Residents' travel heterogeneity and urban mobility structure

doi:10.11947/j.AGCS.2023.20210368

Abstract

Abstract: The urban mobility structure could produce dynamic changes in the process of residents' travel. Discovering urban mobility structure has become a hot issue in urban geography and traffic geography, which is of great significance for urban planning and management, line allocation, traffic estimation, etc. Traditional urban structure discovery methods usually consider a single factor, and lack of research in considering the heterogeneity of residents' travel. Based on the auto-encoder model, this paper proposes a representational learning method considering the heterogeneity of residents' travel to detect the urban mobility structure. Our method realizes the fusion of static attribute information and dynamic travel information and introduces the multivariate Gaussian distribution model to complete the whole process from node expression to community expression considering the residents' travel heterogeneity between different communities, finally can achieve more accurate representational results. The experimental results show that the proposed method can more accurately discover the urban mobility structure and the residents' travel patterns. Compared with the traditional methods, it is proved that this method has unique advantages in the mining of residents' travel behavior.

Key words: urban mobility structure, resident travel, heterogeneity, representational learning, smart card data

CLC Number:

P227

DUAN Xiaoqi, ZHANG Tong, TIAN Youliang, LIU Peilin, WAN Qiao, QIN Yongbin. Residents' travel heterogeneity and urban mobility structure[J]. Acta Geodaetica et Cartographica Sinica, 2023, 52(1): 155-166.

