Performance variation in motor imagery brain–computer interface: A brief review

Estimation of Brain Connectivity during Motor Imagery Tasks using Noise-Assisted Multivariate Empirical Mode Decomposition

“…Among the 100 MMI database, the subjects for whom the classification results were below 64% using the IIR filter and CWT were rejected. The variation of the performance in the MI tasks has been reported, claiming some target users could not produce distinguishable brain signal during the tasks [33]. In particular, subjects performed poorly had less developed brain network [33].…”

“…classification results using the five filtering algorithms with 6 The chance level in a two class separation is not 50 % but 50 % confidence interval depending on the trial number [ Block diagram of the benchmark test of 6 different frequency filtering algorithms for the estimation of 0 subjects in the Physiobank MMI database, the subjects for whom the classification results were below 64% using NA-MEMD, EEMD, EMD, were rejected. The variation of the performance in the MI tasks has been reported, claiming some target users could not produce distinguishable brain signal during the tasks [33]. In particular, subjects poorly had less developed brain network [33].…”

“…The variation of the performance in the MI tasks has been reported, claiming some target users could not produce distinguishable brain signal during the tasks [33]. In particular, subjects poorly had less developed brain network [33]. performance subjects were discarded for the fair benchmark test of the PDC estimation methods.…”

Classifying BCI signals from novice users with extreme learning machine

“…In addition, it is common that researchers use signals from repository data available on Internet such as BCI competitions I-IV or from expert users. It is well known that a BCI system requires the adaptation of the user to the system, so it is necessary to train the user in order to get good results [15][16][17]. In a MI BCI experiment an accuracy between 80% and 90% is expected after 6-9 training sessions of 20 minutes [18].…”

Evaluación de Métodos de Clasificación para el Reconocimiento de Imaginación de Movimiento en un Paciente con Enfermedad Vascular Cerebral

“…Estos sistemas han sido poco probados para la neurorehabilitación de enfermedades que provocan parálisis parcial o completa del miembro inferior y superior, como es el caso de la enfermedad vascular cerebral (EVC). Se estima que cerca del 30% de los potenciales usuarios de un BCI, basado en IM, no podrán controlar este tipo de sistemas con las metodologías de adquisición, extracción de características y clasificación actuales [4]. Una de las etapas más importantes de un BCI, es la de clasificación, por lo que si se mejora su desempeño para el reconocimiento de la IM, se podría incrementar el número de potenciales usuarios de un BCI enfocado a neurorehabilitación.…”