Spectrogram of Surface EMG Data obtained from Myo Armband

Published: 19 August 2022| Version 2 | DOI: 10.17632/xz38kw7m3d.2
Contributors:
Praahas Amin, Airani Mohammad Khan

Description

The Data consists of the spectrogram of electromyography signals for 1 user. The user performed 5 hand gestures. i.e. Point, Middle Finger Extension, Closed Fist, Pinch, and Rest. The data is acquired using a Thalmic Labs Myo Armband, which has a sampling frequency of 200Hz. The participants were made to hold a gesture for 5s and relax for 3s. 6 gesture samples were acquired in one session. 12 such sessions were conducted for each gesture for each user. This gives us 72 samples for each gesture. The spectrogram was computed for each processing window. The spectrogram information can be used for the classification of hand gestures. The gesture classes are point(0), middle finger extension (1), closed-grip (2), pinch (3), rest (4). This data set can be used for gesture recognition problems.

Files

Steps to reproduce

1. Wear a Thalmic Labs Myo armband on the forearm. 2. Interface the Myo Armband with a laptop using a Bluetooth dongle 3. Record EMG Sessions - hold gesture for 5s and relax for 3 seconds. 4. In one session collect 6 samples and not more to avoid the effect of fatigue. 5. Repeat 12 sessions for one gesture. 6. Repeat all steps for any gesture. 7. Compute Spectrogram of every processing window

Institutions

Mangalore University

Categories

Machine Learning, Electromyography, Medical Image Processing, Deep Learning

Licence