[1]李林波,高天爽,姜屿.基于生存分析的夜间驻留停车需求预测[J].东南大学学报(自然科学版),2020,50(1):192-199.[doi:10.3969/j.issn.1001-0505.2020.01.025]
 Li Linbo,Gao Tianshuang,Jiang Yu.Night parking demand forecasting based on survival analysis[J].Journal of Southeast University (Natural Science Edition),2020,50(1):192-199.[doi:10.3969/j.issn.1001-0505.2020.01.025]
点击复制

基于生存分析的夜间驻留停车需求预测()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
50
期数:
2020年第1期
页码:
192-199
栏目:
交通运输工程
出版日期:
2020-01-13

文章信息/Info

Title:
Night parking demand forecasting based on survival analysis
作者:
李林波1高天爽1姜屿2
1同济大学道路与交通工程教育部重点实验室, 上海201804; 2北京市城市规划设计研究院, 北京100045
Author(s):
Li Linbo1 Gao Tianshuang1 Jiang Yu2
1Key Laboratory of Road and Traffic Engineering of Ministry of Education, Tongji University, Shanghai 201804, China
2Beijing Municipal Institute of City Planning and Design, Beijing 100045, China
关键词:
夜间停车 停车需求预测 生存分析 精细化停车管理
Keywords:
night parking parking demand forecasting survival analysis delicacy parking management
分类号:
U491.1
DOI:
10.3969/j.issn.1001-0505.2020.01.025
摘要:
为了在微观层面对夜间停车需求进行准确预测,采用生存分析的方法建立夜间停车需求预测模型.首先将夜间停放的车辆定义为日间驶入车辆的驻留部分,对应的夜间停车需求预测转换为日间驶入车辆驻留的概率预测;进一步从日间驶入车辆的停车时长分布入手,用生存分析方法估计车辆停放不同时长的概率,从而预测夜间驻留的停车需求.最后用上海某科技园实际停车数据进行分析验证,构建Cox比例风险模型,获得不同影响因素下的生存时间曲线以及过夜驻留停车概率.结果表明,车辆夜间驻留的概率与工作日、驶入天气、用户类型以及驶入时刻等变量有关,全天夜间驻留预测精度达92.1%.利用生存分析方法预测夜间停车需求是有效的,能够为停车场的夜间需求管理提供决策依据.
Abstract:
To accurately forecast the demands for night parking at the micro-level, a forecasting model for night parking demands was established by using a survival analysis method. First, the vehicle parked at night was defined as the resident part of the daytime driving vehicle, and the corresponding night parking demand forecast was converted into the resident probability prediction of the daytime driving vehicle. Furthermore, starting with the parking time distribution of the vehicle driving in the daytime, the probability of different parking time was estimated by the survival analysis method, so as to forecast the parking demands of vehicles staying at night. Finally, the actual parking data from a science and technology park in Shanghai were used to validate the forecasting method. The Cox proportional risk model was constructed to obtain the survival time curve and the overnight parking probability under different conditions. The results show that the probability of vehicle staying at night is related to variables, such as weekday, driving weather, user type, and driving time. The forecast accuracy of night parking is 92.1%. It is effective to forecast night parking demands by the survival analysis method, providing the decision-making basis for the night demand management of parking lots.

参考文献/References:

