Active Learning Methods for Model Personalization in Mobile Health

Miscellaneous Talk
Speaker Name
Benjamin Marlin
Date and Time
-
Location
Bryan Research Room 103
Notes
AI Health Distinguished Lecture
Abstract

In mobile health (mHealth), collecting momentary activity or behavioral state labels often comes at a significantly higher cost or level of user burden than collecting unlabeled data using passive sensing. This observation motivates the idea of attempting to optimize the collection of labeled data to minimize cost or burden when developing personalized models. In this talk, I will present on-going research on the problem of developing active learning methods for use in mobile health that leverage the affordances of this domain while respecting its unique constraints. I will also discuss the need to integrate model personalization and intervention adaptation to support the delivery of just-in-time adaptive interventions (JITAIs).

Host
Duke AI Health