Data-intensive spatial pattern discovery based on generalized spatial point representations

Gao, Yizhao

Permalink

https://hdl.handle.net/2142/101698 Copy

Description

Title

Data-intensive spatial pattern discovery based on generalized spatial point representations

Author(s)

Gao, Yizhao

Issue Date

2018-07-13

Director of Research (if dissertation) or Advisor (if thesis)

Wang, Shaowen

Doctoral Committee Chair(s)

Wang, Shaowen

Committee Member(s)

• Kwan, Mei-Po
• Li, Bo
• McLafferty, Sara

Department of Study

Geography & Geographic InfoSci

Discipline

Geography

Degree Granting Institution

University of Illinois at Urbana-Champaign

Degree Name

Ph.D.

Degree Level

Dissertation

Keyword(s)

• CyberGIS
• GeoComputation
• Geographic Information Science
• Movement Analysis
• Spatial Analysis and Modeling

Abstract

Geospatial big data consisting of records at the individual level or with fine spatial resolutions, such as geo-referenced social media posts and movement records collected using GPS, provide tremendous opportunities to understand complex geographic phenomena and their space-time dynamics. Such data have been widely used in many real-world applications, such as event detection and population migration analyses. These applications require not only efficient data handling and processing capabilities, but also innovative data models and analytical approaches that satisfy application-specific requirements. The aim of this dissertation research is to establish a suite of innovative methods for analyzing geospatial big data that can be modeled as generalized spatial points while addressing the following key research questions: how to estimate the spatial and spatiotemporal patterns of geographic phenomena from geospatial big data based on spatial point models? How to compare these patterns to gain insights into complex geographic phenomena? How to estimate the computational intensity of the methods? How can cyberGIS be advanced to resolve the computational intensity? Specifically, novel methods are designed in this dissertation research to exploit spatial data characteristics, innovate spatial point pattern analytics, and resolve computational intensity through high-performance spatial algorithms. Such methods are evaluated in the context of several real-world applications, including event detection from social media data and spatial movement pattern detection. Experiment results demonstrated that fine-scale spatial patterns can be revealed from geospatial big data using the proposed approaches. Novel cyberGIS software capabilities are also created as a result of this dissertation research.

Graduation Semester

2018-08

Type of Resource

text

Permalink

http://hdl.handle.net/2142/101698

Copyright and License Information

Copyright 2018 Yizhao Gao

Owning Collections