一种基于Gradient Boosting的公交车运行时长预测方法

赖永炫; 杨旭; 曹琦; 曹辉彬; 王田; 杨帆

doi:10.11959/j.issn.2096-0271.2019042

您当前的位置：

首页 >

文章列表页 >

一种基于Gradient Boosting的公交车运行时长预测方法

研究 | 更新时间：2024-06-03

- 一种基于Gradient Boosting的公交车运行时长预测方法
- A bus running length prediction method based on Gradient Boosting
- 大数据 2019年5卷第5期页码：2019042-1
- 作者机构：
  
  1. 厦门大学信息学院，福建厦门 361005
  2. 厦门大学深圳研究院，广东深圳 518057
  3. 长春公交（集团）有限责任公司，吉林长春 130000
  4. 龙岩烟草工业有限责任公司，福建龙岩 364000；5.华侨大学计算机科学与技术学院，福建厦门 361021；6.厦门大学航空与航天学院，福建厦门 361005
  5. 华侨大学计算机科学与技术学院，福建厦门 361021
  6. 厦门大学航空与航天学院，福建厦门 361005
- 作者简介：
  
  [ "赖永炫（1981-），男，博士，厦门大学副教授，主要研究方向为交通大数据分析、车载网络。" ]
  [ "杨旭（1975-），男，长春公交（集团）有限责任公司助理工程师，主要研究方向为公交排班管理和公交系统信息化。" ]
  [ "曹琦（1982-），男，龙岩烟草工业有限责任公司工程师，主要从事生产制造信息化与自动化及质量控制领域方面的研究与应用工作。" ]
  [ "曹辉彬（1997-），男，厦门大学信息学院硕士生，主要研究方向为交通大数据分析、车载网络。" ]
  [ "王田（1982-），男，博士，华侨大学计算机科学与技术学院教授，主要研究方向为智能感知网络、交通大数据分析、车载网络。" ]
  [ "杨帆（1982-），男，博士，厦门大学航空与航天学院副教授，主要研究方向为数据挖掘、聚类研究。" ]
- 基金信息：
  
  国家自然科学基金资助项目;The National Natural Science Foundation of China(61672441);国家自然科学基金资助项目;The National Natural Science Foundation of China(61872154);深圳市基础研究计划基金资助项目;The Shenzhen Basic Research Proyram(JCYJ20170818141325209);福建省自然科学基金资助项目;The Natural Science Foundation of Fujian(2018J01097)
- DOI：10.11959/j.issn.2096-0271.2019042
  中图分类号： TP399
- 网络首发：2019-09，
  
  纸质出版：2019-09-15
- 稿件说明：
移动端阅览
赖永炫, 杨旭, 曹琦, 等. 一种基于Gradient Boosting的公交车运行时长预测方法[J]. 大数据, 2019,5(5):2019042-1.

Yongxuan LAI, Xu YANG, Qi CAO, et al. A bus running length prediction method based on Gradient Boosting[J]. Big Data Research, 2019, 5(5): 2019042-1.
赖永炫, 杨旭, 曹琦, 等. 一种基于Gradient Boosting的公交车运行时长预测方法[J]. 大数据, 2019,5(5):2019042-1. DOI： 10.11959/j.issn.2096-0271.2019042.

Yongxuan LAI, Xu YANG, Qi CAO, et al. A bus running length prediction method based on Gradient Boosting[J]. Big Data Research, 2019, 5(5): 2019042-1. DOI： 10.11959/j.issn.2096-0271.2019042.

摘要

目前，我国公交公司主要依靠经验丰富的工作人员估计车辆回场时间，进而进行车辆调度，此方式缺乏辅助的预测方法，常常造成较大的误差与错误的调度决策。从公交公司的实际需求出发，提出了一种基于动态特征选择的预测方法R-GBDT。R-GBDT利用特征选择组件和模型调参组件为预测组件提供符合线路特征的特征组合与参数，由融合组件对其他组件的结果进行融合，形成一个用于预测最终时间间隔的框架。结果表明，相对于其他算法，所提方法能大大提高公交运行时长预测的准确度。

Abstract

At present

China’s public transport companies rely on experienced staff to estimate the return time of vehicles and then conduct vehicle dispatch.This method often results in large errors and wrang decisions due to the lack of auxiliary prediction methods.Based on the actual needs of bus companies

a prediction method R-GBDT based on dynamic feature selection was proposed.The R-GBDT utilizes feature selection components and model parameter adjustment components to provide predictive components with feature combinations and parameters that conform to the line characteristics

then the fusion component combines the results of other components to form a framework for predicting the final time interval.The experimental results from real bus to off-site data show that compared with other algorithms

the method can greatly improve the accuracy of bus transit time prediction.

