EEG motor imagery classification using deep learning approaches in naïve BCI users

Cristian D. Guerrero-Mendez, Cristian F. Blanco-Diaz, Andres F. Ruiz-Olaya, Alberto López-Delis, Sebastian Jaramillo-Isaza, Rafhael Milanezi Andrade, Alberto Ferreira De Souza, Denis Delisle-Rodriguez, Anselmo Frizera-Neto, Teodiano F. Bastos-Filho

Producción científica: Contribución a una revistaArtículorevisión exhaustiva

9 Citas (Scopus)

Resumen

Motor Imagery (MI)-Brain Computer-Interfaces (BCI) illiteracy defines that not all subjects can achieve a good performance in MI-BCI systems due to different factors related to the fatigue, substance consumption, concentration, and experience in the use. To reduce the effects of lack of experience in the use of BCI systems (naïve users), this paper presents the implementation of three Deep Learning (DL) methods with the hypothesis that the performance of BCI systems could be improved compared with baseline methods in the evaluation of naïve BCI users. The methods proposed here are based on Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM)/Bidirectional Long Short-Term Memory (BiLSTM), and a combination of CNN and LSTM used for upper limb MI signal discrimination on a dataset of 25 naïve BCI users. The results were compared with three widely used baseline methods based on the Common Spatial Pattern (CSP), Filter Bank Common Spatial Pattern (FBCSP), and Filter Bank Common Spatial-Spectral Pattern (FBCSSP), in different temporal window configurations. As results, the LSTM-BiLSTM-based approach presented the best performance, according to the evaluation metrics of Accuracy, F-score, Recall, Specificity, Precision, and ITR, with a mean performance of 80% (maximum 95%) and ITR of 10 bits/min using a temporal window of 1.5 s. The DL Methods represent a significant increase of 32% compared with the baseline methods (p < 0.05). Thus, with the outcomes of this study, it is expected to increase the controllability, usability, and reliability of the use of robotic devices in naïve BCI users.

Idioma originalInglés estadounidense
Número de artículo045029
PublicaciónBiomedical Physics and Engineering Express
Volumen9
N.º4
DOI
EstadoPublicada - jul. 2023
Publicado de forma externa

Áreas temáticas de ASJC Scopus

  • Enfermería General

Huella

Profundice en los temas de investigación de 'EEG motor imagery classification using deep learning approaches in naïve BCI users'. En conjunto forman una huella única.

Citar esto