Decoding Lower-Limbs Kinematics from EEG Signals While Walking with an Exoskeleton

Artificial Intelligence in Neuroscience: Affective Analysis and Health Applications(2022)

Cited 0|Views3
No score
Abstract
Neurorehabilitation has gradually become one of the most hopeful tools in some kind of injuries and diseases during the last decade. Several studies have shown that conscious movement effected by patients with mobility difficulties, assisted by a clinical device such as an exoskeleton, contributes positively to their mobility recovery, shortening the rehabilitation times and improving its results. Besides, other studies have hypothesized that the motor cortex is particularly active during specific phases of gait cycle. In this study, a multilinear regression model has been applied to eight users in order to decode lower limb kinematics from EEG signals, reaching an average similitude between real and decoded trajectories (Pearson Correlation Coefficient) of 0.35 and up to 0.42 after optimizing the model parameters. These results encourage us to undertake a deeper analysis of the multilinear regression model as well as consider other processing approaches to perform the decoding in the future.
More
Translated text
Key words
Decoding, EEG, Lower limb kinematics, Multidimensional linear regression, Neurorehabilitation, Exoskeleton, Gait
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined