周蜀杰;曾园园;江昊;

• 1:武汉大学电子信息学院

摘要(Abstract)：

人群的迁移行为可以通过时空相关轨迹和用户上网行为进行记录。通过分析用户的上网行为分布情况发现，用户在不同场景下的浏览内容具有一定的偏好性，据此构建了融合用户上网行为及迁移行为异构信息网络表征城市人群的转移行为。基于该异构信息网络，提出了一种基于扩张因果卷积的城市客流量预测模型，采用扩张因果卷积模块捕捉客流量分布特征和用户上网行为特征，并构建了异构信息融合模型来融合客流量分布特征与用户上网行为特征。客流量分布特征提取是通过不同时间尺度下时间序列提取客流量时间依赖关系，用户上网行为特征提取是根据2种场景下的用户上网内容。特征提取采用扩张因果卷积减少了模型层数，提高了模型效率。异构信息融合模型融合了多维特征信息，提高了模型在预测有突发事件时的即时客流量的准确率。

关键词(KeyWords)： 客流量预测;扩张因果卷积;人群迁移;上网行为

Abstract:

Keywords:

基金项目(Foundation):

作者(Authors): 周蜀杰;曾园园;江昊;

DOI: 10.14188/j.1671-8844.2023-02-011

参考文献(References)：

• [1] Mitchell T M. Mining our reality[J]. Science, 2009,326(5960):1644-1645.
• [2] Box G E P, Jenkins G M, Reinsel G C, et al. Time Series Analysis:Forecasting and Control[M]. New Jersey:John Wiley&Sons, 2015.
• [3]黄大荣,宋军,汪达成，等.基于ARMA和小波变换的交通流预测模型研究[J].计算机工程与应用,2006,42(36):191-194,224.Huang Darong, Song Jun, Wang Dacheng, et al. Forecasting model of traffic flow based on ARMA and wavelet transform[J]. Computer Engineering and Applications, 2006,42(36):191-194,224.
• [4]张春辉,宋瑞,孙杨.基于卡尔曼滤波的公交站点短时客流预测[J].交通运输系统工程与信息,2011,11(4):154-159.Zhang Chunhui, Song Rui, Sun Yang. Kalman filterbased short-term passenger flow forecasting on bus stop[J]. Journal of Transportation Systems Engineering and Information Technology, 2011, 11(4):154-159.
• [5] Zhao Z, Chen W H, Wu X M, et al. LSTM network:a deep learning approach for short-term traffic forecast[J].IET Intelligent Transport Systems, 2017, 11(2):68-75.
• [6] Zhang J B, Zheng Y, Qi D K, et al. DNN-based prediction model for spatio-temporal data[C]//Proceedings of the 24th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems. New York:ACM,2016:1-4.
• [7] Zhang J B, Zheng Y, Qi D K. Deep spatio-temporal residual networks for citywide crowd flows prediction[J]. Proceedings of the AAAI Conference on Artificial Intelligence. 2017, 31(1):1655-1661.
• [8] Zhang J B, Zheng Y, Sun J K, et al. Flow prediction in spatio-temporal networks based on multitask deep learning[J]. IEEE Transactions on Knowledge and Data Engineering, 2020, 32(3):468-478.
• [9] Lin Z Q, Feng J, Lu Z Y, et al. DeepSTN+:contextaware spatial-temporal neural network for crowd flow prediction in metropolis[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2019, 33(1):1020-1027.
• [10]张仕学，李石君，余伟，等.突发事件人群异常聚集热点区域预测[J].中国安全科学学报，2015,25(9):159-164.Zhang Shixue, Li Shijun, Yu Wei, et al. Prediction on hot region of crowd abnormal gathering on unexpected event[J]. China Safety Science Journal, 2015, 25(9):159-164.
• [11] Borovykh A, Bohte S, Oosterlee C W. Conditional time series forecasting with convolutional neural networks[EB/OL]. 2017:arXiv:1703.04691. https://arxiv.org/abs/1703.04691.
• [12] Yu F, Koltun V. Multi-scale context aggregation by dilated convolutions[EB/OL].2015:arXiv:1511.07122.https://arxiv.org/abs/1511.07122
• [13] Mozaffari M H, Lee W S. BowNet:dilated convolution neural network for ultrasound tongue contour extraction[EB/OL]. 2019:arXiv:1906.04232. https://arxiv.org/abs/1906.04232.
• [14] LeCun Y, Bottou L, Orr G B, et al. Efficient BackProp[M]. Berlin:Lecture Notes in Computer Science, 1998:9-50.
• [15] Guthrie D, Allison B, Liu W, et al. A closer look at skip-gram modelling[C]//Language Resources and Evaluation. Paris:European Language Resources Association, 2006:1222-1225.
• [16] Jiang S, Ferreira J, Gonzalez M C. Activity-based human mobility patterns inferred from mobile phone data:a case study of Singapore[J]. IEEE Transactions on Big Data, 2017, 3(2):208-219.
• [17]江昊,李媛,吴礼华,等.一种基站接入用户数量波动性的对比分析方法[J].武汉大学学报(工学版),2018,51(5):459-464.Jiang Hao, Li Yuan, Wu Lihua, et al. A comparative method of accessed user volatility of base stations[J].Engineering Journal of Wuhan University, 2018, 51(5):459-464.
• [18]吴礼华,王兆俊,池卿华,等.移动互联网中基于用户行为的机会连接预测[J].武汉大学学报(工学版), 2019,52(1):89-94.Wu Lihua,Wang Zhaojun,Chi Qinghua,et al.Opportunistic link prediction based on user behavior in mobile Internet[J]. Engineering Journal of Wuhan University,2019,52(1):89-94.
• [19] Hochreiter S, Schmidhuber J. Long short-term memory[J]. Neural Computation, 1997, 9(8):1735-1780.
• [20]杜永萍,赵晓铮,裴兵兵.基于CNN-LSTM模型的短文本情感分类[J].北京工业大学学报, 2019, 45(7):662-670.Du Yongping, Zhao Xiaozheng, Pei Bingbing. Short text sentiment classification based on CNN-LSTM model[J]. Journal of Beijing University of Technology,2019, 45(7):662-670.