Banca de DEFESA: LEANDRO ABIDIAS DA SILVA SERAFIM

Uma banca de DEFESA de MESTRADO foi cadastrada pelo programa.
STUDENT : LEANDRO ABIDIAS DA SILVA SERAFIM
DATE: 15/12/2022
TIME: 14:00
LOCAL: https://meet.google.com/jfz-wqmq-bbf
TITLE:

Feature Selection for Emotion Recognition through EEG Signals

PAGES: 55
BIG AREA: Engenharias
AREA: Engenharia Biomédica
SUBÁREA: Bioengenharia
SUMMARY:

Emotion classification through EEG signals has attracted the attention of researchers in several fields, including those studying brain-computer interfaces. This work focus on feature selection necessary to achieve a good classification performance. We started with the classic Principle Component Analysis (PCA) and the Maximum Relevance Minimum Redundance method (mRMR) . We proposed a modification on the Maximum Relevance Minimum Redundance method, applying it to EEG signals without the need of a discretization step. We show how the proposed method significantly improves the classifiers performance when compared to the use of classical PCA. We also included a detailed analysis of the discrete mRMR, and also a comparison of the methods mentionned above with the well known Backward Wrapper method.

BANKING MEMBERS:
Presidente - Interno ao Programa - 1544392 - ALINE DE OLIVEIRA NEVES PANAZIO
Membro Titular - Examinador(a) Interno ao Programa - 2334927 - ANDRE KAZUO TAKAHATA
Membro Titular - Examinador(a) Externo à Instituição - SARAH NEGREIROS DE CARVALHO LEITE - UFOP
Membro Suplente - Examinador(a) Interno ao Programa - 1761107 - RICARDO SUYAMA
Membro Suplente - Examinador(a) Externo à Instituição - DENIS GUSTAVO FANTINATO - UNICAMP