Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Transfer Learning for Human Activity Recognition Using Representational Analysis of Neural Networks

Transfer Learning for Human Activity Recognition Using Representational Analysis of Neural Networks Human activity recognition (HAR) has increased in recent years due to its applications in mobile health monitoring, activity recognition, and patient rehabilitation. The typical approach is training a HAR classifier offline with known users and then using the same classifier for new users. However, the accuracy for new users can be low with this approach if their activity patterns are different than those in the training data. At the same time, training from scratch for new users is not feasible for mobile applications due to the high computational cost and training time. To address this issue, we propose a HAR transfer learning framework with two components. First, a representational analysis reveals common features that can transfer across users and user-specific features that need to be customized. Using this insight, we transfer the reusable portion of the offline classifier to new users and fine-tune only the rest. Our experiments with five datasets show up to 43% accuracy improvement and 66% training time reduction when compared to the baseline without using transfer learning. Furthermore, measurements on the hardware platform reveal that the power and energy consumption decreased by 43% and 68%, respectively, while achieving the same or higher accuracy as training from scratch. Our code is released for reproducibility.1 http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png ACM Transactions on Computing for Healthcare (HEALTH) Association for Computing Machinery

Transfer Learning for Human Activity Recognition Using Representational Analysis of Neural Networks

Loading next page...
 
/lp/association-for-computing-machinery/transfer-learning-for-human-activity-recognition-using-00kHQ6ri3d

References (71)

Publisher
Association for Computing Machinery
Copyright
Copyright © 2023 Association for Computing Machinery.
ISSN
2691-1957
eISSN
2637-8051
DOI
10.1145/3563948
Publisher site
See Article on Publisher Site

Abstract

Human activity recognition (HAR) has increased in recent years due to its applications in mobile health monitoring, activity recognition, and patient rehabilitation. The typical approach is training a HAR classifier offline with known users and then using the same classifier for new users. However, the accuracy for new users can be low with this approach if their activity patterns are different than those in the training data. At the same time, training from scratch for new users is not feasible for mobile applications due to the high computational cost and training time. To address this issue, we propose a HAR transfer learning framework with two components. First, a representational analysis reveals common features that can transfer across users and user-specific features that need to be customized. Using this insight, we transfer the reusable portion of the offline classifier to new users and fine-tune only the rest. Our experiments with five datasets show up to 43% accuracy improvement and 66% training time reduction when compared to the baseline without using transfer learning. Furthermore, measurements on the hardware platform reveal that the power and energy consumption decreased by 43% and 68%, respectively, while achieving the same or higher accuracy as training from scratch. Our code is released for reproducibility.1

Journal

ACM Transactions on Computing for Healthcare (HEALTH)Association for Computing Machinery

Published: Mar 16, 2023

Keywords: Transfer learning

There are no references for this article.