References

[1] 深圳市交通运输局, 2020年12月交通统计信息[M].深圳:[s.n.],2020. Shenzhen Municipal Bureau of Transport.Traffic statistics for December 2020[M]. Shenzhen:[s.n.],2020.
[2] LONG Ying, SHEN Zhenjiang. Finding public transportation community structure based on large-scale smart card records in Beijing[M]//Geo Journal Library.Cham:Springer International Publishing, 2015: 155-167.
[3] MAEDA T N, MORI J, HAYASHI I, et al. Comparative examination of network clustering methods for extracting community structures of a city from public transportation smart card data[J]. IEEE Access, 2019, 7: 53377-53391.
[4] 顾朝林, 甄峰, 张京祥. 集聚与扩散: 城市空间结构新论[M]. 南京:东南大学出版社, 2000. GU Chaolin, ZHEN Feng, Zhang Jingxiang. Agglomeration and diffusion: a new theory of urban spatial structure[M].Nanjing:Southeast University Press, 2000.
[5] 高琦丽. 大数据驱动的城市活动空间动态研究[D]. 武汉: 武汉大学, 2019. GAO Qili. Big data-driven analysis on urban activity space dynamics[D].Wuhan: Wuhan University, 2019.
[6] 于斌斌, 郭东. 城市群空间结构的经济效率:理论与实证[J]. 经济问题探索, 2021(7): 148-164. YU Binbin, GUO Dong. Economic efficiency of spatial structure of urban agglomeration: theory and empiric[J]. Inquiry into Economic Issues, 2021(7): 148-164.
[7] LIU Xi, GONG Li, GONG Yongxi, et al. Revealing travel patterns and city structure with taxi trip data[J]. Journal of Transport Geography, 2015, 43: 78-90.
[8] 郑燕巧, 焦世泰, 张晓奇. 城市结构对轨道交通系统与房地产价格关系的影响: 以北京、杭州、南京、成都4个城市为例[J]. 经济地理, 2019, 39(6): 75-85. ZHENG Yanqiao, JIAO Shitai, ZHANG Xiaoqi. Impact of urban structure on subway system and real estate price: evidence from Beijing, Hangzhou, Nanjing and Chengdu[J]. Economic Geography, 2019, 39(6): 75-85.
[9] 宋雪涛, 蒲英霞, 刘大伟, 等. 利用行人轨迹挖掘城市区域功能属性[J]. 测绘学报, 2015, 44(S1): 82-88. SONG Xuetao, PU Yingxia, LIU Dawei, et al. Mining urban functional areas using pedestrians' movement trajectories[J]. Acta Geodaetica et Cartographica Sinica, 2015, 44(S1): 82-88.
[10] HILLMAN M, HENDERSON I, WHALLEY A. Transport realities and planning policy[J]. Political and Economic Planning, 1976, 42(567): 196-202.
[11] SONG C, QU Z, BLUMM N, et al. Limits of predictability in human mobility[J]. Science, 2010, 327(5968): 1018-1021.
[12] 曹劲舟. 大数据驱动的个体出行模式与城市空间结构交互研究[J]. 测绘学报, 2021, 50(6): 849.DOI: 10.11947/j.AGCS.2021.20200287. CAO Jinzhou. Big data-driven research on the interaction of human mobility pattern and urban spatial structure[J]. Acta Geodaetica et Cartographica Sinica, 2021, 50(6): 849.DOI: 10.11947/j.AGCS.2021.20200287.
[13] NEWMAN M E, GIRVAN M. Finding and evaluating community structure in networks[J]. Physical Review E, Statistical, Nonlinear, and Soft Matter Physics, 2004, 69(2): 026113.
[14] VON LUXBURG U. A tutorial on spectral clustering[J]. Statistics and Computing, 2007, 17(4): 395-416.
[15] RADICCHI F, CASTELLANO C, CECCONI F, et al. Defining and identifying communities in networks[J]. Proceedings of the National Academy of Sciences of the United States of America, 2004, 101(9):2658-2663.
[16] NEWMAN M E. Modularity and community structure in networks[J]. Proceedings of the National Academy of Sciences of the United States of America, 2006, 103(23): 8577-8582.
[17] ROSVALL M, BERGSTROM C T. Maps of random walks on complex networks reveal community structure[J]. Proceedings of the National Academy of Sciences of the United States of America, 2008, 105(4): 1118-1123.
[18] AIROLDI E M, BLEI D M, FIENBERG S E, et al. Mixed membership stochastic blockmodels[J]. Journal of Machine Learning Research, 2008, 9: 1981-2014.
[19] 李欣. 大城市多中心静态结构和动态关联特征分析[J]. 地理科学, 2021, 41(6): 1061-1068. LI Xin. Static structure and dynamic correlation characteristics of polycentric structure in big city[J]. Scientia Geographica Sinica, 2021, 41(6): 1061-1068.
[20] 张小东, 韩昊英, 唐拥军, 等. 基于百度迁徙数据的中国城市网络结构特征研究[J]. 地球信息科学学报, 2021, 23(10): 1798-1808. ZHANG Xiaodong, HAN Haoying, TANG Yongjun, et al. Research on the characteristics of urban network structure in China based on Baidu migration data[J]. Journal of Geo-Information Science, 2021, 23(10): 1798-1808.
[21] 李智轩, 甄峰, 曹钟茗, 等. 人流视角下城市空间结构特征及规划与治理响应: 以南京市为例[J]. 城市发展研究, 2021, 28(6): 58-65. LI Zhixuan, ZHEN Feng, CAO Zhongming, et al. Characters of urban spatial structure and the response from planning and governance in the perspective of human mobility: a case study of Nanjing[J]. Urban Development Studies, 2021, 28(6): 58-65.
