Date of Award

Fall 2023

Document Type


Degree Name

Doctor of Philosophy (PhD)


Mechanical & Aerospace Engineering


Mechanical Engineering

Committee Director

Stacie I. Ringleb

Committee Member

Sebastian Y. Bawab

Committee Member

Hunter J. Bennett

Committee Member

Gene J. W. Hou


Inactive adults often have decreased musculoskeletal health and increased risk factors for chronic diseases. However, there is limited data linking biomechanical measurements of generally healthy young adults to their physical activity levels assessed through questionnaires. Commonly used data collection methods in biomechanics for assessing musculoskeletal health include but are not limited to muscle quality (measured as echo intensity when using ultrasound), isokinetic (i.e., dynamic) muscle strength, muscle activations, and functional movement assessments using motion capture systems. These assessments can be time consuming for both data collection and processing. Therefore, understanding if all biomechanical assessments are necessary to classify the activity level of an individual is critical. The aims of the study were to determine the relationships between biomechanical measurements used in ascertaining skeletal muscular health using statistical methods, to determine if various machine learning techniques can distinguish between low to moderately active and highly active asymptomatic young adults, and if processing data using machine learning can decrease the number of measurements needed to differentiate between activity levels. The results showed that fundamental statistics alone could not establish connections to all biomechanical variables. Upon employing machine learning, the Support Vector Machine algorithm met minimum performance metrics and was the only method able to differentiate between minimally and highly active adults. Feature reduction was performed, aiming to minimize the number of required biomechanical measurements. The Support Vector Machine algorithm proved successful performance when applied to the reduced set of necessary biomechanical variables, reducing features from 15 to 11. The feature reduction allowed for the elimination of both muscle activity and strength measurements, eliminating the need for two pieces of equipment in the data collection process yields reduced data collection and processing time. Future work would transition these methods into a clinical setting to inform clinicians and educate patients about the impact of inactivity on their musculoskeletal health.


In Copyright. URI: This Item is protected by copyright and/or related rights. You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s).