计算机科学

计算机科学 ›› 2023, Vol. 50 ›› Issue (7): 213-220.doi: 10.11896/jsjkx.220600120

• 人工智能 • 上一篇    下一篇

基于时序知识图谱嵌入的短期地铁客流量预测

毛慧慧, 赵小乐, 杜圣东, 滕飞, 李天瑞   

  1. 西南交通大学计算机与人工智能学院 成都 611756
  • 收稿日期:2022-06-13 修回日期:2022-11-10 出版日期:2023-07-15 发布日期:2023-07-05
  • 通讯作者: 李天瑞(trli@swjtu.edu.cn)
  • 作者简介:(hhmslt@163.com)
  • 基金资助:
    国家重点研发计划(2019YFB2101801)

Short-term Subway Passenger Flow Forecasting Based on Graphical Embedding of Temporal Knowledge

MAO Huihui, ZHAO Xiaole, DU Shengdong, TENG Fei, LI Tianrui   

  1. School of Computing and Artificial Intelligence,Southwest Jiaotong University,Chengdu 611756,China
  • Received:2022-06-13 Revised:2022-11-10 Online:2023-07-15 Published:2023-07-05
  • About author:MAO Huihui,born in 1998,postgra-duate.Her main research interests include knowledge graph and traffic flow prediction.LI Tianrui,born in 1969,Ph.D,professor,Ph.D supervisor,is a distinguished member of China Computer Federation.His main research interests include big data intelligence,rough sets and granular computing.
  • Supported by:
    National Key R&D Program of China(2019YFB2101801).

PDF (PC)

430

摘要： 短期地铁客流量预测任务是城市智能地铁运营工作的重要组成部分,旨在预测未来短时间内地铁站点的客流量。针对现有方法未能充分利用站点的流入流出客流量信息的问题,提出了一种基于时序知识图谱嵌入(Temporal Knowledge Graph Embedding)结合残差网络(ResNet)和长短期记忆网络(LSTM)的短期地铁客流量预测方法,简称TKG-ResLSTM。首先,基于地铁客流量数据构建地铁客流量时序知识图谱,并使用时序知识图谱嵌入技术从中获取地铁站点的动态客流量模式。然后,将抽取出的动态客流量模式转换成动态相似矩阵,应用到基于深度学习的地铁客流量预测框架中完成地铁客流量预测任务。最后,利用北京地铁和A市地铁客流量数据集,分别在10 min,15 min和30 min的时间间隔下进行实验评估。结果表明TKG-ResLSTM能够有效地抽取出地铁站点的动态客流量模式,在不使用外部信息的情况下,相比ResLSTM,TKG-ResLSTM在北京地铁数据集10min时间间隔下的预测均方根误差降低了0.41。

关键词: 深度学习, 时序知识图谱, 时空预测, 动态嵌入, 城市地铁网络

Abstract: Subway short-term passenger flow forecasting is an essential component in urban subway operation,and it aims to forecast the passenger flow of subway stations in a short time in the future.Aiming at the problem that the existing methods fail to make full use of the passenger flow information of stations,a short-term subway passenger flow forecasting method based on temporal knowledge graph embedding combined with residual network and long short-term memory network is proposed,which is called TKG-ResLSTM.First,we use subway passenger flow data to construct a temporal knowledge graph of subway passenger flow,and apply the graphical embedding of temporal knowledge to obtain the dynamic patterns of subway stations passenger flow.Then,the extracted dynamic patterns of passenger flow are converted into dynamic similarity matrices and applied to theforecasting architecture of subway passenger flow based on deep learning to complete the subway passenger flow forecasting task.Finally,experimental evaluations are carried out at time granularities of 10 min,15 min,and 30 min using the Beijing subway and city A subway passenger flow datasets,respectively.Experimental results show that TKG-ResLSTM can effectively extract the dynamic patterns of subway stations passenger flow.Without using external information,TKG-ResLSTM reduces the root mean square error of forecasting by 0.41 compared with ResLSTM in the time granularity of 10 min of the Beijing subway dataset.

