Static Fatigue Detection in Office Syndrome Using Semg and Machine Learning

Name: Parama Pratummas

ThaSH: Machine learning -- Research

ThaSH: Office Syndrome -- Data processing -- Research

Abstract: There are many people around the world getting illness from their workplace as a result of the office syndrome. The purpose of this study is to present the detection system that can identify the fatigue status as in the static position. One subject was recorded surface electromyography (sEMG) on the shoulder while working in the office in a sitting position. The information from the EMG sensor board linked to the surface electrodes was passed to the NodeMCU V2 ESP8266 and then sent to the Arduino IDE. The recorded samples were initially labeled as non-fatigue, but if the individual felt fatigue, they were reclassified as fatigue. These datasets were manipulated and prepared for data analysis by creating seven features (mean, integrated EMG, mean absolute value, mean absolute value1, mean absolute value2, simple square integral, and root mean square). By recursive feature elimination, these seven features were grouped into three: original dataset, feature set I (mean, integrated EMG, mean absolute value, simple square integral, and root mean square), and feature set II (integrated EMG, mean absolute value2, and simple square integral), and then put into six machine learning models (Logistic Regression, Support Vector Machine, Naive Bayes, k-nearest Neighbors, Decision Tree, and Multi-layer Perceptron) to compare the accuracy and performance. As a result, Multi-layer Perceptron was found to have the highest accuracy at 99.6690 percent with a fit time of 18.322849 seconds. Nevertheless, decision tree might be the machine learning model of choice in this research due to its nearly accuracy of 99.2482 percent and faster fit time at 0.027955 seconds

มหาวิทยาลัยธุรกิจบัณฑิตย์. ศูนย์เรียนรู้และหอสมุด.

Address: กรุงเทพมหานคร

Email: library@dpu.ac.th

Name: Chaiyaporn Khemapatapan

Role: Thematic Paper Advisor

Modified: 2567-05-08

Created: 2021

Issued: 2024-04-29

วิทยานิพนธ์/Thesis

application/pdf

eng

Level: Master of Engineering

Descipline: Computer Engineering

Grantor: Dhurakij Pundit University

©copyrights Dhurakij Pundit University

ลำดับที่.	ชื่อแฟ้มข้อมูล	ขนาดแฟ้มข้อมูล	จำนวนเข้าถึง	วัน-เวลาเข้าถึงล่าสุด
1	Parama.Prat.pdf	3.66 MB	13	2026-07-26 22:44:25

ใช้เวลา

0.335915 วินาที