基于Gamma混合模型的出租车落客行为

doi:10.3785/j.issn.1008-973X.2024.03.016

浙江大学学报(工学版)

2024, Vol. 58

Issue (3): 589-598 DOI: 10.3785/j.issn.1008-973X.2024.03.016

土木工程、交通工程

基于Gamma混合模型的出租车落客行为

杨方宜1,2,3(

),杨荣根1,李伟兵2,何向东3

1. 金陵科技学院智能科学与控制工程学院，江苏南京 211169
2. 南京理工大学机械工程学院，江苏南京 210094
3. 浙江好易点智能科技有限公司，浙江金华 321042

Taxi drop-off behavior based on Gamma hybrid model

Fangyi YANG1,2,3(

),Ronggen YANG1,Weibing LI2,Xiangdong HE3

1. College of Intelligent Science and Control Engineering, Jinling Institute of Technology, Nanjing 211169, China
2. School of Mechanical Engineering, Nanjing University of Science and Technology, Nanjing 210094, China
3. Zhejiang Hooeasy Intelligent Technology Co. Ltd, Jinhua 321042, China

全文: PDF(1169 KB) HTML

摘要：

为了更好地理解枢纽送站坪出租车落客行为，提高落客区域通行效率，提出基于Gamma混合模型的出租车落客决策模型. 应用精确的出租车轨迹数据，将出租车停车时间分解为主动停车时间、被迫停车时间和落客时间，基于被迫停车时间分析构建等待耐性混合分布模型，模型验证结果与真实数据相吻合. 在此基础上，以潜在乘客耐心分布、停车位置、期望停车位和行程时间为落客决策模型的核心指标，提取相关因子为解释变量，以是否落客为被解释变量，构建二元面板Logit模型，并对模型进行检验. 结果表明，乘客耐心对车辆落客起着决定性的作用，落客决策模型预测准确率超过81%，表明该模型能够较好地预测出租车落客行为，为研究缓堵策略提供基础.

关键词： 客运枢纽; 落客区域; Gamma混合模型; 落客决策; 面板数据模型

Abstract:

A taxi drop-off decision model was proposed based on the Gamma hybrid model, in order to better understand the taxi drop-off behavior and improve the drop-off area’s traffic efficiency. The accurate taxi trajectory data was used, and the taxi stopping time was decomposed into active stopping time, forced stopping time, and drop-off time. A mixed distribution model of waiting tolerance was established based on the analysis of forced stopping time. The verification results of the model were consistent with the actual data. On this basis, the potential passenger patience distribution, parking location, expected parking space, and travel time were taken as the core indicators of the drop-off decision model. Then, relevant factors were extracted as explanatory variables, with drop-off or not as explained variables. Finally, a binary panel Logit model was constructed and tested. Results show that passenger patience plays a decisive role in vehicle drop-off. The prediction accuracy of the drop-off decision model is more than 81%, which indicates that the model can well predict taxi drop-off behavior and provides a research basis for the further research on congestion reduction strategy.

Key words: passenger terminal passenger drop-off area Gamma hybrid model drop-off decision panel data model

收稿日期: 2023-04-04 出版日期: 2024-03-05

CLC:

U 491.1

基金资助: 江苏省高等学校自然科学基金资助项目（22KJD580003）；金陵科技学院博士科研启动基金资助项目（jit-b-202113）；金陵科技学院科研基金孵化资助项目（jit-fhxm-202105）.

作者简介: 杨方宜（1988—），男，讲师，博士，从事交通流研究. orcid.org/0000-0003-4792-8570. E-mail：yangfy@jit.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
	杨方宜
	杨荣根
	李伟兵
	何向东

引用本文:

杨方宜,杨荣根,李伟兵,何向东. 基于Gamma混合模型的出租车落客行为[J]. 浙江大学学报(工学版), 2024, 58(3): 589-598.

Fangyi YANG,Ronggen YANG,Weibing LI,Xiangdong HE. Taxi drop-off behavior based on Gamma hybrid model. Journal of ZheJiang University (Engineering Science), 2024, 58(3): 589-598.

