基于组合深度学习的轨道交通短时进站客流预测模型

doi:10.3969/j.issn.1674-0696.2024.02.12

摘要/Abstract

摘要： 针对轨道交通短时进站客流考虑不充分和特征学习不全面而导致预测精度不高的问题，选取客流特征、天气、空气质量和道路交通拥堵指数等多个因素，提出了一种基于组合深度学习的轨道交通短时进站客流预测模型(CNN-ResNet-BiLSTM)。基于卷积神经网络(CNN)对多因素客流时间序列进行自动提取，在CNN网络中插入多个残差神经网络(ResNet)来加深网络深度，利用双向长短时记忆神经网络(BiLSTM)捕捉前后两个方向的客流时间序列特征并得到预测结果；以杭州市全网80个站点工作日的进站客流为例，验证了该模型的有效性。研究结果表明：与常用的几种模型相比，多因素CNN-ResNet-BiLSTM组合模型的均方根误差(ERMS)至少降低了8.50%，平均绝对误差(EMA)至少降低了6.74%，平均绝对百分比误差(EMPA)至少降低了6.52%。

关键词: 交通工程；短时客流预测；组合深度学习；轨道进站客流

Abstract: Aiming at the problem of low prediction accuracy caused by incomplete consideration of factors and feature learning in the short-term inbound passenger flow prediction model of rail transit, a combined deep learning model based short-term inbound passenger flow prediction method for rail transit (CNN ResNet BiLSTM) was proposed by selecting multiple factors such as passenger flow characteristics, weather, air quality and road traffic congestion index. The multi-factor passenger flow time series were automatically extracted based on convolution neural network (CNN), and several residual neural networks (ResNet) were added into the CNN network to deepen the depth of the network. The bidirectional long short-term memory neural network (BiLSTM) was used to capture the time series characteristics of passenger flow in bidirectional directions and obtain the prediction results. The validity of the proposed prediction method was verified by a case study on the inbound passenger flow predication of 80 stations in whole network of Hangzhou city on workdays. The research results show that the root mean square error (ERMS) of the multi-factor CNN-ResNet-BiLSTM combined model is reduced by at least 8.50%, and the mean absolute error (EMA) is reduced by at least 6.74% and the mean absolute percentage error (EMPA) is reduced by at least 6.52%, compared with the several commonly used models.

Key words: traffic engineering; short term passenger flow prediction; combined deep learning; rail transit inbound passenger flow

中图分类号:

U293.13

李淑庆，李伟，刘耀鸿，马波. 基于组合深度学习的轨道交通短时进站客流预测模型[J]. 重庆交通大学学报（自然科学版）, 2024, 43(2): 92-99.

LI Shuqing, LI Wei, LIU Yaohong, MA Bo. Short-Term Inbound Passenger Flow Prediction of Model Rail Transit Based on Combined Deep Learning[J]. Journal of Chongqing Jiaotong University(Natural Science), 2024, 43(2): 92-99.

