Evaluation of LSTM for predicting grip strength using electromyography: a comparison of setups and methods

Despite decades of research in prosthetics and myocontrol, using electromyography (EMG) to accurately predict the force a user grasps an object with is still a subject of investigation. Although the problem seems trivial, the optimal EMG setup, able to deliver high prediction accuracy at a minimal e...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Neural computing & applications Jg. 37; H. 21; S. 16461 - 16485
Hauptverfasser: Anam, Khairul, Sudrajat, Ahmad, Rizal, Naufal Ainur, Intyanto, Gramandha Wega, Muldayani, Wahyu, Negara, Mohamad Agung Prawira, Sumardi, Bukhori, Saiful, Gitakarma, Made Santo, Castellini, Claudio
Format: Journal Article
Sprache:Englisch
Veröffentlicht: London Springer London 01.07.2025
Springer Nature B.V
Schlagworte:
Accuracy
Artificial Intelligence
Computational Biology/Bioinformatics
Computational Science and Engineering
Computer Science
Data Mining and Knowledge Discovery
Deep learning
Electromyography
Grip strength
Image Processing and Computer Vision
Methods
Muscle function
Neural networks
Original Article
Pattern recognition systems
Probability and Statistics in Computer Science
Prostheses
Real time
Regression analysis
Sensors
Support vector machines
Time series
Stacked autoencoder
Attention mechanism
LSTM
Grip strength prediction
ISSN:0941-0643, 1433-3058
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Despite decades of research in prosthetics and myocontrol, using electromyography (EMG) to accurately predict the force a user grasps an object with is still a subject of investigation. Although the problem seems trivial, the optimal EMG setup, able to deliver high prediction accuracy at a minimal economic and computational cost needs to be found. In this work, we compare several EMG setups consisting of one to eight sensors and deep learning methods to find out which combination is most convenient. In particular, we compare long short-term memory (LSTM), together with a stacked autoencoder (LSTM–SAE) and an attention mechanism (LSTMATT). Our experimental results reveal that, while the best performance is attained by LSTM–SAE (coefficient of correlation 0.9867 ± 0.0087 , coefficient of determination 0.9676 ± 0.0489 , normalized root mean square error 0.048 ± 0.0213 ), statistically significant differences can only be found when the number of sensors is drastically reduced, namely to 2 sensors, in which case, anyway, the performance is still close to optimal and even surpasses state-of-the-art methods. Further research will focus on testing the optimal approach and setup online on amputated users using prosthetic hardware in daily living activities.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0941-0643
1433-3058
DOI:10.1007/s00521-025-11337-9