Home // COGNITIVE 2018, The Tenth International Conference on Advanced Cognitive Technologies and Applications // View article

EEG based Valence Recognition using Convolutional Kernel on Time-Frequency Axis

Authors:
Jun-Su Kang
Minho Lee

Keywords: valence recognition; convolutional neural network; long-short term memory; spectrogram

Abstract:
In this study, we present an emotion recognition model, namely valence recognition, based on convolutional kernel on time-frequency axis. Our proposed model uses convolutional kernel on Time-Frequency axis for Convolutional Neural Network (CNN). In order to compare our results with previous ones, we use the DEAP dataset that represents the benchmark for emotion classification research. The preliminary results show that the proposed model has a potential for positive and negative emotion recognition when compared to conventional studies.

Pages: 55 to 56

Copyright: Copyright (c) IARIA, 2018

Publication date: February 18, 2018

Published in: conference

ISSN: 2308-4197

ISBN: 978-1-61208-609-5

Location: Barcelona, Spain

Dates: from February 18, 2018 to February 22, 2018