Brain-Computer Interface Controlled Functional Electrical Stimulation: Evaluation With Healthy Subjects and Spinal Cord Injury Patients

Abstract

This work involved human subjects or animals in its research. Approval of all ethical and experimental procedures and protocols was granted by the Research and Ethical Committees of the National Institute of Rehabilitation ''LGII'' under Application No. 08/19, and performed in line with the Declaration of Helsinki.

Decoding EEG rhythms offline and online during motor imagery for standing and sitting based on a brain-computer interface

“…Hence, cross-validation was necessary to evaluate the classification performance of the machine learning models in the offline phase. By contrast, in the online phase, the classification of multiple sliding windows per trial addressed the problem of single-trial misclassification and false positives in order to evaluate the online classification performance of the models (Mendoza-Montoya, 2017;Delijorge et al, 2020;Hernandez-Rojas et al, 2022).…”

“…The following exclusion criteria were applied to identify and discard noisy epochs: (i) Maximum peakto-peak value V pp e greater than 200 µV; (ii) Standard deviation amplitude σ e greater than 50 µV; and (iii) Noise to signal ratio P norm e greater than 0.7. These criteria may indicate if the subject is blinking, the amplifier is saturated, the electrodes are not making good contact with the scalp, or there are some muscle artifacts, as suggested in Mendoza-Montoya (2017), Delijorge et al (2020), andHernandez-Rojas et al (2022). Finally, any epoch where at least one electrode met these criteria was visually inspected to rule out noise-contaminated trials (as a double check) and labeled as an "artifact" manually.…”

STIMGRASP: A Home-Based Functional Electrical Stimulator for Grasp Restoration in Daily Activities

“…BCI technologies offer a direct way to synchronize cortical commands and movements generated by FES, which can be advantageous for inducing neuroplasticity and has gained much attention. However, despite last year’s efforts, BCI systems have not yet reached everyday applications due to their complexity [ 7 , 21 , 22 , 23 , 24 , 25 ].…”

“…Systems that target the final user commonly apply interfaces in the equipment, such as displays, potentiometers, and buttons, or alternatively may use position sensors and myoelectric signals (EMG) to initiate the movements whose parameters are already preconfigured, as mentioned before [ 8 , 14 , 16 , 18 , 19 , 20 ]. Recent advances have also shown the use of brain–machine interfaces (BCI) as user intention in FES systems [ 7 , 21 , 22 , 23 , 24 , 25 ]. However, the two neuroprostheses available on the market that are currently known use wireless communication (Bioness—radio frequency and ReGrasp—Bluetooth), buttons on the control unit (both), and head movements from one earpiece (ReGrasp).…”

A comparative analysis of masking empirical mode decomposition and a neural network with feed-forward and back propagation along with masking empirical mode decomposition to improve the classification performance for a reliable brain-computer interface

“…However, because motor imagery signal's spatial resolution and SNR will be very low, but the higher dynamic characteristics have a low spatial resolution, a low signal-to-noise ratio (SNR), and highly dynamic characteristics, extracting the crucial features will be a critical step in creating a brain-computer interface system (Schirrmeister et al, 2017). The main activity of classifying EEG signals is to analyze brain dynamics, which is a difficult undertaking due to these difficulties and the existence of enormous levels of noise in the data (Hernandez-Rojas et al, 2022;Hwaidi and Chen, 2022).…”