Prediction of Fatigue in Lower Extremity using EMG Sensor and Machine Learning

It appears your Web browser is not configured to display PDF files. Download adobe Acrobat or click here to download the PDF file.

Click here to download the PDF file.

Creator: 

Golmohammadishouraki, Mahdokht

Date: 

2022

Abstract: 

Predicting fatigue in lower extremity significantly improves the stroke patient's recovery by increasing the duration of exercise while encouraging the patients to participate in the rehabilitation. Prediction of fatigue onset, and even quantifying the fatigue level could be utilized in assistive controllers in rehabilitation robots to elongate the sessions. In this research, the fatigue onset prediction and fatigue level recognition were studied on healthy subjects performing squat motions while using an exergame. Different analysis methods where investigated based on the collected data in a developed procedure. The phasing analysis method was developed by analyzing each squat phase. The appropriate muscle activity values were extracted from the data and combined for further classification and regression analysis. The classification analysis goal was to create a model for detecting the onset of fatigue, whereas the regression analysis would predict the fatigue level. Random forest performed best in both analyses.

Subject: 

Engineering - Mechanical
Engineering - Biomedical
Robotics

Language: 

English

Publisher: 

Carleton University

Thesis Degree Name: 

Master of Applied Science: 
M.App.Sc.

Thesis Degree Level: 

Master's

Thesis Degree Discipline: 

Engineering, Mechanical

Parent Collection: 

Theses and Dissertations

Items in CURVE are protected by copyright, with all rights reserved, unless otherwise indicated. They are made available with permission from the author(s).