[22] WANG Hongjian, LI Zhenhui. Region representation learning via mobility flow[C]//Proceedings of 2017 ACM on Conference on Information and Knowledge Management.Singapore:New York,USA: ACM Press, 2017: 237-246.
[23] YUAN N J, ZHENG Yu, XIE Xing, et al. Discovering urban functional zones using latent activity trajectories[J]. IEEE Transactions on Knowledge and Data Engineering, 2015, 27(3): 712-725.
[24] ALHAZZANI M, ALHASOUN F, ALAWWAD Z, et al. Urban attractors: discovering patterns in regions of attraction in cities[J]. PLoS One, 2021, 16(4): e0250204.
[25] CAVALLARI S, ZHENG V W, CAI Hongyun, et al. Learning community embedding with community detection and node embedding on graphs[C]//Proceedings of 2017 ACM on Conference on Information and Knowledge Management.Singapore: ACM Press, 2017.
[26] WANG Jinfeng, ZHANG Tonglin, FU Bojie. A measure of spatial stratified heterogeneity[J]. Ecological Indicators, 2016, 67: 250-256.
[27] MONTERO-ODASSO M, BERGMAN H, BÉLAND F, et al. Identifying mobility heterogeneity in very frail older adults. Are frail people all the same?[J]. Archives of Gerontology and Geriatrics, 2009, 49(2): 272-277.
[28] JIN Cheng, CHENG Jianquan, XU Jing. Using user-generated content to explore the temporal heterogeneity in tourist mobility[J]. Journal of Travel Research, 2018, 57(6): 779-791.
[29] GOYAL P, FERRARA E. Graph embedding techniques, applications, and performance: a survey[J]. Knowledge-Based Systems, 2018, 151: 78-94.
[30] OU Mingdong, CUI Peng, PEI Jian, et al. Asymmetric transitivity preserving graph embedding[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco, CA, USA: ACM Press, 2016: 1105-1114.
[31] ROWEIS S T, SAUL L K. Nonlinear dimensionality reduction by locally linear embedding[J]. Science (New York, N Y), 2000, 290(5500): 2323-2326.
[32] PEROZZI B, AL-RFOU R, SKIENA S. DeepWalk: online learning of social representations[C]//Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining. New York, NY, USA: ACM Press, 2014: 701-710.
[33] GROVER A, LESKOVEC J. Node2vec: scalable feature learning for networks[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco, CA, USA: ACM Press, 2016: 855-864.
[34] WANG Daixin, CUI Peng, ZHU Wenwu. Structural deep network embedding[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.San Francisco, CA, USA: ACM Press, 2016: 1225-1234.
[35] CAO Shaosheng, LU Wei, XU Qiongkai. Deep neural networks for learning graph representations[C]//Proceedings of the 30th AAAI Conference on Artificial Intelligence. New York,NY,USA:ACM Press, 2016: 1145-1152.
[36] ZHANG Tong, LI Yicong, YANG Hui, et al. Identifying primary public transit corridors using multi-source big transit data[J]. International Journal of Geographical Information Science, 2020, 34(6): 1137-1161.
[37] TIBSHIRANI R, WALTHER G, HASTIE T. Estimating the number of clusters in a data set via the gap statistic[J]. Journal of the Royal Statistical Society B, 2001, 63(2): 411-423.
[38] ROUSSEEUW P J. Silhouettes: a graphical aid to the interpretation and validation of cluster analysis[J]. Journal of Computational and Applied Mathematics, 1987, 20: 53-65.
[39] SOBOLEVSKY S, CAMPARI R, BELYI A, et al. General optimization technique for high-quality community detection in complex networks[J]. Physical Review E, Statistical, Nonlinear, and Soft Matter Physics, 2014, 90(1): 012811.
[40] TIAN Fei, GAO Bin, CUI Qing, et al. Learning deep representations for graph clustering[C]//Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence. Québec City, Québec, Canada: ACM Press, 2014: 1293-1299.
[41] KARIMI H, SHETAB-BOUSHEHRI S N, GHADIRIFARAZ B. Sustainable approach to land development opportunities based on both origin-destination matrix and transportation system constraints, case study: central business district of Isfahan, Iran[J]. Sustainable Cities and Society, 2019, 45: 499-507.
[42] JIA Jia, WANG Wang.. The development of intelligent operation method of urban public infrastruc-turedriven by accurate spatio-temporal information[J]. Journal of Geodesy and Geoinformation Science, 2021, 4(2): 27-35.
[43] CHEN Lai, KANG Chaogui, YANG Chao. Understanding citizens' emotion states under the urban livability environment through social media data: a case study of Wuhan[J]. Journal of Geodesy and Geoinformation Science, 2022, 5(2): 49-59.