Published September 20, 2020 | Version 1
Dataset Open

Surface electromyogram (sEMG) dataset recorded from forearm for 9 hand movements and three electrode array positions

  • 1. University of Belgrade - School of Electrical Engineering (UB-ETF)
  • 2. University of Belgrade - School of Electrical Engineering (UB-ETF), Innovation Center at UB-ETF, and Tecnalia Serbia Ltd.

Description

This repository contains raw surface Electromyography signals termed surface Electromyograms (sEMG) recorded with 8 circular surface Ag/AgCl pairs of electrodes placed circumferentially around the forearm of the dominant arm in 10 able-bodied individuals (5 Females and 5 Males). The proposed method for processing sEMG data with subjects' characteristics and protocol can be found in Miljković & Isaković 2021.

For each subject, sEMG was recorded from three recording electrode array positions termed P1, P2, and P3 for 9 hand movements. We provide a compressed .7z folder with 10 sub-folders for each subject named by subject ID (ID1, ID2, ... ID10). Each sub-folder contains 27 .txt data files (for 9 movements × 3 electrode array positions), except for subject  ID7 (there are 24 .txt records, since three records for wrist extension EX in P1, P2, and P3 positions got corrupted in subject ID7). Average size of 10 sub-folders is 167.50 ± 27.02 MB with maximum of 194 MB and minimum of 117 MB.

The subjects performed following hand movements from the reference resting position –relaxation, R (explained in-detail in Miljković & Isaković 2021): (1) spherical power grasp, PS, (2) three finger sphere grasp, 3F, (3) two finger prismatic grasp, PP, (4) wrist flexion, FL, (5) wrist extension, EX, (6) radial deviation, RD, (7) ulnar deviation, UD, and then forearm rotation i.e. (8) pronation, PR, and (9) supination, SU. PS, 3F, PP, FL, EX, RD, UD, PR, and SU correspond to type of hand movement in naming convention for .txt data files.

Hand movements YoutTube playlist contains explanatory videos for 9 hand movements recorded in this study, and we also provide corresponding .wmv here in the "movies hand movements.7z". Naming convention for .wmv files is type of hand movement with both full name and abbreviation for the movement (for example "radialDeviation-RD.wmv").

Naming convention for .txt data files within 10 sub-folders is: subjects ID _ type of hand movement _ recording electrode array position (for example: "ID1_3F_P1.txt" in sub-folder ID1, "ID9_RD_P3.txt" in sub-folder ID9).

Dataset contents

  1. EMG dataset.7z, 267 .txt data files, text format
  2. movies hand movements.7z, 9 .wmv files, explanatory hand movement videos (also available on YouTube)
  3. README.txt, metadata for data files, text format

Data files contain numerical values with decimal point* according to the following structure

  1. column - CH1** (recorded samples from channel 1)
  2. column - CH2** (recorded samples from channel 2)
  3. column - CH3** (recorded samples from channel 3)
  4. column - CH4** (recorded samples from channel 4)
  5. column - CH5** (recorded samples from channel 5)
  6. column - CH6** (recorded samples from channel 6)
  7. column - CH7** (recorded samples from channel 7)
  8. column - CH8** (recorded samples from channel 8)

* For subjects ID1 and ID2 three decimal places are provided, while for other subjects 6 decimal places in .txt data files are provided.

** Each data file contains at least 10 repetitions of the corresponding movement. In cases where file contains >10 repetitions (overall 162 .txt data files), we used the first or the last ten for the analysis (except for two files where short and strong artifact appeared during the measurement procedure, and corresponding movement repetitions were discarded) presented in Miljković & Isaković 2021.

Sample rate was set at 1000 Hz and A/D card had 16 bits resolution. Gain of the amplifier was set at 1000. For more in-detail explanations of electrode array assemble and positioning for sEMG channels CH1, CH2, ... CH8, please refer to Miljković & Isaković 2021.

If you find these signals useful for your own research or teaching class, please cite both relevant preprint and dataset as:

  1. Miljković, N. and Isaković, M.S., 2021. Effect of the sEMG electrode (re) placement and feature set size on the hand movement recognition. Biomedical signal processing and control, 64:102292. 10.1016/j.bspc.2020.102292

  2. Miljković, N. and Isaković, M.S., 2020. Surface electromyogram (sEMG) dataset recorded from forearm for 9 hand movements and three electrode array positions. [Data set]. Zenodo 10.5281/zenodo.4039550.

ACKNOWLEDGEMENTS (from Miljković & Isaković 2021): "Special appreciation the authors owe to Professor Mirjana B. Popović from the University of Belgrade for her kind support,precious guidance, and advice regarding this research which significantly improved the manuscript. Also, the authors would like to thank Dr Matija Štrbac from Tecnalia Serbia Ltd. for providing advice throughout the study.The authors thank all volunteers for their participation."

Files

README.txt

Files (334.8 MB)

Name Size Download all
md5:c577384488e7fd0d7f7916485c87d72b
315.6 MB Download
md5:b326d40cf265d1f19a14e034ee97296f
19.2 MB Download
md5:d22fe9bdc536cee8f4695d4bfe54301c
773 Bytes Preview Download

Additional details

Funding

Effects of assistive systems in neurorehabilitation: recovery of sensory-motor functions 175016
Ministry of Education, Science and Technological Development
Energy efficiency Improvement of Hydro and Thermal power plants in EPS by development and implementation of power electronics based regulation and automation equipment 33020
Ministry of Education, Science and Technological Development