Please use this identifier to cite or link to this item: http://repositorio.unicamp.br/jspui/handle/REPOSIP/243867
Type: Artigo de periódico
Title: Comparative Analysis Of Strategies For Feature Extraction And Classification In Ssvep Bcis
Author: Carvalho
Sarah N.; Costa
Thiago B. S.; Uribe
Luisa F. S.; Soriano
Diogo C.; Yared
Glauco F. G.; Coradine
Luis C.; Attux
Romis
Abstract: Brain-computer interface (BCI) systems based on electroencephalography have been increasingly used in different contexts, engendering applications from entertainment to rehabilitation in a non-invasive framework. In this study, we perform a comparative analysis of different signal processing techniques for each BCI system stage concerning steady state visually evoked potentials (SSVEP), which includes: (1) feature extraction performed by different spectral methods (bank of filters, Welch's method and the magnitude of the short-time Fourier transform); (2) feature selection by means of an incremental wrapper, a filter using Pearson's method and a cluster measure based on the Davies-Bouldin index, in addition to a scenario with no selection strategy; (3) classification schemes using linear discriminant analysis (LDA), support vector machines (SVM) and extreme learning machines (ELM). The combination of such methodologies leads to a representative and helpful comparative overview of robustness and efficiency of classical strategies, in addition to the characterization of a relatively new classification approach (defined by ELM) applied to the BCI-SSVEP systems. (C) 2015 Elsevier Ltd. All rights reserved.
Subject: Brain-computer Interfaces
Visual-evoked Potentials
Motor Imagery
Frequency
Time
Communication
Country: OXFORD
Editor: ELSEVIER SCI LTD
Citation: Comparative Analysis Of Strategies For Feature Extraction And Classification In Ssvep Bcis. Elsevier Sci Ltd, v. 21, p. 34-42 AUG-2015.
Rights: embargo
Identifier DOI: 10.1016/j.bspc.2015.05.008
Address: http://www.sciencedirect.com/science/article/pii/S1746809415000877
Date Issue: 2015
Appears in Collections:Unicamp - Artigos e Outros Documentos

Files in This Item:
File SizeFormat 
wos_000358627300005.pdf2.48 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.