Systematic Evaluation of Feature Extraction and Selection Methods for Noise-Robust EMG-Based Hand Movement Classification

Electromyogram (EMG) signals have been extensively utilized for the control of robotic prosthesis movements. In this context, feature extraction and feature selection play a pivotal role in classifying EMG signals into different intended movements. Although time-domain descriptors, such as mean absolute value, zero crossing, slope sign change, waveform length, and sample entropy, are widely used, their discriminative capacity may be limited under noisy conditions. This study evaluates features extracted from higher-order statistics (HOS), discrete wavelet transform (DWT), wavelet packet decomposition (WPD), and time-domain (TD) descriptors for EMG-based movement classification. In addition, four feature selection techniques are compared: mutual information, ReliefF, mRMR, and Boruta. The experiments were conducted using MLP, KNN, SVM, and RF classifiers, considering both original signals and signals corrupted with Gaussian noise at different SNR levels. The results indicate that cumulant-based features are highly robust in noisy scenarios and that selecting the 25 most relevant features can substantially reduce dimensionality while preserving or improving classification performance.

Authors

Institutions

Publication Details

Journal
Learning and Nonlinear Models
Published
2026-11-20
DOI
https://doi.org/10.21528/lnlm-vol24-no2-art1
Primary Topic
Muscle activation and electromyography studies
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Systematic Evaluation of Feature Extraction and Selection Methods for Noise-Robust EMG-Based Hand Movement Classification

Ricardo Rodrigues Magalhães, Eric F. Schmiele, Rafael Cid dos Santos, Leomar Santos Marques et al.
1 links
Learning and Nonlinear Models
Muscle activation and electromyography studies
article

Systematic Evaluation of Feature Extraction and Selection Methods for Noise-Robust EMG-Based Hand Movement Classification

Ricardo Rodrigues Magalhães, Eric F. Schmiele, Rafael Cid dos Santos, Leomar Santos Marques, Danton Diego Ferreira, Bruno Henrique Groenner Barbosa
article en

Abstract

Electromyogram (EMG) signals have been extensively utilized for the control of robotic prosthesis movements. In this context, feature extraction and feature selection play a pivotal role in classifying EMG signals into different intended movements. Although time-domain descriptors, such as mean absolute value, zero crossing, slope sign change, waveform length, and sample entropy, are widely used, their discriminative capacity may be limited under noisy conditions. This study evaluates features extracted from higher-order statistics (HOS), discrete wavelet transform (DWT), wavelet packet decomposition (WPD), and time-domain (TD) descriptors for EMG-based movement classification. In addition, four feature selection techniques are compared: mutual information, ReliefF, mRMR, and Boruta. The experiments were conducted using MLP, KNN, SVM, and RF classifiers, considering both original signals and signals corrupted with Gaussian noise at different SNR levels. The results indicate that cumulant-based features are highly robust in noisy scenarios and that selecting the 25 most relevant features can substantially reduce dimensionality while preserving or improving classification performance.

Learning and Nonlinear Models
Universidade Federal de Lavras (BR)
Fundação de Amparo à Pesquisa do Estado de São Paulo, Conselho Nacional de Desenvolvimento Científico e Tecnológico, Fundação de Amparo à Pesquisa do Estado de Minas Gerais
Muscle activation and electromyography studies
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon
Systematic Evaluation of Feature Extraction and Selection Methods for Noise-Robust EMG-Based Hand Movement Classification — Ricardo Rodrigues Magalhães, Eric F. Schmiele, et al. · Learning and Nonlinear Models (2026) | TGRS Research Map | TGRS