Multiple Classification Techniques Toward a Robust and Reliable P300 Bci System

Abstract

A brain–computer interface (BCI) can be used for people with severe physical disabilities such as ALS or amyotrophic lateral sclerosis. BCI can allow these individuals to communicate again by creating a new communication channel directly from the brain to an output device. BCI technology can allow paralyzed people to share their intent with others, and thereby demonstrate that direct communication from the brain to the external world is possible and that it might serve useful functions. BCI systems include machine learning algorithms (MLAs). Their performance depends on the feature extraction and classification techniques employed. In this paper, we propose a system to exploit the P300 signal in the brain, a positive deflection in event-related potentials. The P300 signal can be incorporated into a spelling device. There are two benefits behind this kind of research. First of all, this work presents the research status and the advantages of communication via a BCI system, especially the P300 BCI system for disordered people, and the related literature review is presented. Secondly, the paper discusses the performance of different machine learning algorithms. Two different datasets are presented: the first dataset 2004 and the second dataset 2019. A preprocessing step is introduced to the subjects in both datasets first to extract the important features before applying the proposed machine learning methods: linear discriminant analysis (LDA I and LDA II), support vector machine (SVM I, SVM II, SVM III, and SVM IV), linear regression (LREG), Bayesian linear discriminant analysis (BLDA), and twin support vector machine (TSVM). By comparing the performance of the different machine learning systems, in the first dataset it is found that BLDA and SVMIV classifiers yield the highest performance for both subjects “A” and “B”. BLDA yields 98% and 66% for 15th and 5th sequences, respectively, whereas SVMIV yields 98% and 54.4% for 15th and 5th sequences, respectively. While in the second dataset, it is obvious that BLDA classifier yields the highest performance for both subjects “1” and “2”, it achieves 90.115%. The paper summarizes the P300 BCI system for the two introduced datasets. It discusses the proposed system, compares the classification methods performances, and considers some aspects for the future work to be handled. The results show high accuracy and less computational time which makes the system more applicable for online applications.

Sistema domótico controlado a través de una interfaz cerebro-ordenador

“…El objetivo ha sido utilizar únicamente las opciones estándar del software UMA-BCI Spellery, por tanto, BCI2000tal y como lo haría un usuario sin conocimientos técnicos. Una vez validada la propuesta de sistema domótico en estas condiciones, futuros trabajos pueden añadir cambios para mejorar el rendimiento, como aplicar un método de eliminación o corrección de artefactos, modificar el número de estímulos o la forma de presentarlos (por ejemplo, utilizando el paradigma del checkerboard (Townsend et al, 2010)), aplicar técnicas alternativas para mejorar la precisión del clasificador (Labib et al, 2020) o reducir el tiempo de calibración (Jin, Li, et al, 2020). También es importante considerar un diseño de la BCI centrado en las capacidades del usuario, con la opción de emplear otras modalidades sensoriales además de la visual, como la auditiva o incluso la táctil (p.…”

Brain-computer interface (BCI)-generated speech to control domotic devices

“…The aim was to use only the standard options of the used BCI software (UMA-BCI Speller and, therefore, BCI2000), as would be done by a user without extensive technical knowledge. Once the home automation system proposal has been validated under these conditions, new changes can be added to improve performance, such as adding an artifact removal/correction method, modifying the number of stimuli or the way they are presented (e.g., using the checkerboard paradigm [35]) or applying alternative techniques to improve the classifier accuracy [44] or reducing the calibration time [45]. It is also important to consider a BCI design focused on the user's capabilities, with the option of employing other sensory modalities in addition to visual, such as auditory or even tactile (e.g., [46,47]).…”