哈尔滨工业大学,交通科学与工程学院;
【背景】客流预测是城市轨道交通运营和管理的重要组成，近年来结合多源数据和深度神经网络的精准客流预测受到越来越多的关注。【目标】提升轨道交通站点客流预测的精度，为运营管理提供有效支持。【方法】首先，搭建一种融合多特征的站点客流预测模型，该模型通过卷积神经网络（CNN）提取地铁客流的时空特征，并结合残差单元（ResNet）增强特征提取能力，构建特征传播矩阵挖掘站点间的空间特征，采用长短期记忆网络（LSTM）提取影响因子序列数据的时间特征，在特征融合过程中应用注意力机制突出关键特征。随后，引入遗传算法（GA）对模型进行优化，并采用多层感知器（MLP）修正模型的预测结果误差，提高模型的预测精度。【数据】杭州地铁站点刷卡数据及对应的气象数据、POI数据。【结果】优化ResNet-CNN-LSTM-Attention模型（IO-RCLA）的预测精度最高。相比于RCLA模型，IO-RCLA所有站点预测结果的MAE、RMSE、MAPE分别降低了17.09%、16.09%和8.91%，证明了方法在多站点客流预测中的高精度和有效性。
| 751 | 0 | 92 |
| 下载次数 | 被引频次 | 阅读次数 |
[1]中华人民共和国交通运输部.2023年11月城市轨道交通运营数据速报[EB/OL].(2023-12-07)[2024-04-23].https://www.mot.gov.cn/fenxigongbao/yunlifenxi/202312/t20231207_3963882.html.
[2]文超,李津,李忠灿,等.机器学习在铁路列车调度调整中的应用综述[J].交通运输工程与信息学报, 2022, 20(1):1-14.WEN Chao, LI Jin, LI Zhongcan, et al. Review on application of machine learning methods to railway train operation adjustment[J]. Journal of Transportation Engineering and Information, 2022, 20(1):1-14.
[3] LI Z, BI J, LI Z. Passenger flow forecasting research for airport terminal based on SARIMA time series model[J].IOP Conference Series:Earth and Environmental Science, 2017, 100:012146.
[4]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, WENG 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.
[5] MA C, DAI G, ZHOU J. Short-term traffic flow prediction for urban road sections based on time series analysis and LSTM_BILSTM method[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(6):5615-5624.
[6] MA X, ZHANG J, DU B, et al. Parallel architecture of convolutional bi-directional LSTM neural networks for network-wide metro ridership prediction[J]. IEEE Transactions on Intelligent Transportation Systems, 2019, 20(6):2278-2288.
[7]李明捷,王涛,黄欣宁,等.考虑延误特征的航站楼离港聚集客流预测方法[J].交通运输系统工程与信息,2024, 24(3):240-254.LI Mingjie, WANG Tao, HUANG Xinning, et al. Airport terminal departure aggregation passenger flow prediction considering flight delay characteristics[J]. Journal of Transportation Systems Engineering and Information Technology, 2024, 24(3):240-254.
[8]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 Xiaolei, DUAN Zhengyu, YU Qing, 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.
[9]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.
[10] SINGHAL A, KAMGA C, YAZICI A. Impact of weather on urban transit ridership[J]. Transportation Research Part A:Policy and Practice, 2014, 69:379-391.
[11]户佐安,邓锦程,杨江浩,等.轨道交通站点聚类及其对客流预测的影响分析[J].交通运输系统工程与信息, 2023, 23(6):227-238.HU Zuoan, DENG Jincheng, YANG Jianghao, et al. Rail transit station clustering and its impact on passenger flow forecasting[J]. Journal of Transportation Systems Engineering and Information Technology, 2023, 23(6):227-238.
[12]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.
[13] KHALIL S, AMRIT C, KOCH T, et al. Forecasting public transport ridership:management of information systems using CNN and LSTM architectures[J]. Procedia Computer Science, 2021, 184:283-290.
[14]李兆丰,倪少权,孙克洋,等.基于多特征融合的城市轨道交通短时客流预测[J].交通运输工程与信息学报, 2020, 18(4):93-102.LI Zhaofeng, NI Shaoquan, SUN Keyang, et al. Shortterm passenger flow prediction of an urban rail transit based on multi-feature fusion[J]. Journal of Transportation Engineering and Information, 2020, 18(4):93-102.
[15]刘欣彤.降雨天气条件下短时公交客流预测研究[D].哈尔滨:哈尔滨工业大学, 2016.LIU Xintong. Research on short-term bus passenger demand forecasting under rainy weather conditions[D].Harbin:Harbin Institute of Technology, 2016.
