[1]胡明伟,施小龙,吴雯琳,等.城市轨道交通车站短时客流机器学习预测方法[J].深圳大学学报理工版,2022,39(5):593-599.[doi:10.3724/SP.J.1249.2022.05593]
 HU Mingwei,,et al.Machine learning based method for forecasting short-term passenger flow in urban rail stations[J].Journal of Shenzhen University Science and Engineering,2022,39(5):593-599.[doi:10.3724/SP.J.1249.2022.05593]
点击复制

城市轨道交通车站短时客流机器学习预测方法()
分享到:

《深圳大学学报理工版》[ISSN:1000-2618/CN:44-1401/N]

卷:
第39卷
期数:
2022年第5期
页码:
593-599
栏目:
交通物流
出版日期:
2022-09-16

文章信息/Info

Title:
Machine learning based method for forecasting short-term passenger flow in urban rail stations
文章编号:
202205014
作者:
胡明伟1234 施小龙1 吴雯琳1 何国庆1
1)深圳大学土木与交通工程学院,广东深圳 518060
2)深圳大学滨海城市韧性基础设施教育部重点实验室,广东深圳 518060
3)深圳大学未来地下城市研究院,广东深圳 518060
4)深圳大学深圳市地铁地下车站绿色高效智能建造重点实验室,广东深圳 518060
Author(s):
HU Mingwei12 3 4 SHI Xiaolong1 WU Wenlin1 and HE Guoqing1
1) College of Civil and Transportation Engineering, Shenzhen University, Shenzhen 518060, Guangdong Province, P.R.China
2) Key Laboratory of Coastal Urban Resilient Infrastructures of Ministry of Education, Shenzhen University,
Shenzhen 518060, Guangdong Province, P.R.China
3) Underground Polis Academy, Shenzhen University, Shenzhen 518060, Guangdong Province, P.R.China
4) Shenzhen Key Laboratory of Green, Efficient and Intelligent Construction of Underground Metro Station, Shenzhen University, Shenzhen 518060, Guangdong Province, P.R.China
关键词:
交通运输工程城市轨道交通短时客流预测数据处理特征工程机器学习
Keywords:
traffic and transportation engineering urban rail transit short-term passenger flow prediction data processing feature engineering machine learning
分类号:
U491
DOI:
10.3724/SP.J.1249.2022.05593
文献标志码:
A
摘要:
轨道交通具有载客量大、安全及环保等优点,已成为多数乘客的优先出行方式,是缓解城市交通压力的有效途径之一.为提高轨道系统的运行效率,实现轨道交通智慧化运营,基于机器学习算法理论,结合轨道交通车站的时间、空间及外部影响因素等客流特征,建立轻量的梯度提升机(light gradient boosting machine,LightGBM)、长短期记忆(long short-term memory,LSTM)及LightGBM-LSTM融合模型的车站短时客流预测模型,同时构建差分自回归移动平均(autoregressive integrated moving average,ARIMA)和极限梯度提升(extreme gradient boosting,XGBoost)模型作为预测实验的对照模型.以中国杭州地铁自动售票系统刷卡数据为例,选取了5种地铁车站(居住类型、工作类型、居住工作混合类型、购物类型及交通枢纽类型)和3个准确性评价指标(平均绝对误差、均方根误差及平均绝对百分误差),量化评价不同模型的预测准确性.结果表明,基于多特征的机器学习模型可以较好预测地铁车站短时客流,弥补了传统时间序列模型的不足.但单一模型在不同类型车站的预测效果波动性较大.基于多模型融合的LightGBM-LSTM模型可以综合单一模型的优点,预测性能更佳,对于不同类型车站的适应性更好.
Abstract:
Urban rail transit features much strength, such as large capacity, safety and environment-friendliness, and it becomes a preferred choice for most passengers. It also plays a prominent part in solving urban traffic problems. In order to improve the operation efficiency of the urban rail transit system and achieve the goal of smart operations, this paper applies machine learning algorithms and completes the feature engineering of urban rail transit passenger flow data in terms of time, space and external factors. Based on passenger flow characteristics as collected, we build the short-term passenger flow forecast models, which include light gradient boosting machine (LightGBM) model, long short-term memory (LSTM) model, and LightGBM-LSTM fusion model. Besides, we construct the autoregressive integrated moving average (ARIMA) model and extreme gradient boosting (XGBoost) model for experiment comparison. Finally, we conduct the passenger flow forecasting experiments on the Hangzhou subway dataset based on the five prediction-models mentioned above. Then, five types of subway stations are selected (residential type, occupation type, residential-occupation type, business type, and transportation hubs type) and three accuracy evaluation indicators are chosen (mean absolute error, root mean square error and mean absolute percentage error) to evaluate the prediction accuracy of the five prediction models. The experimental results show that, the multi-feature machine learning model can effectively forecast urban rail transit short-term passenger flow which is difficult for the traditional time series model. However, the single model has poor adaptability to different types of subway stations. Compared with a single model, LightGBM-LSTM model equipped with merits of multiple models, fulfills a better function in forecasting and a better adaptability to different types of urban rail transit stations.

