EMG Feature Extraction Toolbox (Extended Version)

Grimmer, Martin; Just, Fabian; Zhao, Guoping

Open Access

EMG Feature Extraction Toolbox (Extended Version)

Files

Features.zip (52.22 KB)

Date

2025-12-16

Type

Software

Authors

Grimmer, Martin
Just, Fabian
Zhao, Guoping

Description

This Matlab code includes scripts to determine 58 different features based on EMG signals. In addition, it includes an example script (Example_Calculate_Features.m) to run these scripts and determine all features based on EMG from example data of one stride of walking. The code was used within the article --Electromyography (EMG) based feature selection for detecting movement effort in human-in-the-loop optimization of lower limb exoskeletons-- on two datasets "Transitions of loaded and unloaded walking dataset" (https://doi.org/10.48328/tudatalib-2068) and "Hip exoskeleton walking with different assistance timings dataset" (https://doi.org/10.48328/tudatalib-2066) to verify the efficiency of each feature to extract changes in EMG at different levels of walking effort. Portions of the MATLAB code used to calculate EMG features were originally provided by Jingwei Too (https://github.com/JingweiToo/EMG-Feature-Extraction-Toolbox). We have extended and modified this code to include additional features. Here references from the original work: Too, J.; Abdullah, A.R.; Saad, N.M. Classification of hand movements based on discrete wavelet transform and enhanced feature extraction. Int. J. Adv. Comput. Sci. Appl. 2019, 10. https://doi.org/https://doi.org/10.14569/IJACSA.2019.0100612 Too, J.; Abdullah, A.R.; Mohd Saad, N.; Tee, W. EMG feature selection and classification using a Pbest-guide binary particle swarm optimization. Computation 2019, 7, 12. https://doi.org/https://doi.org/10.3390/computation7010012