[1] 陈峻, 王炜, 晏克非. 城市停车设施需求预测研究[J]. 东南大学学报, 1999, 29(S1): 121-126.
  Chen J, Wang W, Yan K F. Forecasting research of urban parking facilities’ demand[J]. Journal of Southeast University, 1999, 29(S1): 121-126.(in Chinese)
[2] Eldin M S N, El-Reedy T Y, Ismail H K. Combined parking and traffic assignment model[J]. Traffic Engineering & Control, 1981, 22(10): 524-530.
[3] Kawakami S,Takayama H, Liu Z K. A study on parking place choice and parking demand forecast by traffic assignment models[J]. IFAC Proceedings Volumes, 1994, 27(12): 943-948. DOI:10.1016/s1474-6670(17)47595-1.
[4] Tong C O, Wong S C, Lau W W T. A demand-supply equilibrium model for parking services in Hong Kong[J]. HKIE Transactions, 2004, 11(1): 48-53. DOI:10.1080/1023697x.2004.10667943.
[5] 关宏志, 王鑫, 王雪. 停车需求预测方法研究[J]. 北京工业大学学报, 2006, 32(7): 600-604. DOI:10.3969/j.issn.0254-0037.2006.07.006.
Guan H Z, Wang X, Wang X. The research on forecasting method for parking demanding[J]. Journal of Beijing University of Technology, 2006, 32(7): 600-604. DOI:10.3969/j.issn.0254-0037.2006.07.006. (in Chinese)
[6] 吴家友, 刘术红. 基于区位分析和诱增流量的停车需求预测模型研究[J]. 重庆交通学院学报, 2004, 23(3): 104-106, 114. DOI:10.3969/j.issn.1674-0696.2004.03.027.
Wu J Y, Liu S H. Parking demand forecasting model research based on location analysis and induced traffic[J]. Journal of Chongqing Jiaotong University, 2004, 23(3): 104-106, 114. DOI:10.3969/j.issn.1674-0696.2004.03.027. (in Chinese)
[7] 白玉, 薛昆, 杨晓光. 基于路网容量的停车需求预测方法[J]. 交通运输工程学报, 2004, 4(4): 49-52. DOI:10.3321/j.issn:1671-1637.2004.04.013.
Bai Y, Xue K, Yang X G. Forecasting method of parking-demand based on capacity-of-network[J]. Journal of Traffic and Transportation Engineering, 2004, 4(4): 49-52. DOI:10.3321/j.issn:1671-1637.2004.04.013. (in Chinese)
[8] Dunning A E. Method and system for projecting dynamic parking availability based on an ongoing survey for remote lots with high demand: US, 7049979[P].2006-05-23.
[9] Yu F Q, Guo J H, Zhu X B, et al. Real time prediction of unoccupied parking space using time series model[C]// 3rd International Conference on Transportation Information and Safety(ICTIS 2015). Wuhan, China, 2015: 370-374.
[10] 刘志广. 城市中心区典型商场配建停车泊位共享时间窗口研究[D]. 南京: 东南大学, 2016.
  Liu Z G. Research on shared time window of parking spaces at typical malls in downtown[D]. Nanjing: Southeast University, 2016.(in Chinese)
[11] 张雷. 基于时间序列模型的停车场泊位特性预测研究[J]. 南京师大学报(自然科学版), 2017, 40(2): 24-30. DOI:10.3969/j.issn.1001-4616.2017.02.005.
Zhang L. Research on parking berth characteristics prediction based on time series model[J]. Journal of Nanjing Normal University(Natural Science Edition), 2017, 40(2): 24-30. DOI:10.3969/j.issn.1001-4616.2017.02.005. (in Chinese)
[12] Rajabioun T, Ioannou P A. On-street and off-street parking availability prediction using multivariate spatiotemporal models[J]. IEEE Transactions on Intelligent Transportation Systems, 2015, 16(5): 2913-2924. DOI: 10.1109/TITS.2015.2428705.
[13] 许增昭. 基于泊位诱导及短时预测的智能停车管理系统研究[D]. 广州: 华南理工大学, 2010.
  Xu Z Z. Research on intelligent parking management system based on parking space guidance and short-term prediction[D]. Guangzhou: South China University of Technology, 2010.(in Chinese)
[14] 唐克双, 郝兆康, 衣谢博闻, 等. 停车场泊位占有率预测方法评价[J]. 同济大学学报(自然科学版), 2017, 45(4): 533-543. DOI:10.11908/j.issn.0253-374x.2017.04.011.
Tang K S, Hao Z K, Yixie B W, et al. Evaluation of prediction methods for parking occupancy rate[J]. Journal of Tongji University(Natural Science), 2017, 45(4): 533-543. DOI:10.11908/j.issn.0253-374x.2017.04.011. (in Chinese)
[15] Okutani I, Stephanedes Y J. Dynamic prediction of traffic volume through Kalman filtering theory[J]. Transportation Research Part B: Methodological, 1984, 18(1): 1-11. DOI:10.1016/0191-2615(84)90002-X.
[16] Ji H F, Xu A G, Sui X, et al. The applied research of Kalman in the dynamic travel time prediction[C]//18th International Conference on Geoinformatics. Beijing, China, 2010:18-20. DOI: 10.1109/GEOINFORMATICS.2010.5567722.