链接本文:

https://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2024.03.016 或 https://www.zjujournals.com/eng/CN/Y2024/V58/I3/589

图 1 FIFO落客车道跟随车辆状态变化图

图 2 FIFO落客车道头车和跟随车辆停车时间划分

表 1 车辆等待耐性最优混合分布参数（时间段1）

表 2 车辆等待耐性最优混合分布参数（时间段2）

图 3 区域1第1次受迫停车出租车等待时长直方图及车辆等待耐性概率密度曲线

图 4 区域1第1次受迫停车出租车等待时长累积分布曲线

表 3 受迫停车落客决策模型估计结果

图 5 受迫停车落客决策模型ROC曲线（时间段1）

表 4 落客决策模型ROC结果（时间段1）

图 6 受迫停车落客决策模型ROC曲线（时间段2）

表 5 落客决策模型ROC结果（时间段2）

1	YANG F, GU W, CASSIDY M, et al Achieving higher taxi outflows from a drop-off lane: a simulation-based study[J]. Transportation Research Part C: Emerging Technologies, 2020, 115: 102623 doi: 10.1016/j.trc.2020.102623
2	CHEN Y, ZHANG N, WU H, et al. Calculation method of traffic capacity in airport curbside [C]// Proceedings of the 7th International Conference on Green Intelligent Transportation System and Safety . Singapore:Springer, 2018: 725−736.
3	刘淑敏, 孙莹莹枢纽型机场陆侧交通系统后评价及优化研究: 以南京禄口国际机场为例[J]. 交通与运输:学术版, 2018, (1): 42- 45 LIU Shumin, SUN Yingying Study on post-evaluation and optimization of landside traffic system for airport: take Nanjing Lukou international airport as an example[J]. Traffic and Transportation, 2018, (1): 42- 45
4	CHANG K Y. A simulation model for analyzing airport terminal roadway and traffic and curbside parking [D]. Colloge Park: University of Maryland, 2001.
5	赵林, 姜恒, 袁倩倩深圳机场T3航站楼车道边规模分析[J]. 交通标准化, 2010, (212): 205- 207 ZHAO Lin, JIANG Heng, YUAN Qianqian Scale analysis for curbside at T3 airport terminal of Shenzhen[J]. Transport Standardization, 2010, (212): 205- 207
6	柳伍生, 周和平机场陆侧出发层车道边通行能力分析[J]. 交通科学与工程, 2010, 26 (2): 98- 102 LIU Wusheng, ZHOU Heping Analysis to traffic capacity of departure curbside parking of passenger transportation in airport landside[J]. Journal of Transport Science and Engineering, 2010, 26 (2): 98- 102 doi: 10.3969/j.issn.1674-599X.2010.02.017
7	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 YANG Fangyi, LI Tiezhu Traffic characteristics and capacities of passenger drop-off area at large intermodal transportation terminals[J]. Journal of Zhejiang University: Engineering Science, 2017, 51 (11): 2207- 2214
8	ASHFORD N, WRIGHT P, MUMAYIZ S. Airport engineering: planning, design, and development of 21st century airports [M]. Hobkin: John Wiley and Sons, 2011.
9	PASSOS L, KOKKINOGENIS Z, ROSSETTI R, et al. Multi-resolution simulation of taxi services on airport terminal's curbside [C]// International IEEE Conference on Intelligent Transportation Systems . The Hague: IEEE, 2013: 2361−2366.
10	HARRIS T, NOURINEJAD M, ROORDA M. A mesoscopic simulation model for airport curbside management [EB/OL]. [2023-02-01]. https://www.hindawi.com/journals/jat/2017/4950425/.
11	张晓丽. 基于元胞自动机的航站楼出发层车道边容量研究[D]. 西安: 长安大学, 2021. ZHANG Xiaoli. Curbside capacity analysis departure floor based on cellular automata [D]. Xi'an: Changan University, 2021.
12	TRAIN K. Discrete choice models with simulation [M]. Cambridge: Cambridge University Press, 2002.
13	LUCE D. Individual choice behavior [M]. New York: John Wiley and Sons, 1959.
14	SOUZA F, LARRANAGA A, PALMA D, et al Modeling travel mode choice and characterizing freight transport in a Brazilian context[J]. Transportation Letters, 2021, 14 (9): 983- 996
15	YAZICI M, KAMGA C, SINGHAL A Modeling taxi drivers' decisions for improving airport ground access: John F. Kennedy airport case[J]. Transportation Research Part A: Policy and Practice, 2016, 91: 48- 60 doi: 10.1016/j.tra.2016.06.004
