计算机科学 ›› 2018, Vol. 45 ›› Issue (6A): 527-535.

• 综合、交叉与应用 • 上一篇    下一篇

公交网络中的乘客需求预测系统和方法

周春姐,张志旺,唐文静   

  1. 鲁东大学信息与电气工程学院 山东 烟台264000
  • 出版日期:2018-06-20 发布日期:2018-08-03
  • 作者简介:周春姐(1981-),女,博士,副教授,主要研究方向为物联网、数据挖掘,E-mail:lucyzcj@gmail.com;张志旺(1979-),男,博士,副教授,主要研究方向为数据挖掘与知识发现、机器学习、人工智能和自然语言处理;唐文静(1980-),女,博士,副教授,主要研究方向为数据融合、模式识别、图像分析与处理。
  • 基金资助:
    国家自然科学基金项目(61202111,61472141,61273152,61303017),山东省高等学校科技计划项目(J12LN05),山东省自然科学基金联合专项项目(ZR2013FL009),烟台市科技发展计划项目(2013ZH092,2014JH042),鲁东大学博士基金项目(LY2012023)资助

System and Methods of Passenger Demand Prediction on Bus Network

ZHOU Chun-jie,ZHANG Zhi-wang,TANG Wen-jing   

  1. Department of Information and Electrical Engineering,Ludong University,Yantai,Shandong 264000,China
  • Online:2018-06-20 Published:2018-08-03

摘要: 公共交通工具,尤其是公交车服务,可以减少私家车的使用和燃油消耗,缓解交通拥堵和环境污染状况。当乘坐公交车时,乘客不仅关心等车时间,更在乎公交车的拥挤程度,过度拥挤的公交车会导致乘客放弃乘坐。可见,准确、实时、可靠的乘客需求预测可以帮助公交公司决定合理的公交发车时间间隔,并且可以减少乘客的等车时间,这是人们急切需要的。基于实际公交系统的大量数据,提出一个面向移动用户的乘客需求预测系统。该系统包括服务器端的信息数据流处理和挖掘程序,以及客户端的移动应用程序。然而,公交网络中的乘客需求预测存在三大挑战:不均匀性、突发性和周期性。为了解决这些问题,提出了3种预测模型和1种基于滑动窗口的框架来预测乘客的数目。开发了一个原型系统,该系统可运行在多个版本的Android移动手机上,22个月的连续实验证明,该系统能够对公交网络中的864110项乘客需求进行精确预测,其准确度超过78%。

关键词: 乘客需求预测, 公交车服务, 交通拥堵, 预测模型

Abstract: Public transport,especially bus transport,can reduce the private car usage and fuel consumption,and alleviate the condition of traffic congestion and environmental pullution.However,when traveling with buses,the travelers not only care about the waiting time,but also care about the crowdedness in the bus.Excessively overcrowded buses may drive away many travelers and make them reluctant to take buses.So accurate,real-time and reliable passenger demand prediction becomes necessary,which can help determine the bus headway and reduce the waiting time of passengers.However,there are three major challenges for predicting the passenger demand on bus services:inhomogeneous,seaso-nal bursty periods and periodicities.To overcome the challenges,this paper proposed three predictive models and further took a data stream ensemble framework to predict the number of passengers.This paper developed an experiment over a 22-weekperiod.The evaluation results suggest that the proposed method achieves outstanding prediction accuracy among 86411 passenger demands on bus services,more than 78% of them are accurately forecasted.

Key words: Bus transport, Passenger demand prediction, Predictive models, Traffic congestion

中图分类号: 

