Discovery of Time-Sensitive Thematic Patterns in Urban Functional Areas
LIU Junling1,2, DING Sibo1,2, SUN Huanliang1,2, YU Ge3, XU Jingke1,2
1. School of Computer Science and Engineering, Shenyang Jian-zhu University, Shenyang 110168; 2. Liaoning Provincial Big Data Management and Analysis Laboratory of Urban Construction, Shenyang Jianzhu University, Shenyang 110168; 3. School of Computer Science and Engineering, Northeastern University, Shenyang 110169
摘要 城市空间功能结构分析是城市地理信息领域的一个重要研究方向,正确分析空间功能可合理规划资源及方便居民利用城市空间.因此,文中提出时间敏感的城市功能区主题模式发现模型,用于分析随时间变化的城市动态功能区结构.模型中将城市空间网格化处理为多个空间单元,结合用户访问数据和兴趣点(Point of Interest, POI)数据对空间单元进行嵌入表示.在时间维度上对主题特征向量进行聚类后得到具有差异性的特征分布矩阵,完成时段划分.在空间维度上对具有类似特征分布的相邻区域进行合并,最终得到具有时间敏感性的城市功能主题模式.基于北京市共享单车轨迹数据和百度地图查询数据划分动态功能区,可视化展示功能区划分的合理性,并利用聚类评价指标验证文中模型的有效性.
Abstract:The analysis of urban spatial function structure is a hot research direction in the field of urban geographic information. Correct analysis of spatial function can reasonably plan resources and facilitate residents to utilize urban space. Therefore, a model for discovery of time-sensitive thematic patterns in urban functional areas is proposed to analyze the dynamic urban functional area structure changing with time. In the model, the urban space is gridded into multiple spatial units, and the spatial units are embedded and represented by combining user access data and point of interest data. After clustering the theme feature vectors in the time dimension, the feature distribution matrix with differences is obtained to complete the period division. In the spatial dimension, the adjacent areas with similar feature distribution are merged to obtain a time-sensitive urban function theme model. Based on the shared bicycle trajectory data of Beijing and Baidu map query data, the objective dynamic functional areas are divided, the rationality of functional area division is visualized, and the effectiveness of the proposed model is verified via clustering evaluation measures.
[1] YUAN J, ZHENG Y, XIE X.Discovering Regions of Different Functions in a City Using Human Mobility and POIs // Proc of the 18th ACM SIGKDD International Conference on Knowledge Disco-very and Data Mining. New York, USA: ACM, 2012: 186-194. [2] ZHU J W, TAO C, LIN X, et al. A Multiple Subspaces-Based Model: Interpreting Urban Functional Regions with Big Geospatial Data. International Journal of Geo-Information, 2021, 10(2). DOI: 10.3390/ijgi10020066. [3] QI G D, LI X L, LI S J, et al. Measuring Social Functions of City Regions from Large-Scale Taxi Behaviors // Proc of the IEEE International Conference on Pervasive Computing and Communications Workshops. Washington, USA: IEEE, 2011: 384-388. [4] HU Y F, HAN Y Q.Identification of Urban Functional Areas Based on POI Data: A Case Study of the Guangzhou Economic and Technological Development Zone. Sustainability, 2019, 11(5). DOI: 10.3390/su11051385. [5] GAO S, JANOWICZ K, COUCLELIS H.Extracting Urban Functional Regions from Points of Interest and Human Activities on Location-Based Social Networks. Transactions in GIS, 2017, 21(3): 446-467. [6] WANG S D, LIU Y B, ZHI W, et al. Discovering Urban Functional Polycentricity: A Traffic Flow-Embedded and Topic Modeling-Based Methodology Framework. Sustainability, 2020, 12(5). DOI: 10.3390/su12051897. [7] ZHANG X, SUN G Z, PAN Y G, et al. Students Performance Mo-deling Based on Behavior Pattern. Journal of Ambient Intelligence and Humanized Computing, 2018, 9(5): 1659-1670. [8] HUANG B T, LIU Z G, CHEN J H, et al. Behavior Pattern Clustering in Blockchain Networks. Multimedia Tools and Applications, 2017, 76: 20099-20110. [9] CHOVANAK T, KASSAK O, KOMPAN M, et al. Fast Streaming Behavioural Pattern Mining. New Generation Computing, 2018, 36(4): 365-391. [10] HUSSAIN S M, KANAKAM P, SURYANARAYANA D, et al. Forensics