GRABMyoFlow: Forearm and Wrist sEMG Extension of GRABMyo with Dynamic Gestures

Provider
Ehlert, Tung and Pradhan (PhysioNet)
License
CC-BY-4.0 (source)
Stored at
Amazon S3, s3://physionet-open/grabmyo-flow (us-east-1)
Access
Free and public. No account with the data provider is needed.
DOI
10.13026/ah52-zq51
Category
Physiology
Source
https://doi.org/10.13026/ah52-zq51

About GRABMyoFlow: Forearm and Wrist sEMG Extension of GRABMyo with Dynamic Gestures

GRABMyoFlow extends the Gesture Recognition and Biometrics ElectroMyogram (GRABMyo) dataset of surface electromyography (sEMG) for hand gesture recognition (HGR) and EMG biometric authentication, released by Ehlert, Tung and Pradhan. It adds wrist-only static gesture recordings from 20 newly recruited healthy adults, mapped to subject indices 44 to 63 so the combined wrist set covers 63 participants, and a dynamic trial at the end of each session that captures natural transitions between hand poses (hold gesture A, transition, hold gesture B) for continuous authentication and gesture-event segmentation. Signals have 16 channels sampled at 2048 Hz, 12 of them bipolar wrist channels in two electrode rings, across three sessions. Measured 2026-11-13 (version 1.0.0): static_extension_WFDB/ and dynamic_WFDB/ each hold session1 to session3 folders with one folder per participant; dynamic_WFDB/session1/session1_participant1 holds 120 objects, .dat/.hea WFDB pairs such as session1_participant1_gesture10_trial1.dat (655,360 bytes). The root has subject-info.csv, MotionSeq.txt, gesture images, MATLAB feature extraction scripts and Python WFDB-to-MAT converters. Read records with the wfdb Python package (wfdb.rdrecord). Licensed CC BY 4.0; cite Ehlert et al., doi 10.13026/ah52-zq51, and the original GRABMyo.

How to access this dataset in Python

import boto3
from botocore import UNSIGNED
from botocore.client import Config
s3 = boto3.client('s3', region_name='us-east-1', config=Config(signature_version=UNSIGNED))
s3.list_objects_v2(Bucket='physionet-open', Prefix='grabmyo-flow/', Delimiter='/')

Lists the files with anonymous access. Runs on any machine, with no cloud account.

Data structure

Files

Example file: grabmyo-flow/1.0.0/dynamic_WFDB/session1/session1_participant1/session1_participant1_gesture10_trial1.dat

Analyze this dataset without downloading it

On Scigantic, GRABMyoFlow: Forearm and Wrist sEMG Extension of GRABMyo with Dynamic Gestures opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.

This page is also available as Markdown and as JSON.

Related Physiology datasets