tomazas / itc2017

Code for paper "Application of Convolutional Neural Networks to Four-Class Motor Imagery Classification Problem"

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

About

"Application of Convolutional Neural Networks to Four-Class Motor Imagery Classification Problem"  
by Tomas Uktveris and Vacius Jusas

DOI: http://dx.doi.org/10.5755/j01.itc.46.2.17528

Requirements:

MATLAB 2016a or later w/ CUDA capable GPU.

Running

  1. Download BCI IV 2008 EEG preprocessed data from: https://github.com/tomazas/icist2015/tree/master/data

  2. Update path in config.m to point to the EEG data on disk

  3. Launch an experiment in MATLAB: run experiment_cnn_xxxx.m

N.B. Some experiments take a long time to complete!

Results

Check ./cnn_results directory.

About

Code for paper "Application of Convolutional Neural Networks to Four-Class Motor Imagery Classification Problem"

License:MIT License


Languages

Language:MATLAB 63.5%Language:C 35.7%Language:C++ 0.8%