16	YAO R, BEKHOR S Data-driven choice set generation and estimation of route choice models[J]. Transportation Research Part C: Emerging Technologies, 2020, 121: 102832 doi: 10.1016/j.trc.2020.102832
17	WANG S, WANG Q, BAILEY N, et al Deep neural networks for choice analysis: a statistical learning theory perspective[J]. Transportation Research Part B: Methodological, 2018, 148: 60- 81
18	HASNINE S, HABIB K Modeling the dynamics between tour-based mode choices and tour-timing choices in daily activity scheduling[J]. Transportation, 2020, 47: 2635- 2669 doi: 10.1007/s11116-019-10036-4
19	NIRMALE S, PINJARI A, SHARMA A A discrete-continuous multi-vehicle anticipation model of driving behaviour in heterogeneous disordered traffic conditions[J]. Transportation Research Part C: Emerging Technologies, 2021, 128: 103144 doi: 10.1016/j.trc.2021.103144
20	URATA J, XU Z, KE J Learning ride-sourcing drivers' customer-searching behavior: a dynamic discrete choice approach[J]. Transportation Research Part C: Emerging Technologies, 2021, 130: 103293 doi: 10.1016/j.trc.2021.103293
21	RAMBHA T, NOZICK L, DAVIDSON R Modeling hurricane evacuation behavior using a dynamic discrete choice framework[J]. Transportation Research Part B: Methodological, 2021, 150: 75- 100 doi: 10.1016/j.trb.2021.06.003
22	ANTONINI G, BIERLAIRE M, WEBER M Discrete choice models of pedestrian walking behavior[J]. Transportation Research Part B: Methodological, 2006, 40: 667- 687 doi: 10.1016/j.trb.2005.09.006
23	HASSAN M, NAJMI A, RASHIDI T A two-stage recreational destination choice study incorporating fuzzy logic in discrete choice modelling[J]. Transportation Research Part F: Traffic Psychology and Behaviour, 2019, 67: 123- 141 doi: 10.1016/j.trf.2019.10.015
24	GUZMAN L, ARELLANA J, CAMARGO J A hybrid discrete choice model to understand the effect of public policy on fare evasion discouragement in Bogot´a's Bus Rapid Transit[J]. Transportation Research Part A: Policy and Practice, 2021, 151: 140- 153 doi: 10.1016/j.tra.2021.07.009
25	杨方宜, 李铁柱大型综合客运枢纽送站坪的车辆延误[J]. 中国公路学报, 2018, 31 (9): 139- 149 YANG Fangyi, LI Tiezhu Vehicle delays in drop-off areas at large intermodal transportation terminals[J]. Journal of Highway and Transport, 2018, 31 (9): 139- 149 doi: 10.3969/j.issn.1001-7372.2018.09.016
26	ARKES H, BLUMER C The psychology of sunk cost[J]. Organizational Behavior and Human Decision Processes, 1985, 35 (1): 124- 140 doi: 10.1016/0749-5978(85)90049-4
27	STROUGH J, MEHTA C, MCFALL J, et al Are older adults less subject to the sunk-cost fallacy than younger adults[J]. Psychological Science, 2008, 19 (7): 650- 652 doi: 10.1111/j.1467-9280.2008.02138.x
28	FERNANDEZ P. The sunk cost fallacy and individual differences in health decisions [D]. EI Paso: The University of Texas, 2010.
29	KAPLAN E, MEIER P Nonparametric estimation from incomplete observations[J]. Journal of the American Statistical Association, 1958, 53: 457- 481 doi: 10.1080/01621459.1958.10501452
30	GREENWOOD M. The natural duration of cancer [EB/OL]. [2023-02-01]. https://www.sciencedirect.com/science/article/abs/pii/S0140673601265386.

[1]	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.

Viewed

Full text

Abstract

Cited

Shared

Discussed