Author Date


Degree Name



Mechanical Engineering


Ira A. Fulton College of Engineering

Defense Date


Publication Date


First Faculty Advisor

Dr. David Fullwood

First Faculty Reader

Dr. Anton Bowden

Honors Coordinator

Dr. Brian D. Jensen


Strain Gauges, Sensors, Biomechanics, Machine Learning


Tracking spinal motion in the lower back serves as a useful tool for aiding diagnostics. This study seeks to determine if a fabric garment with integrated strain sensors may provide sufficient information to identify key spinal motion characteristics typically manifested in skin strain. Sensors adhered directly to an individual’s skin would be the most effective means of capturing such characteristics. However, adhering sensors to skin of the lower back is difficult for frequent or everyday application. This research aims to integrate a sensor system into a more comfortable and readily user-applied device. Here we examine the implementation of such a device, along with the optimal placement for strain gauges on a fabric garment to capture key characteristics in a differentiable way.

Leveraging a professional motion capture lab, motion data was collected at both the skin and garment surface positions, and analyzed using machine learning techniques. The optimality of each sensor position and orientation was based on how much information it provided to the best performing models. Our analysis utilized the ability of ML models to discriminate between various motion types as an indicator of information gained. Models were given strain data from markers adhered to skin and a proposed garment designed for measuring lower back motion. Findings from both models were like those in existing literature, in that more sensors typically resulted in better performing models (Baker et al., 2023; Gibbons, McMullin, et al., 2021). A set of reasonable strain gauge positions and orientations were obtained from modeling and can be applied to future versions of the tested garment.