Integrating the Eigendecomposition Approach and k-Means Clustering for Inferring Building Functions with Location-Based Social Media Data

Understanding the relationship between human activity patterns and urban spatial structure planning is one of the core research topics in urban planning. Since a building is the basic spatial unit of the urban spatial structure, identifying building function types, according to human activities, is essential but challenging. This study presented a novel approach that integrated the eigendecomposition method and k-means clustering for inferring building function types according to location-based social media data, Tencent User Density (TUD) data. The eigendecomposition approach was used to extract the effective principal components (PCs) to characterize the temporal patterns of human activities at building level. This was combined with k-means clustering for building function identification. The proposed method was applied to the study area of Tianhe district, Guangzhou, one of the largest cities in China. The building inference results were verified through the random sampling of AOI data and street views in Baidu Maps. The accuracy for all building clusters exceeded 83.00%. The results indicated that the eigendecomposition approach is effective for revealing the temporal structure inherent in human activities, and the proposed eigendecomposition-k-means clustering approach is reliable for building function identification based on social media data.

[1]  Wei Tu,et al.  Unravel the landscape and pulses of cycling activities from a dockless bike-sharing system , 2019, Comput. Environ. Urban Syst..

[2]  Li Zhuo,et al.  A Novel Building Type Classification Scheme Based on Integrated LiDAR and High-Resolution Images , 2017, Remote Sensing.

[3]  Yuan Zhang,et al.  Social functional mapping of urban green space using remote sensing and social sensing data , 2018, ISPRS Journal of Photogrammetry and Remote Sensing.

[4]  Thomas Blaschke,et al.  Ontology-Based Classification of Building Types Detected from Airborne Laser Scanning Data , 2014, Remote. Sens..

[5]  Xiaoping Liu,et al.  The varying patterns of rail transit ridership and their relationships with fine-scale built environment factors: Big data analytics from Guangzhou , 2020 .

[6]  Jianguo Wu,et al.  Spatial pattern of urban functions in the Beijing metropolitan region , 2010 .

[7]  Gotthard Meinel,et al.  Automatic identification of building types based on topographic databases – a comparison of different data sources , 2015 .

[8]  Xianda Zhang,et al.  A genetic algorithm with gene rearrangement for K-means clustering , 2009, Pattern Recognit..

[9]  Antoni Domènech,et al.  Identifying the Socio-Spatial Logics of Foreclosed Housing Accumulated by Large Private Landlords in Post-Crisis Catalan Cities , 2020, ISPRS Int. J. Geo Inf..

[10]  Bin Chen,et al.  Dynamic assessment of PM2.5 exposure and health risk using remote sensing and geo-spatial big data. , 2019, Environmental pollution.

[11]  Peng Wu,et al.  Urban Parcel Grouping Method Based on Urban Form and Functional Connectivity Characterisation , 2019, ISPRS Int. J. Geo Inf..

[12]  F. Gao,et al.  Evaluating the performance of LBSM data to estimate the gross domestic product of China at multiple scales: A comparison with NPP-VIIRS nighttime light data , 2021, Journal of Cleaner Production.

[13]  Yu Liu,et al.  Integrating multi-source big data to infer building functions , 2017, Int. J. Geogr. Inf. Sci..

[14]  Shaowen Wang,et al.  Latent spatio-temporal activity structures: a new approach to inferring intra-urban functional regions via social media check-in data , 2016, Geo spatial Inf. Sci..

[15]  Xiaoping Liu,et al.  Delineating urban functional areas with building-level social media data: A dynamic time warping (DTW) distance based k-medoids method , 2017 .

[16]  Qiuping Li,et al.  Identifying Building Functions from the Spatiotemporal Population Density and the Interactions of People among Buildings , 2019, ISPRS Int. J. Geo Inf..

[17]  Guojun Lu,et al.  An Automatic Building Extraction and Regularisation Technique Using LiDAR Point Cloud Data and Orthoimage , 2016, Remote. Sens..

[18]  Shaoying Li,et al.  Understanding the modifiable areal unit problem in dockless bike sharing usage and exploring the interactive effects of built environment factors , 2021, Int. J. Geogr. Inf. Sci..

[19]  Xiaoping Liu,et al.  Spatially varying impacts of built environment factors on rail transit ridership at station level: A case study in Guangzhou, China , 2020 .

[20]  T. Esch,et al.  Urban structure type characterization using hyperspectral remote sensing and height information , 2012 .

[21]  Dieter Pfoser,et al.  Crowdsourcing urban form and function , 2015, Int. J. Geogr. Inf. Sci..

[22]  F. Canters,et al.  Mapping form and function in urban areas: An approach based on urban metrics and continuous impervious surface data , 2011 .

[23]  Seah Hock Soon,et al.  Points of interest recommendation from GPS trajectories , 2015, Int. J. Geogr. Inf. Sci..

[24]  Yao Shen,et al.  Urban function connectivity: Characterisation of functional urban streets with social media check-in data , 2016 .

[25]  Anil K. Jain.  Data clustering: 50 years beyond K-means , 2010, Pattern Recognit. Lett..

[26]  Michael E. Hodgson,et al.  Building type classification using spatial and landscape attributes derived from LiDAR remote sensing data , 2014 .

[27]  Yongxi Gong,et al.  Exploring the spatiotemporal structure of dynamic urban space using metro smart card records , 2017, Comput. Environ. Urban Syst..

[28]  Qingming Zhan,et al.  Urban land use extraction from Very High Resolution remote sensing imagery using a Bayesian network , 2016 .

[29]  Md Zahidul Islam,et al.  A hybrid clustering technique combining a novel genetic algorithm with K-Means , 2014, Knowl. Based Syst..

[30]  Feng Gao,et al.  Spatial Distribution and Mechanism of Urban Occupation Mixture in Guangzhou: An Optimized GeoDetector-Based Index to Compare Individual and Interactive Effects , 2021, ISPRS Int. J. Geo Inf..

[31]  Wei Huang,et al.  Predicting human mobility with activity changes , 2015, Int. J. Geogr. Inf. Sci..

[32]  Kor de Jong,et al.  A method to analyse neighbourhood characteristics of land use patterns , 2004, Comput. Environ. Urban Syst..

[33]  A. Pentland,et al.  Eigenbehaviors: identifying structure in routine , 2009, Behavioral Ecology and Sociobiology.

[34]  Shaoying Li,et al.  Portraying Citizens' Occupations and Assessing Urban Occupation Mixture with Mobile Phone Data: A Novel Spatiotemporal Analytical Framework , 2021, ISPRS Int. J. Geo Inf..

[35]  Yu Liu,et al.  Inferring trip purposes and uncovering travel patterns from taxi trajectory data , 2016 .

[36]  Wei Chen,et al.  Urban Building Type Mapping Using Geospatial Data: A Case Study of Beijing, China , 2020, Remote. Sens..

[37]  Wei Tu,et al.  Coupling mobile phone and social media data: a new approach to understanding urban functions and diurnal patterns , 2017, Int. J. Geogr. Inf. Sci..

[38]  Shaoying Li,et al.  How Is Urban Greenness Spatially Associated with Dockless Bike Sharing Usage on Weekdays, Weekends, and Holidays? , 2021, ISPRS Int. J. Geo Inf..

[39]  Albert-László Barabási,et al.  Limits of Predictability in Human Mobility , 2010, Science.