大数据背景下基于5S的城市交通拥堵评价模型研究

doi:10.12005/orms.2018.0018

摘要/Abstract

摘要： 近几年来,城市交通拥堵问题日益突出,极大制约了城市发展。在大数据背景下,为了准确掌握交通实时拥堵状况,改善城市交通,便利市民出行,本文深入挖掘城市交通拥堵的影响因素,构建了基于交通5S要素的城市拥堵理论模型,运用径向基函数神经网络方法工具,以上海静安寺、上海站、陆家嘴周围三大拥堵路段的交通数据集为例,验证了该模型的有效性。实验结果表明,由该模型获得的城市交通拥堵预测值与上海实际交通路况具有较好的拟合效果,表明交通5S模型与方法能够准确有效地评价城市交通拥堵。

关键词: 城市交通拥堵, 评价模型, 深度挖掘, 5S理论

Abstract: In recent years, the urban traffic congestion problem is more and more serious so that it greatly restricts the city development. In the background of big data, in order to accurately predict the real-time status of urban traffic congestion and improve urban traffic conditions to make public travel convenient, this paper makes a study of factors of urban traffic congestions. Then we build a urban traffic congestion evaluation model based on the theory of 5S. Lastly, we use a radial basis function neural network to verify the model with traffic data set of Jingan Temple, Shanghai Station, and Lujiazui in Shanghai. The result indicates that the predictive value obtained by the urban traffic congestion evaluation model has a good fitting effect on the Shanghai real road traffic. It shows that the model can accurately evaluate urban traffic congestion effectively.

Key words: urban traffic congestion, evaluation model, deep mining, 5S theory

中图分类号:

C931.1

熊励, 杨淑芬, 张芸. 大数据背景下基于5S的城市交通拥堵评价模型研究[J]. 运筹与管理, 2018, 27(1): 117-124.

XIONG Li, YANG Shu-fen, ZHANG Yun. Research on the Urban Traffic Congestion Evaluation Model Based on 5S Theory[J]. Operations Research and Management Science, 2018, 27(1): 117-124.

