Analysis of Error Potentials generated by a lower limb exoskeleton feedback in a BMI for gait control.

Brain-machine interfaces (BMIs) based on motor imagery (MI) for controlling lower-limb exoskeletons during the gait have been gaining importance in the rehabilitation field. However, these MI-BMI are not as precise as they should. The detection of error related potentials (ErrP) as a self-tune parameter to prevent wrong commands could be an interesting approach to improve their performance. For this reason, in this investigation ErrP elicited by the movement of a lower-limb exoskeleton against subject's will is analyzed in the time, frequency and time-frequency domain and compared with the cases where the exoskeleton is correctly commanded by motor imagery (MI). The results of the ErrP study indicate that there is statistical significative evidence of a difference between the signals in the erroneous events and the success events. Thus, ErrP could be used to increase the accuracy of BMIs which commands exoskeletons.Clinical Relevance- This investigation has the purpose of improving brain-machine interfaces (BMIs) based on motor imagery (MI) by means of the detection of error potentials. This could promote the adoption of robotic exoskeletons commanded by BMIs in rehabilitation therapies.

Transfer Learning with CNN Models for Brain-Machine Interfaces to command lower-limb exoskeletons: A Solution for Limited Data.

This study evaluates the performance of two convolutional neural networks (CNNs) in a brain-machine interface (BMI) based on motor imagery (MI) by using a small dataset collected from five participants wearing a lower-limb exoskeleton. To address the issue of limited data availability, transfer learning was employed by training models on EEG signals from other subjects and subsequently fine-tuning them to specific users. A combination of common spatial patterns (CSP) and linear discriminant analysis (LDA) was used as a benchmark for comparison. The study's primary aim is to examine the potential of CNNs and transfer learning in the development of an automatic neural classification system for a BMI based on MI to command a lower-limb exoskeleton that can be used by individuals without specialized training.Clinical Relevance- BMI can be used in rehabilitation for patients with motor impairment by using mental simulation of movement to activate robotic exoskeletons. This can promote neural plasticity and aid in recovery.