参考文献

［1］ LIU Shuying, LIU Shuo, TIAN Ye, et al. Research on forecast of rail traffic flow based on ARIMA model［J］.Journal of Physics: Conference Series, 2021, 1792(1): 012065.
［2］孟品超, 李学源, 贾洪飞, 等. 基于滑动平均法的轨道交通短时客流实时预测［J］. 吉林大学学报(工学版), 2018, 48(2): 448-453.
MENG Pinchao, LI Xueyuan, JIA Hongfei, et al. Short-time rail transit passenger flow real-time prediction based on moving average［J］. Journal of Jilin University (Engineering and Technology Edition), 2018, 48(2): 448-453.
［3］ LIANG Shidong, MA Minghui, HE Shengxue, et al. Short-term passenger flow prediction in urban public transport: Kalman filtering combined K-nearest neighbor approach［J］.IEEE Access, 1809, 7: 120937-120949.
［4］ ROOS J, GAVIN G, BONNEVAY S. A dynamic Bayesian network approach to forecast short-term urban rail passenger flows with incomplete data［J］.Transportation Research Procedia, 2017, 26: 53-61.
［5］郇宁, 谢俏, 叶红霞, 等. 基于改进KNN算法的城轨进站客流实时预测［J］. 交通运输系统工程与信息, 2018, 18(5): 121-128.
HUAN Ning, XIE Qiao, YE Hongxia, et al. Real-timeforecasting of urban rail transit ridership at the station level based on improved KNN algorithm［J］. Journal of Transportation Systems Engineering and Information Technology, 2018, 18(5): 121-128.
［6］谢臻, 郭建媛, 秦勇. 基于支持向量回归的地铁进站客流短时预测模型［J］. 都市快轨交通, 2020, 33(2): 82-86.
XIE Zhen, GUO Jianyuan, QIN Yong. Short-termprediction model of subway entry passenger flow based on support vector regression［J］. Urban Rapid Rail Transit, 2020, 33(2): 82-86.
［7］惠阳, 王永岗, 彭辉, 等. 基于优化PSO-BP算法的耦合时空特征下地铁客流预测［J］. 交通运输工程学报, 2021, 21(4): 210-222.
HUI Yang, WANG Yonggang, PENG Hui, et al. Subway passenger flow prediction based on optimized PSO-BP algorithm with coupled spatial-temporal characteristics［J］.Journal of Traffic and Transportation Engineering, 2021, 21(4): 210-222.
［8］ MA Xiaolei, DAI Zhuang, HE Zhengbing, et al. Learning traffic as images: A deep convolutional neural network for large-scale transportation network speed prediction［J］.Sensors, 2017, 17(4): 818. DOI: 10.3390/s17040818.
［9］ YANG Xin, XUE Qiuchi, DING Meiling, et al. Short-term prediction of passenger volume for urban rail systems: A deep learning approach based on smart-card data［J］.International Journal of Production Economics, 2021, 231: 107920.
［10］ LI Wei, SUI Liying, ZHOU Min, et al. Short-term passenger flow forecast for urban rail transit based on multi-source data［J］.EURASIP Journal on Wireless Communications and Networking, 2021, 2021(1): 1-13.
［11］赵阳阳, 夏亮, 江欣国. 基于经验模态分解与长短时记忆神经网络的短时地铁客流预测模型［J］. 交通运输工程学报, 2020, 20(4): 194-204.
ZHAO Yangyang, XIA Liang, JIANG Xinguo. Short-term metro passenger flow prediction based on EMD-LSTM［J］.Journal of Traffic and Transportation Engineering, 2020, 20(4): 194-204.
［12］王秋雯, 陈彦如, 刘媛春. 基于卷积长短时记忆神经网络的城市轨道交通短时客流预测［J］. 控制与决策, 2021, 36(11): 2760-2770.
WANG Qiuwen, CHEN Yanru, LIU Yuanchun. Metro short-term traffic flow prediction with ConvLSTM［J］.Control and Decision, 2021, 36(11): 2760-2770.
［13］朱志浩. 基于集成学习的城市轨道交通进出站客流短时预测研究［D］. 成都: 西南交通大学, 2020.
ZHU Zhihao.Short-Term Prediction on Entrance and Exit Passenger Flow of Urban Rail Transit Station by Ensemble Learning［D］. Chengdu: Southwest Jiaotong University, 2020.
［14］王佳琳. 基于深度学习模型的城市轨道交通短时客流预测方法研究［D］. 北京: 北京交通大学, 2020.
WANG Jialin.Research on Short-Term Passenger Flow Prediction Method of Urban Rail Transit Based on Deep Learning Model［D］. Beijing: Beijing Jiaotong University, 2020.
［15］ LI Jing, PENG Hao, LIU Lin, et al. Graph CNNs for urban traffic passenger flows prediction［C］//2018 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (Smart World/SCALCOM/UIC/ATC/CBDCom/IOP/SCI). Guangzhou, China. IEEE, 2018: 29-36.
［16］许熳灵, 付晓, 汤君友, 等. 天气因素对城市地铁客流时空分布的影响——基于智能交通卡数据的实证研究［J］. 地理科学进展, 2020, 39(1): 45-55.
XU Manling, FU Xiao, TANG Junyou, et al. Effects of weather factors on the spatial and temporal distributions of metro passenger flows:An empirical study based on smart card data［J］. Progress in Geography, 2020, 39(1): 45-55.
［17］侯晓云. 城市轨道交通线网短时OD客流预测研究［D］. 北京: 北京交通大学, 2020.
HOU Xiaoyun.Research on Short-Time Origin-Destination Passenger Flow Forecasting for Urban Rail Transit Network［D］. Beijing: Beijing Jiaotong University, 2020.
［18］吴祥国, 张建嵩, 胡义良, 等. 重庆市轨道交通客流时间特性及影响因素探讨［J］. 铁道运输与经济, 2020, 42(11): 117-122.
WU Xiangguo, ZHANG Jiansong, HU Yiliang, et al. Atentative study on the time characteristic and influencing factors of urban rail passenger flow in Chongqing［J］. Railway Transport and Economy, 2020, 42(11): 117-122.
［19］冯骥, 伍思雨, 王琛越. 基于因子分析与K-means聚类算法的P2P网贷平台风险评估模型［J］. 重庆师范大学学报(自然科学版), 2020, 37(5): 96-102.
FENG Ji, WU Siyu, WANG Chenyue. Peer-to-peer lending platform risk identification method based on factor analysis and K-means cluster algorithm［J］. Journal of Chongqing Normal University (Natural Science), 2020, 37(5): 96-102.
［20］ NGUYEN T, NGUYEN G, NGUYEN B M. EO-CNN: An enhanced CNN model trained by equilibrium optimization for traffic transportation prediction［J］.Procedia Computer Science, 2020, 176: 800-809.
［21］ HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition［C］//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, N V, USA. IEEE, 2016: 770-778.
［22］ HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Identity mappings in deep residual networks［C］//European Conference on Computer Vision. Cham: Springer, 2016: 630-645.
［23］冯碧玉. 基于CNN-LSTM组合模型的城市轨道交通短时客流预测研究［D］. 南昌: 华东交通大学, 2020.
FENG Biyu.Short Term Passenger Flow Prediction of Urban Rail Transit Based on CNN-LSTM Combined Model［D］. Nanchang: East China Jiaotong University, 2020.
［24］ LI Zhihong, XU Han, GAO Xiuli, et al. Fusion attention mechanism bidirectional LSTM for short-term traffic flow prediction［J］.Journal of Intelligent Transportation Systems. DOI:10.1080/15472450.2022.2142049.

[1]	刘杰. 基于栈式自编码的高速铁路站间客流短期预测研究[J]. 重庆交通大学学报（自然科学版）, 2021, 40(05): 26-30.
[2]	刘莎，董国发，李想，曾晰. 客流量动态影响下公交智慧出行服务模型研究[J]. 重庆交通大学学报（自然科学版）, 2020, 39(10): 10-17.
[3]	刘杰. 基于集成算法的铁路客流短期预测模型研究[J]. 重庆交通大学学报（自然科学版）, 2022, 41(05): 20-25.