Research and Development

Research

My research focuses on Spatial Big Data, spatial network databases, and scalable algorithms for large-scale spatial networks.

Research Overview

My research is broadly in the area of Spatial Big Data (SBD). Examples of SBD include temporally detailed road maps that provide speeds every minute for every road segment, GPS trace data from cell phones, and engine measurements of fuel consumption and greenhouse gas emissions. Spatial Big Data has the potential to transform society through next-generation routing services, emergency and disaster response, and the discovery of useful patterns embedded in large datasets. However, SBD poses significant challenges because the size, variety, and update rate of mobile datasets exceed the capacity of commonly used spatial computing and spatial database technologies. My research focuses on three key areas:

  • Storage and management of large-scale spatio-temporal network (STN) data.
  • Scalable algorithms and query processing for large spatial networks.
  • AI-driven query processing and spatial data analysis.

Research Projects

NIH: In-Vehicle Sensors to Detect Cognitive Change in Older Drivers

Co-PI: KwangSoo Yang and Ruth Tappen
Funding Agency: National Institutes of Health
Funding: $6,130,807
Period: 2020–2024

NSF CAREER: Spatial Network Database Approach for Emergency Management Information Systems

Funding Agency: National Science Foundation
Award Number: 1844565
Funding: $500,011
Period: 2019–2025

Development of a Traffic Map Evaluation Tool for TMC Applications

Co-PI with Dr. Stevanovic
Funding Agency: Florida Department of Transportation
Funding: $243,706
Period: 2017–2018

Spatial Network Database Approach for Emergency Management Information Systems

Emergency Management Information Systems (EMIS) are increasingly important tools for understanding, managing, and governing transportation-related systems, as well as for testing the stability and vulnerability of these systems against interference. Recently, EMIS have benefited from volunteer geographic information (VGI) and crowdsourcing as powerful methods of collecting user-generated datasets. However, these data sources are challenging because of their very large size, variety, and update rates. Developing fundamental data processing components for advanced queries that deliver critical information during emergencies is important. This research focuses on three interrelated domains:

  • Evacuation route planning
  • Resource assignment
  • Transportation resilience

Spatial Big Data Approaches to Transportation Resilience

Transportation resilience refers to the capability of transportation networks to prepare for, respond to, and recover from significant multi-hazard threats while minimizing damage to public safety, the economy, and security. To increase resilience against potential threats, transportation systems must effectively utilize spatial datasets, including:

  • Locations of hazard areas.
  • Locations of shelters and resources.
  • Transportation network information.
  • Emergency response information.
  • Volunteer geographic information and crowdsourced data.

My research aims to address these challenges by developing scalable Spatial Big Data approaches for transportation network datasets to support timely emergency information and response.


Network Voronoi Diagram and Resource Allocation Problem

Disaster response requires effective allocation of limited resources, including gas stations, shelters, hospitals, and emergency facilities. One important challenge is defining service areas for these facilities while considering their capacity constraints. People naturally tend to visit their nearest service centers, even when other facilities have available capacity. This can cause overloading and inefficient resource utilization. Our research investigates computational techniques for capacity-constrained network service areas and resource allocation.


Presentation Slides

Scroll to Top