[16]许心越,孔庆雪,李建民,等.建成环境对轨道交通客流的时空异质性影响分析[J].交通运输系统工程与信息, 2023, 23(4):194-202, 281.XU Xinyue, KONG Qingxue, LI Jianmin, et al. Analysis of spatio-temporal heterogeneity impact of built environment on rail transit passenger flow[J]. Journal of Transportation Systems Engineering and Information Technology, 2023, 23(4):194-202, 281.
[17]朱子俊,宋国华,范鹏飞,等.基于趋势提取下多尺度时空残差网络的路段速度预测模型[J].交通运输工程与信息学报, 2023, 21(3):74-85.ZHU Zijun, SONG Guohua, FAN Pengfei, et al. Roadway speed prediction model based on multiscale spatiotemporal residual network and detrending[J]. Journal of Transportation Engineering and Information, 2023, 21(3):74-85.
[18]禹倩,张亚东,郭进,等.基于深度集成神经网络的城市轨道交通短时进站客流预测[J].铁道学报, 2023, 45(12):37-46.YU Qian, ZHANG Yadong, GUO Jin, et al. Short-term inbound passenger flow forecasting for urban rail transit based on deep ensemble neural network[J]. Journal of the China Railway Society, 2023, 45(12):37-46.
[19]陈光武,高亚丽,焦相萌.基于自适应变异SAPSOLSSVM的轨道电路故障诊断[J].北京交通大学学报,2021, 45(2):1-7.CHEN Guangwu, GAO Yali, JIAO Xiangmeng. Track circuit fault diagnosis based on adaptive mutation SAPSO-LSSVM[J]. Journal of Beijing Jiaotong University,2021, 45(2):1-7.
[20] CICEK Z I E, OZTURK Z K. Optimizing the artificial neural network parameters using a biased random key genetic algorithm for time series forecasting[J]. Applied Soft Computing, 2021, 102:107091.
[21]陈亮,郝祎纯,李巧茹,等.改进SSA优化的BP神经网络交通量预测模型[J].哈尔滨工业大学学报, 2024, 56(7):94-101.CHEN Liang, HAO Yichun, LI Qiaoru, et al. Traffic volume forecast model based on BP neural network optimized by improved sparrow search algorithm[J]. Journal of Harbin Institute of Technology, 2024, 56(7):94-101.
[22] NIKBAKHT S, ANITESCU C, RABCZUK T. Optimizing the neural network hyperparameters utilizing genetic algorithm[J]. Journal of Zhejiang University:Science A,2021, 22(6):407-426.
[23] PSYLLIDIS A, GAO S, HU Y, et al. Points of Interest(POI):a commentary on the state of the art, challenges,and prospects for the future[J]. Computational Urban Science, 2022, 2(1):20.
[24] CHEN P, FU X, WANG X. A graph convolutional stacked bidirectional unidirectional-LSTM neural network for metro ridership prediction[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(7):6950-6962.
[25] LI K, WANG F, YANG L, et al. Deep feature screening:Feature selection for ultra high-dimensional data via deep neural networks[J]. Neurocomputing, 2023, 538:126186.
[26]邝嘉恒,邬群勇.接驳地铁站的共享单车时空均衡性分析与吸引区域优化[J].地球信息科学学报, 2022, 24(7):1337-1348.KUANG Jiaheng, WU Qunyong. Spatial-temporal equilibrium analysis and attraction area optimization of dockless sharing bicycles connected to subway stations[J].Journal of Geo-Information Science, 2022, 24(7):1337-1348.
[27] YANG F, SHUAI C, QIAN Q, et al. Predictability of short-term passengers’origin and destination demands in urban rail transit[J]. Transportation, 2023, 50(6):2375-2401.
[28] HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Las Vegas:IEEE, 2016:770-778.
[29] KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks[EB/OL].(2016-09-09)[2024-04-02].https://arxiv.org/abs/1609.02907v4.
基本信息:
DOI：10.19961/j.cnki.1672-4747.2024.07.023
中图分类号:U293.13
引用信息:
[1]胡晓伟,吴则洋,卢泓博等.基于遗传算法优化深度神经网络的站点客流预测[J].交通运输工程与信息学报,2025,23(01):72-84.DOI:10.19961/j.cnki.1672-4747.2024.07.023.
基金信息:
国家自然科学基金项目（52272332）; 黑龙江省自然科学基金项目（YQ2021E031）; 中央高校基本科研业务费专项资金项目（HIT.OCEF.2022026）