LIU Ling, et al. Multi-step kalman filtering travel time estimation method based on simplified road network model[J].Systems Engineering:Theory & Practice, 2013,33(5):1289-1297.
[7] 丁宏飞, 李演洪, 刘博, 等. 基于BP神经网络与SVM的快速路行程时间组合预测研究[J]. 计算机应用研究, 2016, 33(10):2929-2932. DING Hong-fei, LI Yan-hong, LIU Bo, et al. Expressway's travel time prediction based on combined BP neural network and support vector machine approach[J]. Application Research of Computers, 2016, 33(10):2929-2932.
[8] 王翔, 陈小鸿, 杨祥妹. 基于K最近邻算法的高速公路短时行程时间预测[J]. 中国公路学报, 2015, 28(1):102-111. WANG Xiang, CHEN Xiao-hong, YANG Xiang-mei. Short term prediction of expressway travel time based on K nearest neighbor algorithm[J]. China Journal of Highway and Transport, 2015, 28(1):102-111.
[9] 张娟, 孙剑. 基于SVM的城市快速路行程时间预测研究[J]. 交通运输系统工程与信息, 2011, 11(2):174-179. ZHANG Juan, SUN Jian. Prediction of urban express way travel time based on SVM[J]. Journal of Transportation Systems Engineering and Information Technology, 2011, 11(2):174-179.
[10] AHMED M, ABDEL-ATY M. Application of stochastic gradient boosting technique to enhance reliability of real-time risk assessment:use of automatic vehicle identification and remote traffic microwave sensor data[J]. Transportation Research Record:Journal of the Transportation Research Board, 2013(2386):26-34.
[11] CHUNG Y S. Factor complexity of crash occurrence:An empirical demonstration using boosted regression trees[J]. Accident Analysis & Prevention, 2013, 61:107-118.
[12] LIU Q C, LU J, CHEN S U. Design and analysis of traffic incident detection based on random forest[J]. Journal of Southeast University, 2014, 1:88-95.
[13] ZHANG Y, HAGHANI A. A gradient boosting method to improve travel time prediction[J]. Transportation Research Part C:Emerging Technologies, 2015, 58:308-324.
[14] FRIEDMAN J H. Greedy function approximation:a gradient boosting machine[J]. Annals of Statistics, 2001:1189-1232.
[15] 范金城, 梅长林. 数据分析[M]. 北京:科学出版社, 2002:6.

[1] 张帅超, 朱谊, 陈喜群. 基于移动检测数据的宏观基本图特征[J]. 浙江大学学报(工学版), 2018, 52(7): 1338-1344.
[2] 李文婧, 孙锋, 李茜瑶, 马东方. 采用递归有序聚类的信号控制时段划分方法[J]. 浙江大学学报(工学版), 2018, 52(6): 1150-1156.
[3] 阮树斌, 王福建, 马东方, 金盛, 王殿海. 基于车牌识别数据的机动车出行轨迹提取算法[J]. 浙江大学学报(工学版), 2018, 52(5): 836-844.
[4] 梅振宇, 章伟. 基于复杂性测度的泊位占有率序列动力学分析[J]. 浙江大学学报(工学版), 2018, 52(4): 727-734.
[5] 曲昭伟, 罗瑞琪, 陈永恒, 曹宁博, 邓晓磊, 汪昆维. 信号交叉口右转机动车轨迹特性[J]. 浙江大学学报(工学版), 2018, 52(2): 341-351.
[6] 曹宁博, 陈永恒, 曲昭伟, 赵利英, 白乔文, 杨秋杰. 基于社会力模型的行人路径选择模型[J]. 浙江大学学报(工学版), 2018, 52(2): 352-357.
[7] 杨庆芳, 赵小辉, 郑黎黎, 张伟. 基于模型预测控制的环形交叉口信号配时方法[J]. 浙江大学学报(工学版), 2018, 52(1): 117-124.
[8] 杨方宜, 李铁柱. 大型综合客运枢纽送站坪交通特性及通行能力[J]. 浙江大学学报(工学版), 2017, 51(11): 2207-2214.
[9] 吴江玲, 张生瑞, Amit Kumar Singh, 秦思, 孙振东. 高速公路强制换道持续时间半参数生存分析[J]. 浙江大学学报(工学版), 2017, 51(11): 2215-2221.
[10] 于德新, 田秀娟, 杨兆升, 周熙阳, 程泽阳. 改进的干线协调信号控制优化模型[J]. 浙江大学学报(工学版), 2017, 51(10): 2019-2029.
[11] 季学斌, 王慧, 宋春跃. 基于元胞自动机的施工场内交通流建模及安全分析[J]. 浙江大学学报(工学版), 2017, 51(10): 2005-2011.
[12] 李显生, 孟凡淞, 郑雪莲, 任园园, 严佳晖. 交通冲突类型对驾驶人生理特性的影响[J]. 浙江大学学报(工学版), 2017, 51(9): 1720-1726.
[13] 王薇, 程泽阳, 刘梦依, 杨兆升. 基于时空相关性的交通流故障数据修复方法[J]. 浙江大学学报(工学版), 2017, 51(9): 1727-1734.
[14] 商强, 林赐云, 杨兆升, 邴其春, 邢茹茹. 基于变量选择和核极限学习机的交通事件检测[J]. 浙江大学学报(工学版), 2017, 51(7): 1339-1346.
[15] 刘美岐, 沈莉潇, 金盛. 考虑右转信号控制的共用车道通行能力模型[J]. 浙江大学学报(工学版), 2017, 51(7): 1347-1354.