Research Repository

Feature selection method based on Menger curvature and LDA theory for a P300 brain–computer interface

Li, Shurui and Jin, Jing and Daly, Ian and Liu, Chang and Cichocki, Andrzej (2022) 'Feature selection method based on Menger curvature and LDA theory for a P300 brain–computer interface.' Journal of Neural Engineering, 18 (6). 066050-066050. ISSN 1741-2560

[img] Text
Feature Selection method based on Menger Curvature and LDA Theory for a P300 Brain-computer Interface.pdf - Accepted Version
Restricted to Repository staff only until 4 January 2023.

Download (1MB) | Request a copy

Abstract

Objective. Brain–computer interface (BCI) systems decode electroencephalogram (EEG) signals to establish a channel for direct interaction between the human brain and the external world without the need for muscle or nerve control. The P300 speller, one of the most widely used BCI applications, presents a selection of characters to the user and performs character recognition by identifying P300 event-related potentials from the EEG. Such P300-based BCI systems can reach good levels of accuracy but are difficult to use in day-to-day life due to redundancy and noisy signal. A room for improvement should be considered. We propose a novel hybrid feature selection method for the P300-based BCI system to address the problem of feature redundancy, which combines the Menger curvature and linear discriminant analysis. Approach. First, selected strategies are applied separately to a given dataset to estimate the gain for application to each feature. Then, each generated value set is ranked in descending order and judged by a predefined criterion to be suitable in classification models. The intersection of the two approaches is then evaluated to identify an optimal feature subset. Main results. The proposed method is evaluated using three public datasets, i.e. BCI Competition III dataset II, brain/neural computer interaction Horizon dataset, and Lausanne Federal Institute of Technology dataset. Experimental results indicate that compared with other typical feature selection and classification methods, our proposed method has better or comparable performance. Significance. Additionally, our proposed method can achieve the best classification accuracy after all epochs in three datasets. In summary, our proposed method provides a new way to enhance the performance of the P300-based BCI speller.

Item Type: Article
Uncontrolled Keywords: brain–computer interface; P300 speller; feature selection; Menger curvature; linear discriminant analysis
Divisions: Faculty of Science and Health > Computer Science and Electronic Engineering, School of
SWORD Depositor: Elements
Depositing User: Elements
Date Deposited: 25 Feb 2022 12:20
Last Modified: 25 Feb 2022 12:20
URI: http://repository.essex.ac.uk/id/eprint/32168

Actions (login required)

View Item View Item