关键词

Keywords

references

陆化普 , 李瑞敏 . 城市智能交通系统的发展现状与趋势 [J ] . 工程研究-跨学科视野中的工程 , 2014 ( 1 ): 6 - 19 .

LU H P , LI R M . Developing trend of ITS and strategy suggestions [J ] . Journal of Engineering Studies , 2014 ( 1 ): 6 - 19 .

LI Y G , FU K , WANG Z , et al . Multi-task representation learning for travel time estimation [C ] // The 24th ACM SIGKDD International Conference on Knowledge Discovery ＆ Data Mining,August 19-23,2018,London,UK . New York:ACM Press , 2018 : 1695 - 1 704.

曹宏 , 何凤娟 . 深化城市轨道交通智能化综合管理研究 [J ] . 城市轨道交通研究 , 2014 , 17 ( 1 ): 74 - 77 .

CAO H , HE F J . Development of smart integrated information management in urban mass transit [J ] . Urban Mass Transit , 2014 , 17 ( 1 ): 74 - 77 .

CHIEN S , YANG Z . Optimal feeder bus routes on irregular street networks [J ] . Journal of Advanced Transportation , 2010 , 34 ( 2 ): 213 - 248 .

WU J Q , SONG R , XU W T , et al . Transit network optimization for feeder bus of BRT based on genetic algorithm [C ] // 2013 4th International Conference on Digital Manufacturing ＆ Automation,June 29-30,2013,Qingdao,China.Piscataway:IEEE Press , 2013

NEWELL G F . Some issues relating to the optimal design of bus routes [J ] . Transportation Science , 1979 , 13 ( 1 ): 20 - 35 .

GAO L , HU X , WANG W , et al . An optimal bus departure plan under the condition of partially overlapping routes [C ] // American Society of Civil Engineers 14th COTA International Conference of Transportation Professionals,July 4-7,2014,Changsha,China.[S.l.:s.n] . 2014 : 1153 - 1163 .

CEDER A . Methods for creating bus timetables [J ] . Transportation Research , 1987 , 21 ( 1 ): 59 - 83 .

CEDER A , GOLANY B , TAL O . Creating bus timetables with maximal synchronization [J ] . Transportation Research , 2001 , 35 ( 10 ): 913 - 928 .

CEDER A . Bus frequency determination using passenger count data [J ] . Transportation Research , 1984 , 18 ( 5-6 ): 439 - 453 .

CHEN Q , LI C . An approach to bus-driver scheduling problem [C ] // 2010 2nd WRI Global Congress on Intelligent Systems,December 16-17,2010,Wuhan,China.Piscataway:IEEE Press , 2010

KWAN R S K , WREN A , KWAN A S K . Hybrid genetic algorithms for scheduling bus and train drivers [C ] // The 2000 Congress on Evolutionary Computation,July 16-19,2000,La Jolla,USA.Piscataway:IEEE Press , 2000 .

KLIEWER N , MELLOULI T , SUHL L . A time–space network based exact optimization model for multi-depot bus scheduling [J ] . European Journal of Operational Research , 2006 , 175 ( 3 ): 1616 - 1 627.

BALL M , BODIN L , DIAL R . Matching based heuristic for scheduling mass transit crews and vehicles [J ] . Transportation Science , 1983 , 17 ( 1 ): 4 - 31 .

YU H , XIAO R , DU Y , et al . A busarrival time prediction model based on historical traffic patterns [C ] // The 2013 International Conference on Computer Sciences and Applications,December 14-15,2013,Wuhan,China . Piscataway:IEEE Press , 2013 .

YU B , YANG Z Z , ZENG Q C . Bus arrival time prediction model based on support vector machine and Kalman filter [J ] . China Journal of Highway and Transport , 2008 , 21 ( 2 ): 89 - 92 .

LIN Y , YANG X , ZOU N , et al . Real-time bus arrival time prediction:case study for Jinan,China [J ] . Journal of Transportation Engineering , 2013 , 139 ( 11 ): 1133 - 1140 .

PADMANABAN R P S , DIVAKAR K , VANAJAKSHI L , et al . Development of a real-time bus arrival prediction system for Indian traffic conditions [J ] . IET Intelligent Transport Systems , 2010 , 4 ( 3 ): 189 - 200 .

BERREBI S J , WATKINS K E , LAVAL J A . A real-time bus dispatching policy to minimize passenger wait on a high frequency route [J ] . Transportation Research Part B Methodological , 2015 , 81 ( Part 2 ): 377 - 389 .

SHEU J B . A fuzzy clustering approach to real-time demand-responsive bus dispatching control [J ] . Fuzzy Sets and Systems , 2005 , 150 ( 3 ): 437 - 455 .

王麟珠 , 苏庆列 , 郑日博 . 基于Elman动态神经网络的公交到站时间预测 [J ] . 机电技术 , 2012 , 35 ( 1 ): 135 - 137 .