Data Analysis for Behavioral Pattern with Cognitive Predictive Task // Proc of the International Conference on Next Gene-ration Computing Technologies. Berlin, Germany: Springer, 2017: 549-557. [11] SADILEK A, KRUMM J.Far Out: Predicting Long-Term Human Mobility. Proceedings of the AAAI Conference on Artificial Intelligence, 2021, 26(1): 814-820. [12] FURLETTI B, CINTIA P, RENSO C, et al. Inferring Human Activities from GPS Tracks // Proc of the 2nd ACM SIGKDD International Workshop on Urban Computing. New York, USA: ACM, 2013. DOI: 10.1145/2505821.2505830. [13] CAO H C, XU F L, SANKARANARAYANAN J, et al. Ha-bit2vec: Trajectory Semantic Embedding for Living Pattern Recognition in Population. IEEE Transactions on Mobile Computing, 2020, 19(5): 1096-1108. [14] MAITI S, SUBRAMANYAM R B V. Mining Behavioural Patterns from Spatial Data. Engineering Science and Technology(An International Journal), 2019, 22(2): 618-628. [15] XU X Z, LIANG T M, ZHU J, et al. Review of Classical Dimensionality Reduction and Sample Selection Methods for Large-Scale Data Processing. Neurocomputing, 2019, 328: 5-15. [16] YAN J, LIU N, YAN S C, et al. Trace-Oriented Feature Analysis for Large-Scale Text Data Dimension Reduction. IEEE Transactions on Knowledge and Data Engineering, 2011, 23(7): 1103-1117. [17] TAO H Y, WANG K L, ZHUO L, et al. Re-examining Urban Region and Inferring Regional Function Based on Spatial-Temporal Interaction. International Journal of Digital Earth, 2019, 12(3): 293-310. [18] PAPADAKIS E, RESCH B, BLASCHKE T.Composition of Place: Towards a Compositional View of Functional Space. Cartography and Geographic Information Science, 2019, 47(1): 28-45. [19] PAPADAKIS E, GAO S, BARYANNIS G.Fusing Knowledge-Based and Data-Driven Techniques for the Identification of Urban Functional Regions. ISPRS International Journal of Geo-Information, 2019, 8. DOI: 10.3390/ijgi8090385. [20] PARENTE J, PEREIRA M G, TONINI M.Space-Time Clustering Analysis of Wildfires: The Influence of Dataset Characteristics, Fire Prevention Policy Decisions, Weather and Climate. Science of the Total Environment, 2016, 559: 151-165. [21] PACI L, FINAZZI F.Dynamic Model-Based Clustering for Spatio-Temporal Data. Statistics and Computing, 2018, 28: 359-374. [22] MELIKER J R, JACQUEZ G M.Space-Time Clustering of Case-Control Data with Residential Histories: Insights into Empirical Induction Periods, Age-Specific Susceptibility, and Calendar Year-Specific Effects. Stochastic Environmental Research and Risk Assessment, 2007, 21(5): 625-634. [23] ZHANG D Z, LEE K, LEE I.Hierarchical Trajectory Clustering for Spatio-Temporal Periodic Pattern Mining. Expert Systems with Applications, 2018, 92. DOI: 10.1016/j.eswa.2017.09.040. [24] PEREIRA M G, CARAMELO L, OROZCO C V, et al. Space-Time Clustering Analysis Performance of an Aggregated Dataset: The Case of Wildfires in Portugal. Environmental Modelling and Software, 2015, 72: 239-249. [25] 宋泽宇,李旸,李德玉,等.融合标签关系的法律文本多标签分类方法.模式识别与人工智能, 2022, 35(2): 185-192. (SONG Z Y, LI Y, LI D Y, et al. Multi-label Classification of Legal Text with Fusion of Label Relations. Pattern Recognition and Artificial Intelligence, 2022, 35(2): 185-192.) [26] LEYLI-ABADI M, LABIOD L, NADIF M.Denoising Autoencoder as an Effective Dimensionality Reduction and Clustering of Text Data // Proc of the Pacific-Asia Conference on Knowledge Disco-very and Data Mining. Berlin, Germany: Springer, 2017: 801-813. [27] WANG Y S, YAO H X, ZHAO S C.Auto-Encoder Based Dimensionality Reduction. Neurocomputing, 2016, 184: 232-242. [28] 张永,刘浩科,张洁.基于类属特征和实例相关性的多标签分类算法.模式识别与人工智能, 2020, 33(5): 439-448. (ZHANG Y, LIU H K, ZHANG J.Multi-label Classification Algorithm Based on Label-Specific Features and Instance Correlations. Pattern Recognition and Artificial Intelligence, 2020, 33(5): 439-448.)