Eventos Anais de eventos
COBEM 2019
25th International Congress of Mechanical Engineering
DECODING IMAGINARY ELBOW MOVEMENT WITH KALMAN FILTER USING NON-INVASIVE EEG
Submission Author:
Elkin Veslin , RJ
Co-Authors:
Elkin Veslin, Max Suell Dutra, Luiz Bevilacqua, Luciano Santos Constantin Raptopoulos, Waltencir Andrade, Rafael da Silva Figueiredo, Juliana Guimarães Martins Soares
Presenter: Elkin Veslin
doi://10.26678/ABCM.COBEM2019.COB2019-0061
Abstract
In this article, the properties of the Kalman Filter to decode imaginary elbow movement from non-invasive EEG are analyzed. Based on a set of executed movements, an expected interval of movement during imagination is estimated, together, with a set of signal's configuration parameters and trough cross-validation the decoded capabilities are analyzed in order to generalize the model that reduces the estimation error around all the volunteers. We found that selecting the parameters correctly to configure the signals and selecting a homogeneous data set is possible to improve the filter estimation capabilities for imaginary movement.
Keywords
Brain-machine interfaces, Decoding, EEG Signals, Kalman Filter
