Title:
Human Movement Analysis
Poster
Preview Converted Images may contain errors
Abstract
Certain movement disorders and neurological conditions can cause abnormal movements and altered gait/posture. More than 10 million Americans are affected by some type of movement disorder, including 7 million who are affected by Essential Tremor and 1 million that are affected by Parkinson’s Disease. The aim of our project was to develop foundational ML models that could be adapted/ built upon by subsequent teams to develop machine learning algorithms that can accurately analyze human movements for use in patient rehabilitation; Specifically, to identify and aid in the correction of movement disorders such as Parkinson’s Disease and Essential Tremor. In terms of a measure of success for our project, our MOV stated that our project will be successful if our ML algorithms could identify biomechanical deficits in real-time and achieve an F1 score greater than 0.61 for the given categorization, making an improvement on previous iterations of similar projects done by our sponsor and paving the way for a model that will allow physical therapists to more easily diagnose and rehabilitate movement disorders.
In addition to working with posture data (good vs. bad), we extended our approach to a pitching experiment. This experiment collects biomechanical data to identify pitching performance and mechanics. By integrating both the posture dataset and the pitching data, our solution demonstrates versatility for not only clinical rehabilitation but also sports performance applications.
Authors
First Name |
Last Name |
James
|
Tyler
|
Trevor
|
DeMarco
|
Joseph
|
Blair
|
Aidan
|
Mahoney
|
Leave a comment
Submission Details
Conference URC
Event Interdisciplinary Science and Engineering (ISE)
Department Computer Science (ISE)
Group Data Science
Added April 22, 2025, 7:34 p.m.
Updated April 22, 2025, 7:35 p.m.
See More Department Presentations Here