Related Experiment Video
Updated: Jun 27, 2025
12:51
Evaluation of Commercial-Off-The-Shelf Wrist Wearables to Estimate Stress on Students
Published on: June 16, 2018
7.5K
A dataset for fatigue estimation during shoulder internal and external rotation movements using wearables
Merve Nur Yasar1, Marco Sica2, Brendan O'Flynn3
1Tyndall National Institute, University College Cork, Cork, T12 R5CP, Ireland. merv.nur.yasar@gmail.com.
Scientific Data
|April 27, 2024
Summary
This study presents a comprehensive dataset for assessing shoulder joint fatigue using wearable sensors. The data enables the development of machine learning models for fatigue detection in sports science and rehabilitation.
Area of Science:
- Sports Science
- Rehabilitation Engineering
- Biomechanics
Background:
- Wearable sensors are increasingly utilized in sports science, physical rehabilitation, and industry for monitoring physical fatigue.
- Analyzing wearable sensor data with machine learning can predict fatigue during complex shoulder joint movements.
Purpose of the Study:
- To present a comprehensive dataset collected via wearable sensors during a shoulder fatigue protocol.
- To facilitate the development of fatigue detection and prediction algorithms for shoulder movements.
Main Methods:
- Thirty-four healthy subjects performed dynamic shoulder internal rotation (IR) and external rotation (ER) movements to maximal exertion.
- Data collected included demographics, anthropometrics, maximal voluntary isometric contraction (MVIC) force, surface electromyography (sEMG), inertial measurement unit (IMU), photoplethysmography (PPG), and self-reported fatigue (Borg scale, Karolinska sleepiness scale).
Main Results:
- The dataset provides multi-modal sensor data synchronized with subject performance and self-reported fatigue levels.
- This comprehensive data captures biomechanical and physiological responses during shoulder fatigue induction.
Conclusions:
- The presented dataset is valuable for advancing research in physical fatigue assessment, particularly for shoulder joint movements.
- It supports the development of advanced fatigue detection and prediction algorithms utilizing machine learning and wearable sensor technology.