  • TP391
[1]DAGANZO C F.A Headway-based Approach to Eliminate Bus Bunching:Systematic Analysis and Comparisons[J].Transportation Research Part B Methodological,2009,43(10):913-921.
[2]YAN S Y,CHI C J,TANG C H.Inter-city Bus Routing and Timetable Setting under Stochastic Demands[J].Transportation Research Part A Policy & Practice,2006,40(7):572-586.
[3]CHANG H,PARK D,LEE S,et al.Dynamic Multi-interval Bus Travel Time Prediction using Bus Transit Data[J].Transportmetrica,2010,6(1):19-38.
[4]YU B,LAM W,TAM M L.Bus Arrival Time Prediction at Bus Stop with Multiple Routes[J].Transportation Research Part C Emerging Technology,2011,19(6):1157-1170.
[5]DORNBUSH S,JOSHI A.StreetSmart Traffic:Discovering and Disseminating Automobile Congestion Using VANET’s[C]∥Proceedings of the 65th Vehicular Technology Conference,VTC2007-Spring.IEEE,2007:11-15.
[6]SCHUNEMANN B,WEDEL J,RADUSCH I.V2X-Based Traffic Congestion Recognition and Avoidance[J].Tamkang Journal of Science and Engineering,2010,13(1):63-70.
[7]LAKAS A,CHAQFEH M.A Novel Method for Reducing Road Traffic Congestion using Vehicular Communication[C]∥Proceedings of the 6th International Wireless Communications and Mobile Computing Conference.IWCMC,ACM,2010:16-20.
[8]FERREIRA M,FERNANDES R,CONCEICAO H,et al.Self-organized Traffic Control[C]∥Proceedings of the Annual International Conference on Mobile Computing and Networking.MOBICOM,ACM,2010:85-90.
[9]HOLT C.Forecasting Seasonals and Trends by Exponentially Weighted Moving Averages[J].International Journal of Forecasting,2004,20(1):5-10.
[10]MAKRIDAKIS S,HIBON M.The M3-Competition:Results, Conclusions and Implications[J].International Journal of Forecasting,2000,16(4):451-476.
[11]ZHOU C,MENG X,CHEN Y.Out-of-order Durable Event Pro- cessing in Integrated Wireless Networks[J].Pervasive and Mobile Computing,2011,7(5):595-610.
[12]CHANG H,TAI Y,CHEN H,et al.iTaxi:Context-Aware Taxi Demand Hotspots Prediction Using Ontology and Data Mining Approaches[C]∥Proceedings of the 13th Conference on Artificial Intelligence and Applications (TAAI).2008.
[1] 颜锐, 梁智勇, 李锦涛, 任菲.
基于深度学习和H&E染色病理图像的肿瘤相关指标预测研究综述
Predicting Tumor-related Indicators Based on Deep Learning and H&E Stained Pathological Images:A Survey
计算机科学, 2022, 49(2): 69-82. https://doi.org/10.11896/jsjkx.210900140
[2] 陈慧琴, 郭贯成, 秦朝轩, 李兆碧.
基于GM-LSTM模型的南京市老年人口预测研究
Research on Elderly Population Prediction Based on GM-LSTM Model in Nanjing City
计算机科学, 2021, 48(6A): 231-234. https://doi.org/10.11896/jsjkx.200900142
[3] 王博宇, 王中卿, 周国栋.
基于回复生成的对话意图预测
Dialogue Act Prediction Based on Response Generation
计算机科学, 2021, 48(2): 212-216. https://doi.org/10.11896/jsjkx.200700137
[4] 黄寿孟.
一种基于监督学习的异构网链路预测模型
Heterogeneous Network Link Prediction Model Based on Supervised Learning
计算机科学, 2021, 48(11A): 111-116. https://doi.org/10.11896/jsjkx.210300030
[5] 李吟, 李必信.
基于脚本预测和重组的内存泄漏测试加速技术
Memory Leak Test Acceleration Based on Script Prediction and Reconstruction
计算机科学, 2020, 47(9): 31-39. https://doi.org/10.11896/jsjkx.200100075
[6] 熊亭, 戚湧, 张伟斌.
基于DCGRU-RF模型的路网短时交通流预测
Short-term Traffic Flow Prediction Based on DCGRU-RF Model for Road Network
计算机科学, 2020, 47(5): 84-89. https://doi.org/10.11896/jsjkx.190100213
[7] 周杰, 罗云芳, 雷耀建, 李文敬, 封宇.
基于时空优化的多尺度卷积神经网络空气质量预测模型
Multi-scale Convolutional Neural Network Air Quality Prediction Model Based on Spatio-Temporal Optimization
计算机科学, 2020, 47(11A): 535-540. https://doi.org/10.11896/jsjkx.200700164
[8] 徐丽丽, 李洪, 李劲.
基于灰色预测和径向基网络的人口预测研究
Research on Population Prediction Based on Grey Prediction and Radial Basis Function Network
计算机科学, 2019, 46(6A): 431-435.
[9] 吴发友, 王林峰, 翁其能.
灰色预测模型在隧道洞顶楔形体稳定性预测中的应用
Application of Grey Prediction Model in Prediction of Stability of Wedge-shaped Body of Tunnel
计算机科学, 2019, 46(5): 327-330. https://doi.org/10.11896/j.issn.1002-137X.2019.05.051
[10] 徐方, 邓敏, 熊曾刚, 叶从欢, 徐宁.
移动社会网络中基于多维上下文匹配的数据转发算法
Data Forwarding Algorithm Based on Multidimensional Context Matching in Mobile Social Networks
计算机科学, 2019, 46(2): 81-87. https://doi.org/10.11896/j.issn.1002-137X.2019.02.013
[11] 王利君, 支志英, 贾鹿, 李伟.
基于SCRF的抽油井结蜡预测方法优化研究
Study on Optimized Method for Predicting Paraffin Deposition of Pumping Wells Based on SCRF
计算机科学, 2019, 46(11A): 599-603.
[12] 邢一鸣, 班晓娟, 刘旭, 尹航, 沈晴.
基于核超限学习机群组算法的交通拥堵预测
Traffic Congestion Prediction Based on Kernel Extreme Learning Machine Group Algorithm
计算机科学, 2019, 46(11): 241-246. https://doi.org/10.11896/jsjkx.191100507C
[13] 史小婉, 马于涛.
一种基于文本分类和评分机制的软件缺陷分配方法
Software Bug Triaging Method Based on Text Classification and Developer Rating
计算机科学, 2018, 45(11): 193-198. https://doi.org/10.11896/j.issn.1002-137X.2018.11.030
[14] 温润,谭丽.
结合HS算法与ESN算法的光伏发电短期出力预测
Short-term Power Forecasting for Photovoltaic Generation Based on HS-ESN
计算机科学, 2017, 44(6): 226-231. https://doi.org/10.11896/j.issn.1002-137X.2017.06.038
[15] 杨冬菊,邓崇彬.
基于ARIMA模型的虚拟资源动态调度方法
Dynamic Scheduling Method of Virtual Resources Based on ARIMA Model
计算机科学, 2017, 44(10): 14-18. https://doi.org/10.11896/j.issn.1002-137X.2017.10.003
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!