Biostatistics Weekly Seminar

Unlocking the Actome: Characterizing Human Activity and Behavior Patterns Using Smartphone Sensor Data

Julian Wolfson, PhD
University of Minnesota

Modern technology has given us tools to accurately measure a wide variety of biomarkers, from genetic sequences to high-resolution scans to immunochemistry. However, methods for quantifying human activity and behavior patterns still often rely on blunter data collection instruments such as time use diaries, which are burdensome to study participants and prone to recall bias. In this talk, I will summarize my involvement in a project aimed at modernizing the way we capture human activity and behavior data by collecting and processing smartphone sensor data. I will discuss my participation in several "non-traditional" activities for an academic biostatistician, including developing a smartphone application, applying for a patent, and co-founding a startup company (Daynamica). I will then describe ongoing methodological work focused on questions such as: 1) How do we define activity and behavior patterns, and identify sets of individuals with similar patterns? 2) How do we predict future activity and behavior patterns? 3) How can we combine individual- and population-level data to make inference about individual patterns? and 4) How can activity and behavior data be combined with data from other sources to yield insights into human health?

MRBIII, Room 1220
15 May 2019

Speaker Itinerary

Topic revision: r3 - 30 Apr 2019, SrKrueger

This site is powered by FoswikiCopyright © 2013-2017 by the contributing authors. All material on this collaboration platform is the property of the contributing authors.
Ideas, requests, problems regarding Vanderbilt Biostatistics Wiki? Send feedback