Geospatial Big Data Analytics

Permanent URI for this collectionhttps://hdl.handle.net/10125/107543

Browse

Recent Submissions

Now showing 1 - 5 of 5
  • Thumbnail Image
    Item type: Item ,
    Geospatial Network Analysis of US Megaregions in 40 Years
    (2024-01-03) Thongmak, Pawornwan; Xiao, Yinshuang; Gavino, Phillip; Zhang, Ming; Sha, Zhenghui
    This paper proposes a network analysis framework based on geographic information systems (GIS) to study the development of megaregions in support of urban planning and policy making. The framework includes a new approach to modeling geo-shaped polygon data of cesus places as the Place Geo-Adjacency Network (PGAN). In particular, the integration of descriptive network analysis and degree distribution analysis supports the study of spatial connections, geospatial growth, hub effects, and expansion patterns in megaregions. To demonstrate this framework, a case study was conducted on four US megaregions to study their growth and expansion in the last 40 years since 1980. The degree distribution analysis captures the small-world property and quantifies the level of geospatial connectivity influenced by the hub effects. Policymakers can use the model as a decision support for urban planning and policy design to reduce disparities and improve connectivity in megaregion areas.
  • Thumbnail Image
    Item type: Item ,
    A Framework for Destination Uniqueness Identification through Concept Modeling of Tourist-generated Travel Photos
    (2024-01-03) Nguyen, Thuc; Vu, Huy Quan; Cybulski, Jacob L.; Nguyen, Lemai
    In the ever-changing tourism industry, destinations face the difficult task of defining their distinct identity to attract tourists in a highly competitive market. The advent of digital technology has not only revolutionized how content is created and shared, but it has also given tourists the power to influence how a destination is perceived. This study introduces the Destination Uniqueness Identification Framework (DUIF) leveraging concept modeling to analyze geotagged travel photos shared by travelers. DUIF aims to identify both common and unique travel experiences within a country and its cities from tourists’ perspectives. The proposed framework was validated through a case study of Australia, successfully pinpointing unique themes such as Sydney's light festivals and Melbourne's graffiti streets. This study provides valuable insights into the behaviors and preferences of tourists, which contribute to the existing literature on tourism research and offer useful information for destination marketers seeking to develop targeted marketing strategies.
  • Thumbnail Image
    Item type: Item ,
    Geospatial Imputation of Urban Mobility Data with Self-Supervised Learning
    (2024-01-03) Han, Bin; Howe, Bill
    Missing values in urban data can be caused by sensor or software failures, data quality issues, interference from weather events, incomplete data collection, or varying data use regulations; any missing data can render the entire dataset unusable for downstream applications. In our work, we adapt image inpainting techniques to impute large, irregular missing regions in urban settings characterized by temporal dependency and spatial skew. To incorporate temporal information, we adapt computer vision techniques for image inpainting to operate on 3D histograms (2D space + 1D time) commonly used for data exchange in urban settings. To combat spatial skew of urban data --- small dense regions surrounded by large sparse areas, we 1) train simultaneously in space and time, and 2) focus attention on dense regions by biasing the masks used for training to the dense resgions in the data. We evaluate the core model and these two extensions using the NYC taxi data and the NYC bikeshare data, simulating different conditions for missing data. We show that the core model is effective qualitatively and quantitatively, that biased masking during training reduces error, and that the number of timesteps during learning exhibits a tradeoff between model performance and resolution of transient events.
  • Thumbnail Image
    Item type: Item ,
    Conducting Trade Area Analysis Using Mobile Data: The Case of Michigan’s Super-Regional Shopping Centres
    (2024-01-03) Azmy, Ali; Aversa, Joe; Hernandez, Tony
    The increasing availability of spatial big data has revolutionized data analytics and provided valuable insights into consumer behaviour. Spatial big data has enabled retailers to optimize product assortment, pricing, site selection, and trade area analysis. Mobile location data has further enhanced the analysis of individual consumer mobility patterns, offering a more detailed understanding of movement in various contexts. However, using mobile location data for trade area analysis in retail remains understudied. This study aims to fill this gap by employing advanced methods of trade area analysis using mobile location data. Two research questions guide the study: 1) How effective is mobile location data in modelling shopping centre trade area activity? and 2) How reliable are the derived metrics in reflecting changes in trade area consumer traffic patterns during and after the global COVID-19 pandemic? By addressing these questions, this study enhances our understanding of the potential of mobile location data for trade area analysis in retail. It provides insights into consumer behaviour dynamics during the pandemic.
  • Thumbnail Image
    Item type: Item ,