[17] Sun Y, Liu C P, Wang Y H, et al. A forecasting model for parking guidance system[C]// 2009 WRI World Congress on Computer Science & Information Engineering. Los Angeles, CA, USA, 2009: 607-611. DOI: 10.1109/CSIE.2009.1088.
[18] Vlahogianni E I, Kepaptsoglou K, Tsetsos V, et al. A real-time parking prediction system for smart cities[J]. Journal of Intelligent Transportation Systems, 2016, 20(2):192-204. DOI: 10.1080/15472450.2015.1037955.
[19] Tamrazian A, Qian Z, Rajagopal R. Where is my parking spot? Online and offline prediction of time-varying parking occupancy[J]. Transportation Research Board Annual Meeting, 2015(2489): 77-85.
[20] Ji Y J, Wang W, Deng W. Available parking space occupancy change characteristics and short-term forecasting model[J]. Journal of Southeast University(English Edition), 2007, 23(4): 604-608.
[21] 何洪波, 韩印, 姚佼. 基于混沌和BP神经网络的有效停车泊位预测[J]. 交通与运输(学术版), 2012(1): 24-28.
  He H B, Han Y, Yao J. The prediction of effective parking space based on chaos and BP neural network[J]. Traffic & Transportation, 2012(1): 24-28.(in Chinese)
[22] 季彦婕, 陈晓实, 王炜, 等. 基于小波变换和粒子群小波神经网络组合模型的有效停车泊位短时预测[J]. 吉林大学学报(工学版), 2016, 46(2): 399-405. DOI:10.13229/j.cnki.jdxbgxb201602010.
Ji Y J, Chen X S, Wang W, et al. Short-term forecasting of parking space using particle swarm optimization-wavelet neural network model[J]. Journal of Jilin University(Engineering and Technology Edition), 2016, 46(2): 399-405. DOI:10.13229/j.cnki.jdxbgxb201602010. (in Chinese)
[23] 李田田, 杨有, 余平, 等. 优化小波神经网络停车泊位多步预测[J]. 重庆师范大学学报(自然科学版), 2018, 35(5): 107-114. DOI:10.11721/cqnuj20180515.
Li T T, Yang Y, Yu P, et al. Multi-step parking prediction based on improved wavelet network[J]. Journal of Chongqing Normal University(Natural Science Edition), 2018, 35(5): 107-114. DOI:10.11721/cqnuj20180515. (in Chinese)
[24] Ji Y J, Tang D N, Blythe P, et al. Short-term forecasting of available parking space using wavelet neural network model[J]. IET Intelligent Transport Systems, 2015, 9(2):202-209. DOI:10.1049/iet-its.2013.0184.
[25] 彭非, 王伟. 生存分析[M]. 北京:人民大学出版社, 2004:3-24.
[26] Bagloee S A, Asadi M. Crash analysis at intersections in the CBD: A survival analysis model[J]. Transportation Research Part A: Policy and Practice, 2016, 94: 558-572. DOI:10.1016/j.tra.2016.10.019.
[27] 何莉, 徐学才. 信号交叉口行人受伤严重程度生存分析[J]. 公路, 2018, 63(6): 211-215.
  He L, Xu X C.Survival analysis of pedestrian injury severity at signalized intersection [J]. Highway, 2018, 63(6): 211-215.(in Chinese)
[28] 陈建军, 夏正丰. 基于生存分析的交通事故持续时间预测模型[J]. 公路与汽运, 2014(6): 68-72. DOI:10.3969/j.issn.1671-2668.2014.06.019.
Chen J J, Xia Z F. Prediction model of traffic accident duration based on survival analysis [J]. Highways & Automotive Applications, 2014(6): 68-72. DOI:10.3969/j.issn.1671-2668.2014.06.019. (in Chinese)
[29] 杨文臣, 张轮, 施奕骋, 等. 城市快速路交通事件持续时间生存分析[J]. 交通运输系统工程与信息, 2014, 14(5): 168-174. DOI:10.3969/j.issn.1009-6744.2014.05.025.
Yang W C, Zhang L, Shi Y C, et al. Survival analysis of traffic incident duration for urban expressways[J]. Journal of Transportation Systems Engineering and Information Technology, 2014, 14(5): 168-174. DOI:10.3969/j.issn.1009-6744.2014.05.025. (in Chinese)
[30] Li R M. Traffic incident duration analysis and prediction models based on the survival analysis approach[J].IET Intelligent Transport Systems, 2015, 9(4): 351-358. DOI:10.1049/iet-its.2014.0036.
[31] Zhao F C,Guo H W, Wang W H, et al. Modeling lateral interferences between motor vehicles and non-motor vehicles: A survival analysis based approach[J]. Transportation Research Part F: Traffic Psychology and Behaviour, 2015, 42(S1): 447-455. DOI:10.1016/j.trf.2015.07.005.
[32] Tiwari G, Bangdiwala S, Saraswat A, et al. Survival analysis: Pedestrian risk exposure at signalized intersections[J]. Transportation Research Part F: Traffic Psychology and Behaviour, 2007, 10(2): 77-89. DOI:10.1016/j.trf.2006.06.002.

备注/Memo

备注/Memo:
收稿日期: 2019-05-16.
作者简介: 李林波(1974—),男,博士,副教授,博士生导师,llinbo@tongji.edu.cn.
基金项目: 上海市科学规划一般课题资助项目(2017BGL029).
引用本文: 李林波,高天爽,姜屿.基于生存分析的夜间驻留停车需求预测[J].东南大学学报(自然科学版),2020,50(1):192-199. DOI:10.3969/j.issn.1001-0505.2020.01.025.
更新日期/Last Update: 2020-01-20