参考文献/References:

[1] 中国人民共和国交通运输部.6月新增轨道交通运营里程150公里[EB/OL].(2022-07-08)[2022-07-25]. https://www.mot.gov.cn/jiaotongyaowen/202207/t20220708_3660760.html.
Ministry of Transport of the People’s Republic of China. In June, the new rail transit operation mileage was 150 kilometers 2022 [EB/OL]. (2022-07-08) [2022-07-25]. https://www.mot.gov.cn/jiaotongyaowen/202207/t20220708_3660760.html.(in Chinese)
[2] SUN Shiliang, ZHANG Changshui, YU Guoqiang. A Bayesian network approach to traffic flow forecasting [J]. IEEE Transactions on Intelligent Transportation Systems, 2006, 7(1): 124-132.
[3] CHANG H, LEE Y, YOON B, et al. Dynamic near-term traffic flow prediction: system-oriented approach based on past experiences [J]. IET Intelligent Transport Systems, 2012, 6(3): 292-305.
[4] JEONG Y, BYON Y, CASTRO-NETO M M, et al. Supervised weighting-online learning algorithm for short-term traffic flow prediction [J]. IEEE Transactions on Intelligent Transportation Systems, 2013, 14(4): 1700-1707.
[5] 傅贵,韩国强,逯峰,等.基于支持向量机回归的短时交通流预测模型[J].华南理工大学学报自然科学版,2013,41(9):71-76.
FU Gui, HAN Guoqiang, PANG Feng, et al. Short term traffic flow prediction model based on support vector machine regression [J]. Journal of South China University of Technology Natural Science Edition, 2013, 41(9): 71-76.(in Chinese)
[6] 付宇,翁剑成,钱慧敏,等.基于XGBoost算法的大型活动期间轨道进出站量预测[J].武汉理工大学学报交通科学与工程版,2020,44(5):832-836.
FU Yu, WEN Jiancheng, QIAN Huimin, et al. Prediction of metro passenger flow during large-scale activities based on XGBoost algorithm [J]. Journal of Wuhan University of Technology Transportation Science & Engineering, 2020, 44(5): 832-836.(in Chinese)
[7] LI Linchao, HE Shuanglu, ZHANG Jian, et al. Short-term highway traffic flow prediction based on a hybrid strategy considering temporal-spatial information [J]. Journal of Advanced Transportation, 2016, 50(8): 2029-2040.
[8] SHI Rui, XU Xinyue. A train arrival delay prediction model using XGBoost and Bayesian optimization [C]// Proceedings of IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC). Rhodes, Greece: IEEE, 2020: 1-6.
[9] 谭满春,冯荦斌,徐建闽.基于ARIMA与人工神经网络组合模型的交通流预测[J].中国公路学报,2007,20(4):118-121.
TAN Manchun, FENG Luobin, XU Jianmin, et al. Traffic flow prediction based on hybrid ARIMA and ANN model [J]. China Journal of Highway and Transport, 2007, 20(4): 118-121.(in Chinese)
[10] 李若怡.基于改进时空LSTM模型的城市轨道交通系统OD客流短时预测[D].北京:北京交通大学,2019.
LI Ruoyi. Short-term prediction of origin-destination passenger flow for urban rail transit based on improved spatio-temporal LSTM model [D]. Beijing: Beijing Jiaotong University, 2019.(in Chinese)

相似文献/References:

