Related Experiment Video
Updated: Nov 17, 2025
09:41
Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping
Published on: April 21, 2023
2.0K
A deep learning-based method for grip strength prediction: Comparison of multilayer perceptron and polynomial
Jaejin Hwang1, Jinwon Lee2, Kyung-Sun Lee3
1Department of Industrial and Systems Engineering, Northern Illinois University, DeKalb, IL, United States of America.
Plos One
|February 11, 2021
Summary
This study used deep learning to predict grip strength, finding that multi-layer perceptron (MLP) regression with all variables accurately estimated individual strength. This method can help prevent workplace injuries.
Area of Science:
- Biomechanics
- Machine Learning
- Ergonomics
Background:
- Grip strength is crucial for upper extremity function and injury prevention.
- Accurate, individual-specific grip strength prediction is needed for ergonomic assessments.
- Current methods may lack precision for on-site, personalized evaluations.
Purpose of the Study:
- To develop and evaluate a deep learning model for predicting maximal grip strength.
- To compare the predictive performance of multi-layer perceptron (MLP) regression against polynomial regression models.
- To identify the optimal set of variables for grip strength prediction.
Main Methods:
- Collected maximal grip strength data from 164 young adults across various postures.
- Utilized demographic, anthropometric, and postural data as input variables.
- Trained and tested MLP regression and polynomial regression models (linear, quadratic, cubic).
Main Results:
- MLP regression demonstrated superior performance compared to polynomial regressions.
- Including all variables (demographic, anthropometric, postural) yielded the best predictive model.
- The optimal MLP model achieved high accuracy (RMSE = 69.01N, R = 0.88, ICC = 0.92).
Conclusions:
- Deep learning, specifically MLP regression, offers a powerful tool for accurate grip strength prediction.
- This approach enables precise, individual-specific, on-site grip strength assessment.
- The findings support the use of MLP for reducing musculoskeletal disorder risks in the workplace.