WANG L Z , SU Q L , ZHENG R B . Bus arrival time prediction based on Elman dynamic neural network [J ] . Mechanical and Electrical Technology , 2012 , 35 ( 1 ): 135 - 137 .

张强 , 张艳艳 . 基于时间分段的公交车到站时间预测模型研究 [J ] . 数字技术与应用 , 2014 ( 11 ): 60 - 62 .

ZHANG Q , ZHANG Y Y . Study on prediction model of bus arrival time based on time segmentation [J ] . Digital Technology and Application , 2014 ( 11 ): 60 - 62 .

季彦婕 , 陆佳炜 , 陈晓实 , 等 . 基于粒子群小波神经网络的公交到站时间预测 [J ] . 交通运输系统工程与信息 , 2016 , 16 ( 3 ): 60 - 66 .

JI Y J , LU J W , CHEN X S , et al . Prediction model of bus arrival time based on particle swarm optimization and wavelet neural network [J ] . Journal of Transportation Systems Engineering and Information Technology , 2016 , 16 ( 3 ): 60 - 66 .

罗频捷 , 温荷 , 万里 . 基于遗传算法的模糊神经网络公交到站时间预测模型研究 [J ] . 计算机科学 , 2016 , 43 ( S1 ): 87 - 89 ,108.

LUO P J , WEN H , WAN L . Research on bus arrival time prediction model based on fuzzy neural network with genetic algorithm [J ] . Computer Science , 2016 , 43 ( S1 ): 87 - 89 ,108.

杨奕 , 张雯蕊 , 张灿 . 基于遗传算法的BP神经网络在公交车到站时间预测中的应用 [J ] . 现代商业 , 2017 ( 16 ): 38 - 40 .

YANG Y , ZHANG W R , ZHANG C . Application of BP neural network based on genetic algorithms in bus arrival time prediction [J ] . Modern Business , 2017 ( 16 ): 38 - 40 .

张昕 , 姜佳佳 , 刘进 . 基于SVM+GA的客运车辆到站时间预测 [J ] . 计算机与数字工程 , 2017 , 45 ( 6 ): 1062 - 1066 ,1085.

ZHANG X , JIANG J J , LIU J . Coach bus arrival time prediction based on SVM and GA [J ] . Computer and Digital Engineering , 2017 , 45 ( 6 ): 1062 - 1066 ,1085.

谢芳 , 顾军华 , 张素琪 , 等 . 基于MapReduce聚类和神经网络的公交车到站时间预测模型 [J ] . 计算机应用 , 2017 , 37 ( S1 ): 118 - 122 .

XIE F , GU J H , ZHANG S Q , et al . Predicting model of bus arrival time based on MapReduce clustering and neural network [J ] . Journal of Computer Applications , 2017 , 37 ( S1 ): 118 - 122 .

O’SULLIVAN A , PEREIRA F C , ZHAO J , et al . Uncertainty in bus arrival time predictions:treating heteroscedasticity with a metamodel approach [J ] . IEEE Transactions on Intelligent Transportation Systems , 2016 , 17 ( 11 ): 1 - 11 .

SINN M , YOON W J , CALABRESE F , et al . Predicting arrival times of buses using real-time GPS measurements [C ] // International IEEE Conference on Intelligent Transportation Systems,September 16-19,2012,Anchorage,USA.Piscataway:IEEE Press , 2012 .

ABIDIN A F , KOLBERG M . Towards improved vehicle arrival time prediction in public transportation:integrating SUMO and Kalman filter models [C ] // The 17th Uksim-amss International Conference on Modelling ＆ Simulation,March 25-27,2015,Cambridge,UK.Piscataway:IEEE Press , 2015 .

JEONG R , RILETT L R . Bus arrival time prediction using artificial neural network model [C ] // The 7th International IEEE Conference on Intelligent Transportation Systems,October 3-6,2004,Washington,USA.Piscataway:IEEE Press , 2004 .

MAITI S , PAL A , PAL A , et al . Historical data based real time prediction of vehicle arrival time [C ] // The 17th IEEE International Conference on Intelligent Transportation Systems,October 8-11,2014,Qingdao,China.Piscataway:IEEE Press , 2014 .

SCHAPIRE R E , SINGER Y . Improved boosting algorithms using confidencerated predictions [C ] // The 11th Annual Conference on Computational Learning Theory,July 24-26,1998,Madison,USA . New York:ACM Press , 1998 : 80 - 91 .

QUINLAN J R . Induction on decision tree [J ] . Machine Learning , 1986 , 1 ( 1 ): 81 - 106 .

JOACHIMS T , . Text categorization with support vector machines:learning with many relevant features [C ] // The 10th European Conference on Machine Learning,April 21–23,1998,Chemnitz,Germany . Heidelberg:Springer , 1998 : 137 - 142 .

浏览量

482

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据