PPGINF PÓS-GRADUAÇÃO EM ENGENHARIA DA INFORMAÇÃO FUNDAÇÃO UNIVERSIDADE FEDERAL DO ABC Telefone/Ramal: Não informado http://propg.ufabc.edu.br/ppginfo

Banca de QUALIFICAÇÃO: CAROLINE PIRES ALAVEZ MORAES

Uma banca de QUALIFICAÇÃO de DOUTORADO foi cadastrada pelo programa.
DISCENTE : CAROLINE PIRES ALAVEZ MORAES
DATA : 28/06/2022
HORA: 09:00
LOCAL: https://meet.google.com/ntm-rihb-seo
TÍTULO:

Feature Extraction through IVA: a new approach for BCI applications


PÁGINAS: 50
GRANDE ÁREA: Engenharias
ÁREA: Engenharia Elétrica
RESUMO:

Joint Blind Source Separation (JBSS) is an extension of the Blind Source
Separation (BSS) problem being an important problem applied in many areas in view
of its versatility and practical applications. However, BSS still lacks methodologies
capable of ensuring source separation of multiple datasets, which makes this research
field very actual and challenging. Among the several possible methods in the context
of JBSS, the Independent Vector Analysis (IVA) is an interesting approach, since it is
based on the Independent Component Analysis (ICA) and it explores the statistical
dependency between different datasets through the use of Mutual Information
(MuInf). This work proposes an analysis of IVA in the biomedical signal area, focused
on the Motor Imagery (MI) paradigm and Transfer Learning (TL) approach. Firstly,
in the context of motor imagery classification based on electroencephalogram (EEG)
signals for Brain-Computer Interface (BCI), several methods have been proposed
to extract features efficiently, mainly based on common spatial patterns and filter
banks. In this scenario, we propose an original approach for feature extraction in
motor imagery, based on exploring the minimization of mutual information through
IVA followed by the use of Autoregressive filters. For the classification of imaginated
movements, two consolidated classifiers were used: Linear Discriminant Analysis
and Support Vector Machines. This approach was evaluated in two different MI
datasets (BCI Competition IV Dataset 1 and Dataset 2a). In addition, we present
the preliminary results for the TL approach with IVA for motor imagery movements
based on the BCI Competition IV - Dataset 2a. Finally, the future perspectives for
the work are presented, which include an epilepsy seizure prediction application,
combining IVA with the Graph Neural Network (GNN). This work will be developed
jointly with the Signal Processing Laboratory (LTS4) in École Polytechnique Federal
de Lausanne (EPFL), in Switzerland.


MEMBROS DA BANCA:
Presidente - Interno ao Programa - 1544392 - ALINE DE OLIVEIRA NEVES PANAZIO
Membro Titular - Examinador(a) Interno ao Programa - 1761107 - RICARDO SUYAMA
Membro Titular - Examinador(a) Externo à Instituição - SARAH NEGREIROS DE CARVALHO LEITE - UFOP
Membro Suplente - Examinador(a) Interno ao Programa - 2334927 - ANDRE KAZUO TAKAHATA
Notícia cadastrada em: 13/06/2022 11:13
SIGAA | UFABC - Núcleo de Tecnologia da Informação - ||||| | Copyright © 2006-2024 - UFRN - sigaa-2.ufabc.int.br.sigaa-2-prod