The goal of this research study is to develop an AI-based model to detect physical fatigue in healthy young adults. The main questions it aims to answer are: 1. Can muscle, heart, and brain signals be used to predict physical fatigue in real time? 2. How accurately can an AI model detect fatigue based on these signals? Participants will: * Perform moderate to high intensity physical exercises, including static bicycling and dumbbell squats, while wearing non-invasive sensors that measure muscle activity (sEMG), heart rate (HR), and brain activity (EEG). * Before starting the exercises, participants will complete a brief warm-up session that includes stretching and mobility movements. * Each participant undergoes two training sessions, with pre- and post-evaluations of their physical fitness status and static muscle strength.
Study Type
INTERVENTIONAL
Allocation
NA
Purpose
SCREENING
Masking
NONE
Enrollment
30
Participants will complete two fatiguing exercises, including static bicycling and dumbbell squats. During each exercise, surface electromyography (sEMG), electroencephalography (EEG), and heart rate (HR) will be recorded to analyze fatigue levels.
National Taipei University, Master Program in Smart Healthcare Management
New Taipei City, Taiwan
RECRUITINGEEG (Electroencephalography) Alpha, Beta, Delta, and Theta Band Frequency (Hz)
Relative power in the alpha (8 to 12 Hz), beta (12 to 30 Hz), delta (2 to 4 Hz), and theta (4 to 8 Hz) bands extracted from EEG signals recorded during exercise. Alpha power is associated with the onset of physical fatigue and is computed using MATLAB.
Time frame: Two sessions: Day 1 (Cycling session) and Day 2 (Squat session)
sEMG (Surface Electromyography) amplitude (μV) and median frequency (MDF) (Hz)
sEMG (microvolts) recorded from both sides of the quadriceps, hamstrings, tibialis anterior, and gastrocnemius muscles. Signal processing will be performed to compute amplitude and median frequency, assessing neuromuscular activation and fatigue during exercise.
Time frame: Two sessions: Day 1 (Cycling session) and Day 2 (Squat session)
Heart rate (HR) and Heart rate variability (HRV)
Heart rate (HR) and heart rate variability (HRV) are recorded in beats per minute (bpm) throughout cycling and squat sessions. Average and peak heart rates, as well as average heart rate variability (HRV), are used to evaluate physical fatigue and cardiovascular stress.
Time frame: Day 1 (Cycling session) and Day 2 (Squatting session)
Body mass index (BMI)
BMI is recorded by measuring body weight and height
Time frame: Two times: before and after exercise sessions
Static muscle strength (N)
Static muscle strength in Newton of both sides of the quadriceps, hamstrings, tibialis anterior, and gastrocnemius is recorded using a dynamometer
Time frame: Two times: before and after exercise sessions
Borg rate of perceived exertion score (RPE)
RPE scale records physical fatigue level for two exercise sessions
Time frame: Two sessions: Day 1 (Cycling session) and Day 2 (Squat session)
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.