Mining Spatial and Spatial-Temporal Patterns Linking Daily Mobility with Health Status Using GPS-EMA Coupled Data

Authors: Diep Dao*, University of Colorado - Colorado Springs, Michelle Barris, University of Colorado - Colorado Springs, Craig Ravesloot, Director, RTC:Rural, Lillie Greiman, Research Associate, RTC:Rural, Tannis Hargrove, Research Associate, RTC:Rural
Topics: Geographic Information Science and Systems
Keywords: Spatial Data Mining, Human Dynamics, GPS-EMA coupled data
Session Type: Paper
Day: 4/13/2018
Start / End Time: 3:20 PM / 5:00 PM
Room: Bayside B, Sheraton, 4th Floor
Presentation File: No File Uploaded

GPS-based daily location tracking coupled with ecological momentary assessment (EMA) survey technique built on a mobile communication platform provides an excellent tool for collecting spatial temporal rich data in support for behavior insight analyses linking mobility and health. This study makes use of such a dataset collected on a group of 94 participants living in Missoula, Montana over a period of 14 days. The objective is to examine different data mining techniques, such as association rule mining and sequential pattern mining, to link daily travel mobility and health status. Socio-demographic background and long-term health status of participants are available for the study. Their GPS or Wi-Fi -based location was record every 5 minutes. EMA self-reporting on physical and psychological health status such as pain, stress, fatigue level rating from 1 to 10 was recorded every two hours.

Abstract Information

This abstract is already part of a session. View the session here.

To access contact information login