Author: Yang Hu1, Mengyue Huang2, Jonathan Cerna3, Rachneet Kaur4, Manuel E Hernandez3,5,6,7,8
Affiliation:
1 Department of Kinesiology, College of Health and Human Science, San José State University, San Jose, CA 95129, USA.
2 School of Information Sciences, University of Illinois Urbana-Champaign, Urbana, IL 61801, USA.
3 Neuroscience Program, University of Illinois Urbana-Champaign, Urbana, IL 61801, USA.
4 Department of Industrial and Enterprise Systems Engineering, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA.
5 Department of Biomedical and Translational Sciences, University of Illinois Urbana-Champaign, Urbana, IL 61801, USA.
6 Department of Bioengineering, University of Illinois Urbana-Champaign, Urbana, IL 61801, USA.
7 Department of Kinesiology and Community Health, University of Illinois Urbana-Champaign, Urbana, IL 61801, USA.
8 Beckman Institute, University of Illinois Urbana-Champaign, Urbana, IL 61801, USA.
Conference/Journal: Sensors (Basel)
Date published: 2024 Jul 31
Other:
Volume ID: 24 , Issue ID: 15 , Pages: 4955 , Special Notes: doi: 10.3390/s24154955. , Word Count: 209
Tai Chi is a Chinese martial art that provides an adaptive and accessible exercise for older adults with varying functional capacity. While Tai Chi is widely recommended for its physical benefits, wider adoption in at-home practice presents challenges for practitioners, as limited feedback may hamper learning. This study examined the feasibility of using a wearable sensor, combined with machine learning (ML) approaches, to automatically and objectively classify Tai Chi expertise. We hypothesized that the combination of wrist acceleration profiles with ML approaches would be able to accurately classify practitioners' Tai Chi expertise levels. Twelve older active Tai Chi practitioners were recruited for this study. The self-reported lifetime practice hours were used to identify subjects in low, medium, or highly experienced groups. Using 15 acceleration-derived features from a wearable sensor during a self-guided Tai Chi movement and 8 ML architectures, we found multiclass classification performance to range from 0.73 to 0.97 in accuracy and F1-score. Based on feature importance analysis, the top three features were found to each result in a 16-19% performance drop in accuracy. These findings suggest that wrist-wearable-based ML models may accurately classify practice-related changes in movement patterns, which may be helpful in quantifying progress in at-home exercises.
Keywords: Parkinson’s disease; machine learning; wearables.
PMID: 39124002 PMCID: PMC11314743 DOI: 10.3390/s24154955
