Date of Award

Spring 2023

Document Type

Thesis

Terms of Use

© 2023 Youssef Kharrat. This work is freely available courtesy of the author. It may be used under the terms of the Creative Commons Attribution 4.0 International (CC BY 4.0) license. For all other uses, please contact the copyright holder.

Creative Commons License

Creative Commons Attribution 4.0 International License
This work is licensed under a Creative Commons Attribution 4.0 International License.

Degree Name

Bachelor of Arts

Department

Engineering

First Advisor

Maggie Delano

Abstract

This project introduces a classification model whose purpose is the distinction between the two possible movements done by the bicep; namely flexion and rotation. Surface EMG data was collected using the MIKROE-2621. It was later sampled from Analog to Digital by a Nucleo 401-RE board at 200 Hz. To generate the dataset, I connected the apparatus to my arm and performed the movements a total number of 300 times. This data was later analyzed and a choice of features were made that eventually was fed into MATLAB Classification Learner. A Support Vector Machine performed best and was able to classify the movements at a 94.3 % accuracy rate. This report shows the different techniques used to analyze the data and how I developed an understanding of the principal components that govern this classification using statistical methods.

Included in

Engineering Commons

Share

COinS