TASKED: Transformer-based Adversarial learning for human activity recognition using wearable sensors via Self-KnowledgE Distillation
Abstract
Wearable sensor-based human activity recognition (HAR) has emerged as a principal research area and is utilized in a variety of applications. Recently, deep learning-based methods have achieved significant improvement in the HAR field with the development of human–computer interaction applications. However, most of them are limited to operating in a local neighborhood in the process of a standard convolution neural network, and correlations between different sensors on body positions are ignored. In addition, even though several recent existing works considered the correlations between different sensor positions, they still face significant challenging problems with performance degradation due to large gaps in the distribution of training and test data, and behavioral differences between subjects. In this work, we propose a novel Transformer-based Adversarial learning framework for human activity recognition using wearable sensors via Self-KnowledgE Distillation (TASKED), that accounts for individual sensor orientations and spatial and temporal features. The proposed method is capable of learning cross-domain embedding feature representations from multiple subjects datasets using adversarial learning and the maximum mean discrepancy (MMD) regularization to align the data distribution over multiple domains. In the proposed method, we adopt the teacher-free self-knowledge distillation to improve the stability of the training procedure and the performance of human activity recognition. Experimental results show that TASKED not only outperforms state-of-the-art methods on the four real-world public HAR datasets (alone or combined) but also improves the subject generalization effectively.
Dr. Sungho Suh
Senior Researcher
Human Activity Recognition, Safe and Trusted Human Centric Artificial Intelligence in Future Manufacturing Lines
Prof. Dr. rer. nat. Paul (Pawel) Lukowicz
Professor (W3) “Embedded Intelligence”
Paul Lukowicz is Full Professor of AI at the Technical University of Kaiserslautern in Germany where he is heading the Embedded Intelligence group at DFKI. From 2006 till 2011 he has been full Professor (W3) of Computer Science at the University of Passau. He has also been a senior researcher (“Oberassistent”) at the Electronics Laboratory at the Department of Information Technology and Electrical Engineering of ETH Zurich Paul Lukowicz has MSc. (Dipl. Inf.) and a Ph.D. (Dr. rer nat.) in Computer Science a MSc. in Physics (Dipl. Phys.). His research focus are context aware ubiquitous and wearable systems including sensing, pattern recognition, system architectures, models of large scale self-organized systems, and applications. Paul Lukowicz coordinates the FP7-FET SOCIONICAL projects, is Associate Editor in Chief of IEEE Pervasive Computing Magazine, and has been serving as TPC Chair of a number of international events in the area