Simplifying Prediction of Intended Grasp Type: Accelerometry Performs Comparably to Combined EMG-Accelerometry in Individuals With and Without Amputation

Samira Afshari; Rachel V Vitali; Deema Totah

doi:10.3390/s25226984

Back

Simplifying Prediction of Intended Grasp Type: Accelerometry Performs Comparably to Combined EMG-Accelerometry in Individuals With and Without Amputation

Journal article

Open access

Peer reviewed

Simplifying Prediction of Intended Grasp Type: Accelerometry Performs Comparably to Combined EMG-Accelerometry in Individuals With and Without Amputation

Samira Afshari, Rachel V Vitali and Deema Totah

Sensors (Basel, Switzerland), Vol.25(22), 6984

11/15/2025

DOI: 10.3390/s25226984

PMCID: PMC12656353

PMID: 41305191

Files and links (1)

url

https://doi.org/10.3390/s25226984View

Published (Version of record) Open Access

Abstract

The adoption of active upper-limb prostheses with multiple degrees of freedom is largely lagging due to bulky designs and counterintuitive operation. Accurate gesture prediction with minimal sensors is key to enabling low-profile, user-friendly prosthetic devices. Wearable sensors, such as electromyography (EMG) and accelerometry (ACC) sensors, provide valuable signals for identifying patterns relating muscle activity and arm movement to specific gestures. This study investigates which sensor type (EMG or ACC) has the most valuable information to predict hand grasps and identifies the signal features contributing the most to grasp prediction performance. Using an open-source dataset, we trained two types of subject-specific classifiers (LDA & KNN) to predict 10 grasp types in 13 individuals with and 28 individuals without amputation. Having 4-fold cross-validation, LDA average accuracies using ACC only features (84.7%) were similar to combined ACC & EMG (88.3%) and much greater than with only EMG features (58.1%). Feature importance analysis showed that participants with amputation reached more than 80% accuracy using only three features, two of which were ACC-derived, while able-bodied participants required nine features, with greater reliance on EMG. These findings suggest that ACC is sufficient for robust grasp classification in individuals with amputation and can support simpler, more accessible prosthetic designs. Future work should focus on incorporating object and grip force detection alongside grasp recognition and testing model performance in real-time prosthetic control settings.

Artificial Limbs

Accelerometry - methods

Adult

Amputation, Surgical

Electromyography - methods

Female

Hand Strength - physiology

Humans

Male

Middle Aged

Wearable Electronic Devices

Details

Title: Subtitle: Simplifying Prediction of Intended Grasp Type: Accelerometry Performs Comparably to Combined EMG-Accelerometry in Individuals With and Without Amputation
Creators: Samira Afshari - Department of Mechanical Engineering, University of Iowa, Iowa City, IA 52242, USA
Rachel V Vitali - University of Iowa
Deema Totah - University of Iowa
Resource Type: Journal article
Publication Details: Sensors (Basel, Switzerland), Vol.25(22), 6984
DOI: 10.3390/s25226984
PMID: 41305191
PMCID: PMC12656353
NLM abbreviation: Sensors (Basel)
ISSN: 1424-8220
eISSN: 1424-8220
Publisher: MDPI
Grant note: EDP116S210005 / US Department of Education
Language: English
Date published: 11/15/2025
Academic Unit: Roy J. Carver Department of Biomedical Engineering; Mechanical Engineering; Internal Medicine
Record Identifier: 9985035030002771

Metrics

20 Record Views