Bayesian Determination to Communication Patterns in Brain Structures for Brain-Computer Interfaces using K2 Learning Algorithm

Research areas:

• Volume 4,Issue 1, July 2015

Year:

2015

Type of Publication:

Article

Keywords:

BCI, Bayesian Networks, Brain, EEG

Authors:

Tláloc Daniel Espinoza Huerta; Guillermo Alfonso De La Torre-Gea; Gabriela García-Manzo; Juan Nicolás De La Vega-Flatow; Sandra L. Martínez-Alcaráz; Rosa María Quijada-López; Claudia Soraya Rodríguez-Reyes; Luis Guillermo Almeida-Montes

Journal:

IJAIM

Volume:

4

Number:

1

Pages:

8-12

Month:

July

Abstract:

For the development of Brain-Computer Interfaces, is necessary to create communication models between brain structures. Determining patterns in the communication of brain structures is difficult due to the complexity of their anatomy and function. The Bayesian Networks are uncertain numerical techniques that can be used to study this problem. We obtained 20 sets of experimental data from Electroencephalograms applied to different people under the same basal conditions. The data set were discretized and used to develop a Bayesian network model that describes the relationships between the structures studied for different signal frequencies. The model shows differences that allow us to identify the degree of dependence of variables and quantify their inference as well as quantifying the degree of influence between them.

Full text: IJAIM_458_Final.pdf