Low cost implementation of a Motor Imagery experiment with BCI system and its use in neurorehabilitation.

Abstract

The application of rehabilitation programs based on videogames with brain-computer interfaces (BCI) allows to provide feedback to the user with the expectation of stimulate the brain plasticity that will restore the motor control. The use of specific mental strategies such as Motor Imagery (MI) in neuroscientific experiments with BCI systems often requires the acquisition of sophisticated interfaces and specialized software for execution, which usually have a high implementation costs. We present a combination of low-cost hardware and open-source software for the implementation of videogame based on virtual reality with MI and its potential use as neurotherapy for stroke patients. Three machine learning algorithms for the BCI signals classification are shown: LDA (Linear Discriminant Analysis) and two Support Vector Machines (SVM) in order to determine which task of MI is being performed by the user in a particular moment of the experiment. All classification algorithms was evaluated in 8 healthy subjects, the average accuracy of the best classifier was 96.7%, which shows that it is possible to carry out serious neuroscientific experiments with MI using low-cost BCI systems and achieve comparable accuracies with more sophisticated and expensive devices.