Analyzing the performance of segmented trajectory reconstruction of lower limb movements from EEG signals with combinations of electrodes, gaps, and delays

Abstract

ObjectiveBrain–machine interfaces have performed continuous trajectory reconstruction of limb movements from brain signals relying on multiple linear regression. Most reported approaches deal with the reconstruction of the entire motion trajectory using a single regression and choosing its parameters arbitrarily. This study proposes the reconstruction of trajectories dividing them on phases and proposing a regression for each phase. The parameters for each regressor were selected according to their influence in the performance of the trajectory reconstruction. MethodsIsotonic flexions and extensions of the hip and knee were segmented in phases and a linear regressor was proposed for each phase. The number of electrodes, gaps, and delays of these regressors were selected using an exhaustive comprehensive search to improve the correlation coefficient, normalized root mean square error, and signal-to-noise ratio of the reconstructed trajectory. ResultsThe most frequent electrodes in the trajectory reconstructions between subjects with good performance were electrodes Fz, C3, C4, Cz, P3, P4, and Pz. The combination of a delay of 3 s with 9 gaps gave better performances in general. ConclusionsIn this study it was appreciated that the electrodes that mainly contribute to the trajectory reconstruction are located around the mid-scalp. Also, it was appreciated that the information of movement in the electrical activity is located around 3 s before the movement. SignificanceThe set of parameters obtained could be helpful to define a limited numbers of electrodes. The delay and number of data samples could also be helpful to establish better experimental setups.