Key words: Deep learning, Temporal knowledge graph, Spatial-Temporal forecasting, Dynamic embedding, Citywide metro network

中图分类号: 

  • TP391
[1]LIU J,GUAN W.A summary of traffic flow forecasting me-thods[J].Journal of Highway and Transportation Research and Development,2004,21(3):82-85.
[2]WANG P,LIU Y.Network traffic prediction based on improved BP wavelet neural network[C]//2008 4th International Confe-rence on Wireless Communications,Networking and Mobile Computing.IEEE,2008:1-5.
[3]LENG B,ZENG J,XIONG Z,et al.Probability tree based passenger flow prediction and its application to the Beijing subway system[J].Frontiers of Computer Science,2013,7(2):195-203.
[4]SU H,YU S.Hybrid GA based online support vector machine model for short-term traffic flow forecasting[C]//International Workshop on Advanced Parallel Processing Technologies.Springer,2007:743-752.
[5]ROOS J,BONNEVAY S,GAVIN G.Short-term urban rail passenger flow forecasting:A dynamic bayesian network approach[C]//2016 15th IEEE International Conference on Machine Learning and Applications(ICMLA).IEEE,2016:1034-1039.
[6]SUN Y,LENG B,GUAN W.A novel wavelet-SVM short-time passenger flow prediction in Beijing subway system[J].Neurocomputing,2015,166:109-121.
[7]LECUN Y,BENGIO Y,HINTON G.Deep learning[J].Nature,2015,521(7553):436-444.
[8]ZHANG J,CHEN F,GUO Y,et al.Multi-graph convolutional network for short-term passenger flow forecasting in urban rail transit[J].IET Intelligent Transport Systems,2020,14(10):1210-1217.
[9]YANG D,CHEN K,YANG M,et al.Urban rail transit passenger flow forecast based on LSTM with enhanced long-term features[J].IET Intelligent Transport Systems,2019,13(10):1475-1482.
[10]TANG T T,ZHOU W.Research on commodity sales forecastoriented on deep learning[J].Journal of Chongqing University of Technology(Natural Science),2022,36(7):310-317.
[11]ZHANG J,ZHENG Y,QI D.Deep spatio-temporal residual networks for citywide crowd flows prediction[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2017:1655-1661.
[12]YAO H,WU F,KE J,et al.Deep multi-view spatial-temporal network for taxi demand prediction[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2018:2588-2595.
[13]HAN Y,WANG S,REN Y,et al.Predicting station-level short-term passenger flow in a citywide metro network using spatiotemporal graph convolutional neural networks[J].ISPRS International Journal of Geo-Information,2019,8(6):243.
[14]YU B,YIN H,ZHU Z.Spatio-temporal graph convolutional networks:A deep learning framework for traffic forecasting[J].arXiv:1709.04875,2017.
[15]TANG L,ZHAO Y,CABRERA J,et al.Forecasting short-term passenger flow:An empirical study on shenzhen metro[J].IEEE Transactions on Intelligent Transportation Systems,2018,20(10):3613-3622.
[16]ZHANG J,CHEN F,CUI Z,et al.Deep learning architecture for short-term passenger flow forecasting in urban rail transit[J].IEEE Transactions on Intelligent Transportation Systems,2020,22(11):7004-7014.
[17]JI T,HE Y,ZHU Y Y,et al.Power user clustering methodbased on a combination of knowledge graph and modified Gaussian mixture model[J].Journal of Chongqing University of Technology(Natural Science),2022,36(12):92-101.
[18]LIU Y,LIU Z,JIA R.DeepPF:A deep learning based architecture for metro passenger flow prediction[J].Transportation Research Part C:Emerging Technologies,2019,101:18-34.
[19]HAO S,LEE D H,ZHAO D.Sequence to sequence learningwith attention mechanism for short-term passenger flow prediction in large-scale metro system[J].Transportation Research Part C:Emerging Technologies,2019,107:287-300.
[20]YE J,ZHAO J,YE K,et al.Multi-STGCnet:A graph convolution based spatial-temporal framework for subway passenger flow forecasting[C]//2020 International Joint Conference on Neural Networks(IJCNN).IEEE,2020:1-8.
[21]LIN Y,HAN X,XIE R,et al.Knowledge representation lear-ning:A quantitative review[J].arXiv:1812.10901,2018.
[22]GARCÍA-DURÁN A,DUMANCˇIĆS,NIEPERT M.Learning sequence encoders for temporal knowledge graph completion[J].arXiv:1809.03202,2018.
[23]GOEL R,KAZEMI S M,BRUBAKER M,et al.Diachronic embedding for temporal knowl-edge graph completion[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2020:3988-3995.
[24]JIANG T,LIU T,GE T,et al.Towards time-aware knowledge graph completion[C]//Proceedings of the 26th International Conference on Computational Linguistics:Technical Papers.2016:1715-1724.
[25]YANG B,YIH W,HE X,et al.Embedding entities and relations for learning and inference in knowledge bases[J].arXiv:1412.6575,2014.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发