[1]马羽,王卓群,温少表,等.基于乘客均衡候车的轨道交通协同限流建模[J].深圳大学学报理工版,2017,34(5):537.[doi:10.3724/SP.J.1249.2017.05537]
 Ma Yu,Wang Zhuoqun,Wen Shaobiao,et al.Modeling of flow co-control among multi-stations based on passenger equilibrium waiting for urban rail transit[J].Journal of Shenzhen University Science and Engineering,2017,34(5):537.[doi:10.3724/SP.J.1249.2017.05537]
[2]于泉,刘洋,郭骁伟.基于路口相关性的交通流量修复研究[J].深圳大学学报理工版,2019,36(3):304.[doi:10.3724/SP.J.1249.2019.03304]
 YU Quan,LIU Yang,and GUO Xiaowei.Restoration of traffic flow data based on intersection correlation[J].Journal of Shenzhen University Science and Engineering,2019,36(5):304.[doi:10.3724/SP.J.1249.2019.03304]
[3]曾翠峰,侯宇菲,罗钦,等.延误条件下的轨道交通客流拥挤传播建模[J].深圳大学学报理工版,2019,36(3):310.[doi:10.3724/SP.J.1249.2019.03310]
 ZENG Cuifeng,HOU Yufei,LUO Qin,et al.Modeling of congestion propagation of rail transit passenger flow under delay conditions[J].Journal of Shenzhen University Science and Engineering,2019,36(5):310.[doi:10.3724/SP.J.1249.2019.03310]
[4]李伟,等.基于多层灰色关联的地铁列车运行图综合评价[J].深圳大学学报理工版,2019,36(6):682.[doi:10.3724/SP.J.1249.2019.06682]
 LI Wei,YANG Yongtai,et al.Comprehensive evaluation of train schedule on urban rail network based on grey correlated analysis[J].Journal of Shenzhen University Science and Engineering,2019,36(5):682.[doi:10.3724/SP.J.1249.2019.06682]
[5]贺云鹏,李建国.平面移动式立体车库客流状态聚类研究[J].深圳大学学报理工版,2020,37(3):314.[doi:10.3724/SP.J.1249.2020.03314]
 HE Yunpeng and LI Jianguo.Passenger flow state clustering in flat mobile automated garage[J].Journal of Shenzhen University Science and Engineering,2020,37(5):314.[doi:10.3724/SP.J.1249.2020.03314]
[6]李军,郑培庆.城市公交过剩通勤分析与评价——以广州市为例[J].深圳大学学报理工版,2020,37(6):623.[doi:10.3724/SP.J.1249.2020.06623]
 LI Jun and ZHENG Peiqing.Analyzing and evaluating of the urban transit excess commuting: a case study of Guangzhou City[J].Journal of Shenzhen University Science and Engineering,2020,37(5):623.[doi:10.3724/SP.J.1249.2020.06623]
[7]胡明伟,等.基于系统动力学的地铁客流防疫调控仿真分析[J].深圳大学学报理工版,2021,38(2):111.[doi:10.3724/SP.J.1249.2021.02111]
 HU Mingwei,,et al.Simulation analysis of epidemic prevention and regulation for metro passenger flow based on system dynamics[J].Journal of Shenzhen University Science and Engineering,2021,38(5):111.[doi:10.3724/SP.J.1249.2021.02111]
[8]杨波,李建国,康耀军.立体车库顾客到达的非齐次泊松过程模拟仿真[J].深圳大学学报理工版,2021,38(2):121.[doi:10.3724/SP.J.1249.2021.02121]
 YANG Bo,LI Jianguo,and KANG Yaojun.Simulation of non-homogeneous Poisson process of customer arrival in stereo garage[J].Journal of Shenzhen University Science and Engineering,2021,38(5):121.[doi:10.3724/SP.J.1249.2021.02121]
[9]刘鹏,胡明伟,等.深圳市非道路移动机械排放清单研究[J].深圳大学学报理工版,2021,38(4):331.[doi:10.3724/SP.J.1249.2021.04331]
 LIU Peng,HU Mingwei,,et al.Emission inventory of non-road mobile machinery in Shenzhen[J].Journal of Shenzhen University Science and Engineering,2021,38(5):331.[doi:10.3724/SP.J.1249.2021.04331]
[10]胡明伟,等.地铁车站水侵应急疏散仿真研究[J].深圳大学学报理工版,2022,39(2):159.[doi:10.3724/SP.J.1249.2022.02159]
 HU Mingwei,TANG Jingyan,and HE Guoqing.Simulation study on emergency evacuation due to water invasion in subway stations[J].Journal of Shenzhen University Science and Engineering,2022,39(5):159.[doi:10.3724/SP.J.1249.2022.02159]
[11]李伟,罗钦.基于逐步优化的轨道交通网络行车计划衔接[J].深圳大学学报理工版,2018,35(6):629.[doi:10.3724/SP.J.1249.2018.06629]
 LI Wei and LUO Qin.Rail transit network planning based on gradual optimization[J].Journal of Shenzhen University Science and Engineering,2018,35(5):629.[doi:10.3724/SP.J.1249.2018.06629]
[12]周菁楠,李伟,罗钦.城轨车站大客流条件下列车运行调整[J].深圳大学学报理工版,2020,37(6):617.[doi:10.3724/SP.J.1249.2020.06617]
 ZHOU Jingnan,LI Wei,and LUO Qin.Adjustment for train operation under the condition of mass passenger flow in urban rail transit[J].Journal of Shenzhen University Science and Engineering,2020,37(5):617.[doi:10.3724/SP.J.1249.2020.06617]

备注/Memo

备注/Memo:
Received: 2021- 06-22; Accepted: 2021-08-11; Online (CNKI): 2022- 08- 09
Foundation: Guangdong Consulting and Research Funding Project for China’s Engineering Science and Technology Development Strategy (2020-GD-09)
Corresponding author: Professor HU Mingwei. E-mail: humw@szu.edu.cn
Citation: HU Mingwei, SHI Xiaolong, WU Wenlin, et al. Machine learning based method for forecasting short-term passenger flow in urban rail stations [J]. Journal of Shenzhen University Science and Engineering, 2022, 39(5): 593-599.(in Chinese)
基金项目:中国工程科技发展战略广东咨询研究资助项目(2020-GD- 09)
作者简介:胡明伟(1972—),深圳大学教授、博士生导师.研究方向:交通系统建模与仿真,智能交通系统. E-mail: humw@szu.edu.cn
引文:胡明伟,施小龙,吴雯琳,等.城市轨道交通车站短时客流机器学习预测方法[J].深圳大学学报理工版,2022,39(5):593-599.
更新日期/Last Update: 2022-09-30