融合长短期记忆网络和图卷积网络的轨道交通短时客流起讫点预测
作者:
中图分类号:

TP301.6

基金项目:

重庆理工大学研究生教育高质量发展行动计划资助(gzlcx20223189);重庆市轨道交通(集团)有限公司博士后项目(2019-347-37)。


Urban rail transit short-term passenger flow origin-destination forecast based on LSTM and GCN
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [26]
  • |
  • 相似文献 [20]
  • | | |
  • 文章评论
    摘要:

    轨道交通客流起讫点(origin-destination,OD)矩阵存在时间相关性和空间相关性。根据客流OD的时空特征,提出长短期记忆(long short-term memory,LSTM)网络和图卷积网络(graph convolutional networks,GCN)的短时组合预测方法。预测方法主要利用LSTM网络来获取客流的时间相关性,利用GCN来获取客流的空间相关性,基于出站口建立客流OD矩阵,对整个路网的客流OD进行训练预测。实验表明:融合LSTM神经网络和GCN神经网络的短时预测模型能有效预测轨道交通客流OD。相较于单独的LSTM神经网络,组合模型在预测误差方面有所改善,更适用于短时客流OD的预测。

    Abstract:

    The urban rail transit passenger flow origin-destination (OD) matrix has temporal correlation, spatial correlation. According to the spatio-temporal characteristics of passenger flow OD, a short-term prediction method based on long short-term memory (LSTM) neural network and graph convolution network (GCN) is proposed. The proposed prediction method uses the LSTM neural network to capture the temporal correlation, employs the GCN to capture the spatial correlation of the passenger flow, and builds the passenger flow OD matrix based on exit stations to train and test the passenger flow of the whole road network. The experiment shows that the short-term prediction modelled by combing LSTM neural network and GCN can predict the urban rail transit passenger flow OD more effectively. Compared with the single LSTM neural network, the proposed method reduces the prediction error, and is more suitable for short-term passenger flow OD prediction.

