Phd Defense by Sungtae An

Primary tabs

Title: Weakly Supervised Deep Learning for Human Activity Recognition   Sungtae An Ph.D. Candidate in Computer Science School of Interactive Computing Georgia Institute of Technology   Date: Wednesday, November 16, 2022 Time: 3:00 PM - 5:00 PM EST Location: TSRB 523A   Committee: Dr. Omer T. Inan (Advisor), School of Electrical and Computer Engineering, Georgia Institute of Technology Dr. James Rehg (Co-advisor), School of Interactive Computing, Georgia Institute of Technology Dr. Thomas Ploetz, School of Interactive Computing, Georgia Institute of Technology Dr. Jon Duke, School of Interactive Computing, Georgia Institute of Technology Dr. Mindy L. Millard-Stafford, School of Biological Sciences, Georgia Institute of Technology Dr. Alessio Medda, Aerospace, Transportation & Advanced Systems Laboratory, Georgia Tech Research Institute   Abstract: Human activity recognition (HAR) using wearable sensors and machine learning algorithms is an emerging capability in domains including but not limited to healthcare and ergometric analysis of populations by providing context to physiological measures from wearable sensors during natural daily living activities. Despite the success of deep supervised models in recent years, obtaining a fully labeled HAR dataset is often challenging due to the high cost and workforce associated with labeling. In this dissertation, I address the challenge with the following contributions. First, I present the bilateral domain adaptation problem in HAR for the first time and propose AdaptNet, a semi-supervised deep translation network. AdaptNet enables information fusion of two different data domains using both unlabeled and labeled data. Next, I present a novel framework, DynaLAP, a semi-supervised variational recurrent neural network with a dynamic prior distribution, to perform activity recognition in fixed routes and protocols. DynaLAP implicitly exploits the information about the environment to enhance HAR in fixed protocols such as military and athletic training with few labeled subject data. Then, I present DualCPC, self-supervised pre-training with the contrastive predictive coding framework using a tri-axial accelerometer signal and corresponding physiological variable measurements such as instantaneous oxygen uptake (VO2) during activities performed. Utilizing the additional physiological variable in training time only, the DualCPC pre-trained model outperformed the baseline models across different numbers of labeled training data available.  Finally, I conclude the dissertation by discussing the potential future work and extensions.  


  • Workflow Status: Published
  • Created By: Tatianna Richardson
  • Created: 11/03/2022
  • Modified By: Tatianna Richardson
  • Modified: 11/03/2022