Smoking and Activity Space

Project Summary

Computer Science major Yumin Zhang and IIT student Akhil Kumar Pabbathi spent ten weeks working closely with Dr. Joe McClernon from Psychiatry and Behavioral Sciences to understand smoking and tobacco purchase behavior through activity space analysis.

Themes and Categories
Year
2016

Project Results

The team developed a robust algorithm to extract meaningful features from GPS tracking and subject-indicated smoking and tobacco purchase data, and verified purchases with locations of tobacco retail outlets in Durham County. Yumin and Akhil used clustering techniques and network analysis to compare activity space and length-of-stay behaviors between smokers and non-smokers. Their computational framework has brought valuable insights to the clinical study team and will play an integral role in future studies carried out by Dr. McClernon and colleagues.

Download the Executive Summary (PDF)

Faculty Sponsor

  • Joe McClernon, Associate Professor, Psychiatry and Behavioral Sciences

"Our DATA+ team did wonderful work. I’d wanted a software tool for quantifying human mobility data using network analysis for 5 years—the team got it done in 8 weeks! Paul and Ashlee run a fantastic program that requires minimal oversight on the part of faculty but with maximum returns. Sign me up for next year!" Joe McClernon, Associate Professor, Psychiaty and Behavioral Sciences

Project Manager

  • Tianyuan Liu, UNC-Chapel Hill Transportation Planning and Health Behavior

Participants

  • Yumin Zhang, Duke University Computer Science
  • Pabbathi Akhil Kumar, Duke University Electrical and Computer Engineering

Disciplines Involved

  • Economics
  • Sociology
  • Public Health
  • Psychology
  • All quantitative STEM

Related People

Related Projects

Social and environmental contexts are increasingly recognized as factors that impact health outcomes of patients. This team will have the opportunity to collaborate directly with clinicians and medical data in a real-world setting. They will examine the association between social determinants with risk prediction for hospital admissions, and to assess whether social determinants bias that risk in a systematic way. Applied methods will include machine learning, risk prediction, and assessment of bias. This Data+ project is sponsored by the Forge, Duke's center for actionable data science.

Project Leads: Shelly Rusincovitch, Ricardo Henao, Azalea Kim

Project Manager: Austin Talbot

Aaron Chai (Computer Sciece, Math) and Victoria Worsham (Economics, Math) spent ten weeks building tools to understand characteristics of successful oil and gas licenses in the North Sea. The team used data-scraping, merging, and OCR method to create a dataset containing license information and work obligations, and they also produced ArcGIS visualizations of license and well locations. They had the chance to consult frequently with analytics professionals at ExxonMobil.

Click here to read the Executive Summary

 

Project Lead: Kyle Bradbury

Project Manager: Artem Streltsov

Yueru Li (Math) and Jiacheng Fan (Economics, Finance) spent ten weeks investigating abnormal behavior by companies bidding for oil and gas rights in the Gulf of Mexico. Working with data provided by the Bureau of Ocean Energy Management and ExxonMobil, the team used outlier detection methods to automate the flagging of abnormal behavior, and then used statistical methods to examine various factors that might predict such behavior. They had the chance to consult frequently with analytics professionals at ExxonMobil.

 

Click here to read the Executive Summary

 

Project Lead: Kyle Bradbury

Project Manager: Hyeongyul Roh