An Asynchronous P300-Based Brain-Computer Interface Web Browser for Severely Disabled People

Abstract

Abstract-This paper presents an electroencephalographic (EEG) P300-based brain-computer interface (BCI) Internet browser. The system uses the "odd-ball" row-col paradigm for generating the P300 evoked potentials on the scalp of the user, which are immediately processed and translated into web browser commands. There were previous approaches for controlling a BCI web browser. However, to the best of our knowledge, none of them was focused on an assistive context, failing to test their applications with a suitable number of end users. In addition, all of them were synchronous applications, where it was necessary to introduce a "read-mode" command in order to avoid a continuous command selection. Thus, the aim of this study is twofold: (i) to test our web browser with a population of multiple sclerosis (MS) patients in order to assess the usefulness of our proposal to meet their daily communication needs; and (ii) to overcome the aforementioned limitation by adding a threshold that discerns between control and non-control states, allowing the user to calmly read the web page without undesirable selections. The browser was tested with sixteen MS patients and five healthy volunteers. Both quantitative and qualitative metrics were obtained. MS participants reached an average accuracy of 84.14%, whereas 95.75% was achieved by control subjects. Results show that MS patients can successfully control the BCI web browser, improving their personal autonomy.Index Terms-Brain-computer interfaces, P300 event-related potentials, electroencephalography, web browser, multiple sclerosis, asynchronous control.

Controlling a Smartphone with Brain-Computer Interfaces: A Preliminary Study

“…P300 evoked potentials were selected as control signals, due to its exogenous nature and the large amount of commands that can be selected by the user [3,4,13]. These potentials, defined as voltage deflections that appear in parietal and occipital cortex in response to infrequent and significant stimuli about 300 ms after their onset, are elicited using an oddball paradigm [3].…”

“…Whenever the target's row or column is flashed, a P300 potential is produced in the scalp of the user. Therefore, the desired character can be determine by computing the intersection where those potentials were found [3,4,13,14]. In particular, two switchable RCP matrices have been used: (i) navigation matrix, a small one intended to provide efficient navigation; and (ii) keyboard matrix, intended to write texts and fill out forms.…”

“…The signal processing pipeline that has been followed in this study is the most common one in the P300-based BCI literature, which applies: down-sampling to 20 Hz as feature extraction, step-wise (SW) regression (max. of 60 features, p in = 0.1, p out = 0.15) as feature selection, and linear discriminant analysis (LDA) as feature classification [4,[15][16][17][18]. As a result, the likelihood of selecting each matrix command is returned, and the final selected command will be the one that provides the maximum probability (i.e., p sel = max p).…”

“…The facility of these systems to create a communication system between our brains and the environment makes them a suitable alternative to bypass diseases that impairs the neural pathways that control muscles [1][2][3]. For instance, BCIs have been successfully applied with users that suffer from traumatic brain injuries, muscle disorders, ataxia, cerebral palsy, multiple sclerosis, among others [1,2,4]. In order to perform such bypassing, brain signals should be monitored.…”

Estado del Arte en Neurotecnologías para la Asistencia y la Rehabilitación en España: Tecnologías Fundamentales

“…Dentro de las aplicaciones desarrolladas se encuentran: (1) una aplicación de control domótico de los dispositivos presentes en el hogar, tales como TV, DVD, luces, reproductor de música, ventilador, calefacción y teléfono (Corralejo et al, 2014); (2) una aplicación asíncrona de navegación web basada en potenciales evocados P300, que cuenta con todas las funcionalidades típicas de un navegador, incluyendo la navegación a través de hipervínculos, la reproducción de multimedia, la redacción de e-mails y formularios, etcétera (Martínez-Cagigal et al, 2016); y (3) una aplicación de entrenamiento cognitivo orientada a ralentizar las consecuencias del envejecimiento . Con respecto al procesado de señal, el GIB-UVa ha contribuido en el estudio de nuevos clasificadores, tanto en sistemas exógenos basados en potenciales P300 (Martínez-Cagigal et al, 2017), como en sistemas endógenos basados en imaginación motora (NicolasAlonso et al, 2015).…”