Search

In this work, hip and knee angles were decoded from low frequency EEG components recorded during the execution of two tasks. In order to compare their performance, three decoders based on multiple linear regression (MLR) models were applied under different conditions; which consisted in considering the processed data as a whole or divided into segments. Results suggest that, when the segments are related to specific tasks, the segmentation provides a better performance than applying the decoding method to unsegmented data.

One of the most interesting brain machine interface (BMI) applications, is the control of assistive devices for rehabilitation of neuromotor pathologies. This means that assistive devices (prostheses, orthoses, or exoskeletons) are able to detect user motion intention, by the acquisition and interpretation of electroencephalographic (EEG) signals. Such interpretation is based on the time, frequency or space features of the EEG signals. For this reason, in this paper a coherence-based EEG study is proposed during locomotion that along with the graph theory allows to establish spatio-temporal parameters that are characteristic in this study. The results show that along with the temporal features of the signal it is possible to find spatial patterns in order to classify motion tasks of interest. In this manner, the connectivity analysis alongside graphs provides reliable information about the spatio-temporal characteristics of the neural activity, showing a dynamic pattern in the connectivity during locomotions tasks. [ABSTRACT FROM AUTHOR]