Date on Master's Thesis/Doctoral Dissertation
5-2018
Document Type
Doctoral Dissertation
Degree Name
Ph. D.
Department
Electrical and Computer Engineering
Degree Program
Electrical Engineering, PhD
Committee Chair
Welch, Karla
Committee Co-Chair (if applicable)
Rejc, Enrico
Committee Member
Rejc, Enrico
Committee Member
Naber, John
Committee Member
Zurada, Jacek
Author's Keywords
machine learning; wavelets; sensorimotor; disuse; emg
Abstract
Electrophysiological measurements have been used in recent history to classify instantaneous physiological configurations, e.g., hand gestures. This work investigates the feasibility of working with changes in physiological configurations over time (i.e., longitudinally) using a variety of algorithms from the machine learning domain. We demonstrate a high degree of classification accuracy for a binary classification problem derived from electromyography measurements before and after a 35-day bedrest. The problem difficulty is increased with a more dynamic experiment testing for changes in astronaut sensorimotor performance by taking electromyography and force plate measurements before, during, and after a jump from a small platform. A LASSO regularization is performed to observe changes in relationship between electromyography features and force plate outcomes. SVM classifiers are employed to correctly identify the times at which these experiments are performed, which is important as these indicate a trajectory of adaptation.
Recommended Citation
Stallard, Robert Warren, "Longitudinal tracking of physiological state with electromyographic signals." (2018). Electronic Theses and Dissertations. Paper 2980.
https://doi.org/10.18297/etd/2980
Included in
Bioelectrical and Neuroengineering Commons, Biomechanics Commons, Biomedical Commons, Longitudinal Data Analysis and Time Series Commons, Motor Control Commons, Multivariate Analysis Commons, Signal Processing Commons, Statistical Models Commons, Systems and Integrative Engineering Commons, Systems Neuroscience Commons
