yannickdaelemans / data_analyses_emg_v1 Goto Github PK

This Python is meant to do some initial data-analysis for a Machine Learning project. The data was taken from: https://archive.ics.uci.edu/ml/datasets/EMG+data+for+gestures. 

In this Python file, I get the data from the file, normalize it, delete data from the 0-class (because there is too many of that), and put it back in the file. 
There will also be some statistics shown in the terminal.

Underneath you can read the READ-ME from the scientists who put together the datasets.


EMG Pattern Database

For recording patterns, we used a MYO Thalmic bracelet worn on a user’s forearm, and a PC with a Bluetooth receiver. The bracelet is equipped with eight sensors equally spaced around the forearm that simultaneously acquire myographic signals. The signals are sent through a Bluetooth interface to a PC. 
We present raw EMG data for 36 subjects while they performed series of static hand gestures.The subject performs two series, each of which consists of six (seven) basic gestures. Each gesture was performed for 3 seconds with a pause of 3 seconds between gestures.


Description of raw_data _*** file
Each file consist of 10 columns:
1) Time - time in ms;
2-9) Channel - eightEMG channels of MYO Thalmic bracelet;
10) Class  –thelabel of gestures: 
0 - unmarked data,
1 - hand at rest, 
2 - hand clenched in a fist, 
3 - wrist flexion,
4 – wrist extension,
5 – radial deviations,
6 - ulnar deviations,
7 - extended palm (the gesture was not performed by all subjects).




Relevant Paper:
Lobov S., Krilova N., Kastalskiy I., Kazantsev V., Makarov V.A. Latent Factors Limiting the Performance of sEMG-Interfaces. Sensors. 2018;18(4):1122. doi: 10.3390/s18041122


Supported by the Ministry of Education and Science of the Russian Federation in the framework of megagrant allocation in accordance with the decree of the government of the Russian Federation №220, project № 14.Y26.31.0022