Factor Analysis for Finding Invariant Neural Descriptors of Human Emotions

A major challenge in decoding human emotions from electroencephalogram (EEG) data is finding representations that are invariant to inter- and intrasubject differences. Most of the previous studies are focused in building an individual discrimination model for every subject (subject dependent model)....

Full description

Saved in:
Bibliographic Details
Main Authors: Vitor Pereira, Filipe Tavares, Petya Mihaylova, Valeri Mladenov, Petia Georgieva
Format: Article
Language:English
Published: Wiley 2018-01-01
Series:Complexity
Online Access:http://dx.doi.org/10.1155/2018/6740846
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849407501546553344
author Vitor Pereira
Filipe Tavares
Petya Mihaylova
Valeri Mladenov
Petia Georgieva
author_facet Vitor Pereira
Filipe Tavares
Petya Mihaylova
Valeri Mladenov
Petia Georgieva
author_sort Vitor Pereira
collection DOAJ
description A major challenge in decoding human emotions from electroencephalogram (EEG) data is finding representations that are invariant to inter- and intrasubject differences. Most of the previous studies are focused in building an individual discrimination model for every subject (subject dependent model). Building subject-independent models is a harder problem due to the high data variability between different subjects and different experiments with the same subject. This paper explores, for the first time, the Factor Analysis as an efficient technique to extract temporal and spatial EEG features suitable to build brain-computer interface for decoding human emotions across various subjects. Our findings show that early waves (temporal window of 200–400 ms after the stimulus onset) carry more information about the valence of the emotion. Also, spatial location of features, with a stronger impact on the emotional valence, occurs in the parietal and occipital regions of the brain. All discrimination models (NN, SVM, kNN, and RF) demonstrate better discrimination rate of the positive valence. These results match closely experimental psychology hypothesis that, during early periods after the stimulus presentation, the brain response—to images with highly positive valence—is stronger.
format Article
id doaj-art-43aeff8cbe0d4a88a87fdc49a4864e45
institution Kabale University
issn 1076-2787
1099-0526
language English
publishDate 2018-01-01
publisher Wiley
record_format Article
series Complexity
spelling doaj-art-43aeff8cbe0d4a88a87fdc49a4864e452025-08-20T03:36:02ZengWileyComplexity1076-27871099-05262018-01-01201810.1155/2018/67408466740846Factor Analysis for Finding Invariant Neural Descriptors of Human EmotionsVitor Pereira0Filipe Tavares1Petya Mihaylova2Valeri Mladenov3Petia Georgieva4Department of Electronics Telecommunications and Informatics/IEETA, University of Aveiro, Aveiro, PortugalDepartment of Electronics Telecommunications and Informatics/IEETA, University of Aveiro, Aveiro, PortugalTechnical University of Sofia, Sofia, BulgariaTechnical University of Sofia, Sofia, BulgariaDepartment of Electronics Telecommunications and Informatics/IEETA, University of Aveiro, Aveiro, PortugalA major challenge in decoding human emotions from electroencephalogram (EEG) data is finding representations that are invariant to inter- and intrasubject differences. Most of the previous studies are focused in building an individual discrimination model for every subject (subject dependent model). Building subject-independent models is a harder problem due to the high data variability between different subjects and different experiments with the same subject. This paper explores, for the first time, the Factor Analysis as an efficient technique to extract temporal and spatial EEG features suitable to build brain-computer interface for decoding human emotions across various subjects. Our findings show that early waves (temporal window of 200–400 ms after the stimulus onset) carry more information about the valence of the emotion. Also, spatial location of features, with a stronger impact on the emotional valence, occurs in the parietal and occipital regions of the brain. All discrimination models (NN, SVM, kNN, and RF) demonstrate better discrimination rate of the positive valence. These results match closely experimental psychology hypothesis that, during early periods after the stimulus presentation, the brain response—to images with highly positive valence—is stronger.http://dx.doi.org/10.1155/2018/6740846
spellingShingle Vitor Pereira
Filipe Tavares
Petya Mihaylova
Valeri Mladenov
Petia Georgieva
Factor Analysis for Finding Invariant Neural Descriptors of Human Emotions
Complexity
title Factor Analysis for Finding Invariant Neural Descriptors of Human Emotions
title_full Factor Analysis for Finding Invariant Neural Descriptors of Human Emotions
title_fullStr Factor Analysis for Finding Invariant Neural Descriptors of Human Emotions
title_full_unstemmed Factor Analysis for Finding Invariant Neural Descriptors of Human Emotions
title_short Factor Analysis for Finding Invariant Neural Descriptors of Human Emotions
title_sort factor analysis for finding invariant neural descriptors of human emotions
url http://dx.doi.org/10.1155/2018/6740846
work_keys_str_mv AT vitorpereira factoranalysisforfindinginvariantneuraldescriptorsofhumanemotions
AT filipetavares factoranalysisforfindinginvariantneuraldescriptorsofhumanemotions
AT petyamihaylova factoranalysisforfindinginvariantneuraldescriptorsofhumanemotions
AT valerimladenov factoranalysisforfindinginvariantneuraldescriptorsofhumanemotions
AT petiageorgieva factoranalysisforfindinginvariantneuraldescriptorsofhumanemotions