Dataset for multi-channel surface electromyography (sEMG) signals of hand gestures
This dataset contains electromyography (EMG) signals for use in human-computer interaction studies. The dataset includes 4-channel surface EMG data from 30 participants with an equal gender distribution. The gestures in the data are rest, extension, flexion, ulnar deviation, radial deviation, punch, and open hand. Data were collected from 4 forearm muscles when simulating 7 unique hand gestures and recorded with the Biopac MP36 device using Ag/AgCl surface bipolar electrodes. Each participant's data contains five repetitive cycles of seven hand gestures. A survey was applied to the participants before the signal recording process. This data can be utilized for recognition, classification, and prediction studies in order to develop EMG-based hand movement controller systems. The dataset can also be useful as a reference to create an artificial intelligence model (especially a deep learning model) to detect gesture-related EMG signals.
Steps to reproduce
A survey was done to choose proper individuals for data collection and collect background information about participant's signals before the signal recording. EMG signals were acquired from a 4-channel MP36 model Biopac device (Biopac Co., USA). MP36 Data Acquisition Unit includes 4 certified human-safe input channels and built-in amplifiers and uses BSL 4 software. In the data collection stage, SS2LB electrode lead sets with smart and simple sensors connectors, and non-invasive 3M brand foam monitoring Ag/AgCl surface electrodes (3.3x3.99 cm size) with disposable and highly adhesive were used. Before electrodes were attached to the forearm, skin surface is cleaned by alcohol to remove dead cells and oils. The approximate locations of four forearm muscles were determined, and then Biopac system electrode gel (GEL1) was applied to the skin. The sensors were calibrated when the electrodes were placed on the participant. The procedure slide was begun with recording simultaneously.