    参考文献
    [1] 侯晓云, 邵丽萍, 李静, 等. 基于深度学习的城市轨道交通短时客流起讫点预测[J]. 城市轨道交通研究, 2020, 23(1):55-58, 115. Hou X Y, Shao L P, Li J, et al. Urban rail transit short-time passenger flow OD forecasting based on deep learning modeling[J]. Urban Mass Transit, 2020, 23(1):55-58, 115.(in Chinese)
    [2] 唐继强, 钟鑫伟, 刘健, 等. 基于时间序列季节分类模型的轨道交通客流短期预测[J]. 重庆交通大学学报(自然科学版), 2021, 40(7):31-38, 60. Tang J Q, Zhong X W, Liu J, et al. Short term forecast of rail transit passenger flow based on time series seasonal classification model[J]. Journal of Chongqing Jiaotong University (Natural Science), 2021, 40(7):31-38, 60.(in Chinese)
    [3] Perrakis K, Karlis D, Cools M, et al. A Bayesian approach for modeling origin-destination matrices[J]. Transportation Research Part A:Policy and Practice, 2012, 46(1):200-212.
    [4] 姚向明, 赵鹏, 禹丹丹. 城市轨道交通网络短时客流OD估计模型[J]. 交通运输系统工程与信息, 2015, 15(2):149-155, 162. Yao X M, Zhao P, Yu D D. Short-time passenger flow origin-destination estimation model for urban rail transit network[J]. Journal of Transportation Systems Engineering and Information Technology, 2015, 15(2):149-155, 162.(in Chinese)
    [5] Kumar S V. Traffic flow prediction using Kalman filtering technique[J]. Procedia Engineering, 2017, 187:582-587.
    [6] Cai P L, Wang Y P, Lu G Q, et al. A spatiotemporal correlative k-nearest neighbor model for short-term traffic multistep forecasting[J]. Transportation Research Part C:Emerging Technologies, 2016, 62:21-34.
    [7] 方琴, 李永前. K近邻短期交通流预测[J]. 重庆交通大学学报(自然科学版), 2012, 31(4):828-831. Fang Q, Li Y Q. On K-nearest neighbor short-term traffic flow prediction[J]. Journal of Chongqing Jiaotong University (Natural Science), 2012, 31(4):828-831.(in Chinese)
    [8] 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 G, Han G Q, Lu F, et al. Short-term traffic flow forecasting 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)
    [9] Liyanage S, Abduljabbar R, Dia H, et al. AI-based neural network models for bus passenger demand forecasting using smart card data[J]. Journal of Urban Management, 2022, 11(3):365-380.
    [10] 吴慰. 短时交通流预测的PSO-PLS组合预测模型研究[D]. 重庆:重庆大学, 2009. Wu W. Study on PSO-PLS combined forecasting model for short-term traffic flow forecasting[D]. Chongqing:Chongqing University, 2009. (in Chinese)
    [11] Smith B L, Demetsky M J. Short-term traffic flow prediction:neural network approach[J]. Transportation Research Record, 1994, 1453(1453):98-104.
    [12] 赵顗, 沈玲宏, 马健霄, 等. 综合小波分解和BP神经网络的交通小区生成交通短时预测[J]. 重庆交通大学学报(自然科学版), 2021, 40(11):60-66. Zhao Y, Shen L H, Ma J X, et al. Traffic short-term prediction generated by wavelet decomposition and BP neural network of traffic zone[J]. Journal of Chongqing Jiaotong University (Natural Science), 2021, 40(11):60-66.(in Chinese)
    [13] 李洁, 彭其渊, 文超. 基于LSTM深度神经网络的高速铁路短期客流预测研究[J]. 系统工程理论与实践, 2021, 41(10):2669-2682. Li J, Peng Q Y, Wen C. Short term passenger flow prediction of high speed railway based on LSTM deep neural network[J]. Systems Engineering-Theory & Practice, 2021, 41(10):2669-2682.(in Chinese)
    [14] 徐冰冰, 岑科廷, 黄俊杰, 等. 图卷积神经网络综述[J]. 计算机学报, 2020, 43(5):755-780. Xu B B, Cen K T, Huang J J, et al. A survey on graph convolutional neural network[J]. Chinese Journal of Computers, 2020, 43(5):755-780.(in Chinese)
    [15] 陈喜群, 周凌霄, 曹震. 基于图卷积网络的路网短时交通流预测研究[J]. 交通运输系统工程与信息, 2020, 20(4):49-55. Chen X Q, Zhou L X, Cao Z. Short-term network-wide traffic prediction based on graph convolutional network[J]. Journal of Transportation Systems Engineering and Information Technology, 2020, 20(4):49-55.(in Chinese)
    [16] 陈镇元. 基于图卷积神经网络的地铁客流预测方法[J]. 科学技术创新, 2021(3):88-89. Chen Z Y. Subway passenger flow forecasting method based on graph convolution neural network[J]. Scientific and Technological Innovation, 2021(3):88-89.(in Chinese)
    [17] 雷斌, 张源, 郝亚睿, 等. 城市轨道交通短期客流预测研究进展[J]. 长安大学学报(自然科学版), 2022, 42(1):79-96. Lei B, Zhang Y, Hao Y R, et al. Research progress on short-term passenger flow forecast model of urban rail transit[J]. Journal of Chang'an University (Natural Science Edition), 2022, 42(1):79-96.(in Chinese)
    [18] 刘晓磊, 段征宇, 余庆, 等. 基于图卷积循环神经网络的城市轨道客流预测[J]. 华南理工大学学报(自然科学版), 2022, 50(3):21-27. Liu X L, Duan Z Y, Yu Q, et al. Passenger flow forecast of urban rail transit based on graph convolution and recurrent neural network[J]. Journal of South China University of Technology (Natural Science Edition), 2022, 50(3):21-27.(in Chinese)
    [19] 梁强升, 许心越, 刘利强. 面向数据驱动的城市轨道交通短时客流预测模型[J]. 中国铁道科学, 2020, 41(4):153-162. Liang Q S, Xu X Y, Liu L Q. Data-driven short-term passenger flow prediction model for urban rail transit[J]. China Railway Science, 2020, 41(4):153-162.(in Chinese)
    [20] 申慧涛, 郑亮, 李树凯, 等. 基于生成对抗网络的地铁OD需求短时预测[J]. 铁道科学与工程学报, 2022, 19(6):1530-1539. Shen H T, Zheng L, Li S K, et al. Short-term urban metro OD demand prediction with a Generative Adversarial Network[J]. Journal of Railway Science and Engineering, 2022, 19(6):1530-1539.(in Chinese)
    [21] Sutskever I, Vinyals O, Le Q V. Sequence to sequence learning with neural networks[EB/OL].[2022-01-01]. https://doi.org/10.48550/arXiv.1409.3215.
    [22] Sun R, Giles C L. Sequence learning:from recognition and prediction to sequential decision making[J]. IEEE Intelligent Systems, 2001, 16(4):67-70.
    [23] Kipf T N, Welling M. Semi-supervised classification with graph convolutional networks[EB/OL].[2021-01-01]. https://doi.org/10.48550/arXiv.1609.02907.
    [24] 林友芳, 尹康, 党毅, 等. 基于时空LSTM的OD客运需求预测[J]. 北京交通大学学报, 2019, 43(1):114-121. Lin Y F, Yin K, Dang Y, et al. Spatio-temporal LSTM for OD passenger demand prediction[J]. Journal of Beijing Jiaotong University, 2019, 43(1):114-121.(in Chinese)
    [25] 张建旭, 宾科, 蒋雨洋. 考虑轨道出行时空分布的断面客流预测[J]. 重庆理工大学学报:自然科学, 2022, 36(6):164-171.Zhang J X, Bin K, Jiang Y Y. Cross-section passenger flow prediction considering the temporal and spatial distribution of rail travel[J]. Journal of Chongqing University of Technology:Natural Science, 2022, 36(6):164-171. (in Chinese)
    [26] Hu J L, Yang B, Guo C J, et al. Stochastic origin-destination matrix forecasting using dual-stage graph convolutional, recurrent neural networks[C]//2020 IEEE 36th International Conference on Data Engineering. IEEE, 2020:1417-1428.
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

唐继强,杨璐琦,杨武.融合长短期记忆网络和图卷积网络的轨道交通短时客流起讫点预测[J].重庆大学学报,2022,45(11):91-99.

复制
分享
文章指标
  • 点击次数:629
  • 下载次数: 920
  • HTML阅读次数: 888
  • 引用次数: 0
历史
  • 收稿日期:2022-06-25
  • 在线发布日期: 2022-12-01
文章二维码