参考文献

[1] 刘治彦,岳晓燕,赵睿.我国城市交通拥堵成因与治理对策[J].城市发展研究,2011,18(11):90-96.
[2] 百度.我的2014年上班路[EB/OL]. http://baijia.baidu.com/static/workway/distance/index.php.
[3] Roy S, Sen R, Kulkarni S, et al.. Wireless across road: RF based road traffic congestion detection[C]//Communication Systems and Networks (COMSNETS), 2011 Third International Conference on. IEEE, 2011: 1-6.
[4] Bauza R, Gozálvez J. Traffic congestion detection in large-scale scenarios using vehicle-to-vehicle communications[J]. Journal of Network and Computer Applications, 2013, 36(5): 1295-1307.
[5] 曾鹦,李军.合作博弈视角下城市道路交通拥堵收费研究[J].运筹与管理,2013,(1):9-14.
[6] 李春英,汤志康,曹元大.多分类器组合的交通拥堵预测模型研究[J].计算机工程与设计,2010,(23):5088-5091.
[7] Sun Daniel, Liu Xiaofeng, Ni Anning et al.. Traffic congestion evaluation method for urban arterials[J]. Transportation Research Record: Journal of the Transportation Research Board, 2014, 2461(1): 9-15.
[8] 李树彬,吴建军,高自友,等.基于复杂网络的交通拥堵与传播动力学分析[J].物理学报,2011,60(5):50701-050701.
[9] 牛灵芝, 温惠英. 城市道路拥堵与道路平均速度相关性分析[J].交通信息与安全,2014,32(6).
[10] 吴佩莉,刘奎恩,郝身刚,等.基于浮动车数据的快速交通拥堵监控[J].计算机研究与发展,2015,51(1):189-198.
[11] Kersys Arturas. Sustainable urban transport system development reducing traffic congestions costs[J]. Engineering Economics, 2011, 22(1): 5-13.
[12] 王曦,祝付玲.基于高斯混合分布的交通拥堵评价模型[J].公路交通科技,2011,28(2):127-132.
[13] 杨柳青,宗刚,柳应华.基于复杂网络的路网交通拥堵评估仿真模型[J].计算机应用研究,2014,31(3):796-800.
[14] 邬贺铨.关于大数据的若干思考[J].中国信息化,2014,(9):3-7.
[15] 胡宇舟,范滨,顾学道,等.基于Storm的云计算在自动清分系统中的实时数据处理应用[J].计算机应用,2014,34(A01):96-99.
[16] 代亮,陈婷,许宏科,等.大数据测试技术研究[J].计算机应用研究,2014,31(6):1606-1611.
[17] Zheng Y, Chen Y, Li Q, et al. Understanding transportation modes based on GPS data for web applications[J]. ACM Transactions on the Web(TWEB), 2010, 4(1): 1.
[18] Yoon B, Chang H. Potentialities of data-driven nonparametric regression in urban signalized traffic flow forecasting[J]. Journal of Transportation Engineering, 2014, 140(7).
[19] Shi Q, Abdel-Aty M. Big Data applications in real-time traffic operation and safety monitoring and improvement on urban expressways[J]. Transportation Research Part C: Emerging Technologies, 2015.
[20] 覃雄派,王会举,杜小勇,等.大数据分析-RDBMS与MapReduce的竞争与共生[J].软件学报,2012,23(1).
[21] Edward A. Fox. The 5S framework for digital libraries and two case studies: NDLTD and CSTC[C]. NIT '99:international conference on new information technology No11, 1999. 115-125.
[22] Marcos André Gonéalves, Edward A. Fox, Layne T. Watson,etc. streams, structures, spaces, scenarios, societies(5S): a formal model for digital libraries[J]. ACM Transactions on Information Systems, 2004, 22(2): 270-312.
[23] Marcos André Gonéalves, Moreira B L, Fox E A, et al. “What is a good digital library?”-a quality model for digital libraries[J]. Information processing & management, 2007, 43(5): 1416-1437.
[24] 徐大芳,王亚军.数字图书馆5S模型的构成与应用[J].情报科学,2008,(6):872-875.
[25] 张文萍,邓仲华,黎春兰.基于5S模型的数字图书馆本体模型研究[J].图书馆杂志,2013,32(7):57-62.
[26] 胡翠红.基于5S理论的数字图书馆资源整合研究[J].现代情报,2011,31(1):44-46.
[27] 熊励,薛珊,张芸.大数据环境下基于5S理论的城市智能交通用户行为模型研究[C].管理科学与工程学会2013年年会暨第十一届中国管理科学与工程论坛,2013.256-259.
[28] Li Xiong, Yun Zhang, Bing Fang, etc. Research on recommendation model of multi-source information of urban intelligent transportation based on 5S theory in cloud computing[J]. International Journal of Advances in Management Science, 2014, 3(1): 44-49.
[29] 孙启鹏,王庆云.我国综合交通结构问题的战略思考[J].综合运输,2010,(2):4-7.
[30] 闫冬梅,向红艳,邵毅明.城市轨道交通换乘站运行效率评价[J].重庆交通大学学报 (自然科学版),2013,32(1):99-102.
[31] 柴彦威,申悦,塔娜.基于时空间行为研究的智慧出行应用[J].城市规划,2014,(3):83-89.
[32] 杨敏,杨应翔,陈健,王炜.基于多智能体交互作用的活动-出行时空分布特性仿真[J].北京工业大学学报,2012,38(10):1531-1535.
[33] Moody J, Darken C. Leaming with localized receptive fields inproc 1998 connection is models summer school. D Touretzky.G Hinton. And T Scjnowski(Eds)[M]. Camegie Mellon University, Morgan Kaufmann Publishers. 1988.
[34] 高德交通,http://trp.autonavi.com/traffic/.
[35] 赵鹏军,李铠.大数据方法对于缓解城市交通拥堵的作用的理论分析[J].现代城市研究, 2014 (10): 25-30.
[36] 王静波,王竞涛.基于波动方程的动态交通流网络模型研究[J].计算机仿真,2012,(1):314-317.
[37] 张晓亮,赵淑芝,刘华胜,高祥涛.高峰时段公交客流分配的Logit模型改进[J].吉林大学学报 (工学版),2014,6:013.
[38] Cesar A Quiroga. Performance measures and data requirements for congestion management systems[J]. Transportation Research Part C: Emerging Technologies, 2000, 8(1): 287-306.
[39] Robert R, Theodore F. Contrasting the use of time-based and distance-based measures to quantify traffic congestion levels: an analysis of new jersey counties[C]. The 81th Annual Meetings of the Transportation Research Board, Washington, DC. 2002.
[40] Daniela Bremmer, Keith Cotton, Dan Cotey, Charles Prestrud, Gary Westby. measuring congestion: learning from operational data[J]. Transportation Research Record: Journal of the Transportation Research Board, 2004, 1895(1): 188-196.
[41] Ma Zhen-Liang, Ferreira Luis, Mesbah Mahmoud. Hojati ahmad tavassoli. modelling bus travel yime reliability using supply and demand data from automatic vehicle location and smart card systems[C]. Transportation Research Board 94th Annual Meeting. 2015(15-0402).
[42] http://spotshot.baidu.com/.
[43] http://www.jtcx.sh.cn/