Publication Date
2025
Document Type
Thesis
Committee Members
Tanvi Banerjee, Ph.D. (Advisor); Wen Zhang, Ph.D. (Committee Member); William Lee Romine, Ph.D. (Committee Member)
Degree Name
Master of Science (MS)
Abstract
This study investigates how Iyengar yoga postures influence autonomic nervous system (ANS) activity by analyzing multimodal physiological signals collected via wearable sensors. The physiological mechanisms underlying Iyengar yoga’s therapeutic effects remain under-explored at the granular, pose-level. Using data collected from 16 participants, this research evaluates whether machine learning models can distinguish between baseline, parasympathetic-dominant, and sympathetic-dominant states based on wrist-worn sensor data. The goals were to explore whether subtle postural variations elicit measurable autonomic responses and to identify which sensor features most effectively capture these changes. Participants performed a sequence of yoga poses while wearing synchronized sensors measuring electrodermal activity (EDA), blood volume pulse (BVP), heart rate variability, skin temperature, and motion. Experimental results demonstrated that the physiological states were statistically significant (MANOVA η2 p = 0.889). Interpretable machine learning models were trained to distinguish physiological states and rank feature relevance. Among the evaluated classifiers, Random Forest model outperformed linear baselines, achieving a 94% classification accuracy. Exploratory visualization using t-SNE indicated that while “relaxed” states are distinct, sympathetic and parasympathetic states exhibit high non-linearity, explaining the necessity for ensemble-based approaches. SHAP analysis further identified phasic EDA responses and HRV variability as the most influential features. Overall, these findings provide objective evidence that subtle postural variations in Iyengar yoga evoke measurable and classifiable autonomic responses, offering a foundation for precision-tailored mind-body interventions.
Page Count
66
Department or Program
Department of Computer Science and Engineering
Year Degree Awarded
2025
Copyright
Copyright 2025, all rights reserved. My ETD will be available under the "Fair Use" terms of copyright law.
