Cargando…

Machine Learning Methods for Fear Classification Based on Physiological Features

This paper focuses on the binary classification of the emotion of fear, based on the physiological data and subjective responses stored in the DEAP dataset. We performed a mapping between the discrete and dimensional emotional information considering the participants’ ratings and extracted a substan...

Descripción completa

Detalles Bibliográficos
Autores principales: Petrescu, Livia, Petrescu, Cătălin, Oprea, Ana, Mitruț, Oana, Moise, Gabriela, Moldoveanu, Alin, Moldoveanu, Florica
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8271969/
https://www.ncbi.nlm.nih.gov/pubmed/34282759
http://dx.doi.org/10.3390/s21134519
_version_ 1783721115778023424
author Petrescu, Livia
Petrescu, Cătălin
Oprea, Ana
Mitruț, Oana
Moise, Gabriela
Moldoveanu, Alin
Moldoveanu, Florica
author_facet Petrescu, Livia
Petrescu, Cătălin
Oprea, Ana
Mitruț, Oana
Moise, Gabriela
Moldoveanu, Alin
Moldoveanu, Florica
author_sort Petrescu, Livia
collection PubMed
description This paper focuses on the binary classification of the emotion of fear, based on the physiological data and subjective responses stored in the DEAP dataset. We performed a mapping between the discrete and dimensional emotional information considering the participants’ ratings and extracted a substantial set of 40 types of features from the physiological data, which represented the input to various machine learning algorithms—Decision Trees, k-Nearest Neighbors, Support Vector Machine and artificial networks—accompanied by dimensionality reduction, feature selection and the tuning of the most relevant hyperparameters, boosting classification accuracy. The methodology we approached included tackling different situations, such as resolving the problem of having an imbalanced dataset through data augmentation, reducing overfitting, computing various metrics in order to obtain the most reliable classification scores and applying the Local Interpretable Model-Agnostic Explanations method for interpretation and for explaining predictions in a human-understandable manner. The results show that fear can be predicted very well (accuracies ranging from 91.7% using Gradient Boosting Trees to 93.5% using dimensionality reduction and Support Vector Machine) by extracting the most relevant features from the physiological data and by searching for the best parameters which maximize the machine learning algorithms’ classification scores.
format Online
Article
Text
id pubmed-8271969
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-82719692021-07-11 Machine Learning Methods for Fear Classification Based on Physiological Features Petrescu, Livia Petrescu, Cătălin Oprea, Ana Mitruț, Oana Moise, Gabriela Moldoveanu, Alin Moldoveanu, Florica Sensors (Basel) Article This paper focuses on the binary classification of the emotion of fear, based on the physiological data and subjective responses stored in the DEAP dataset. We performed a mapping between the discrete and dimensional emotional information considering the participants’ ratings and extracted a substantial set of 40 types of features from the physiological data, which represented the input to various machine learning algorithms—Decision Trees, k-Nearest Neighbors, Support Vector Machine and artificial networks—accompanied by dimensionality reduction, feature selection and the tuning of the most relevant hyperparameters, boosting classification accuracy. The methodology we approached included tackling different situations, such as resolving the problem of having an imbalanced dataset through data augmentation, reducing overfitting, computing various metrics in order to obtain the most reliable classification scores and applying the Local Interpretable Model-Agnostic Explanations method for interpretation and for explaining predictions in a human-understandable manner. The results show that fear can be predicted very well (accuracies ranging from 91.7% using Gradient Boosting Trees to 93.5% using dimensionality reduction and Support Vector Machine) by extracting the most relevant features from the physiological data and by searching for the best parameters which maximize the machine learning algorithms’ classification scores. MDPI 2021-07-01 /pmc/articles/PMC8271969/ /pubmed/34282759 http://dx.doi.org/10.3390/s21134519 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Petrescu, Livia
Petrescu, Cătălin
Oprea, Ana
Mitruț, Oana
Moise, Gabriela
Moldoveanu, Alin
Moldoveanu, Florica
Machine Learning Methods for Fear Classification Based on Physiological Features
title Machine Learning Methods for Fear Classification Based on Physiological Features
title_full Machine Learning Methods for Fear Classification Based on Physiological Features
title_fullStr Machine Learning Methods for Fear Classification Based on Physiological Features
title_full_unstemmed Machine Learning Methods for Fear Classification Based on Physiological Features
title_short Machine Learning Methods for Fear Classification Based on Physiological Features
title_sort machine learning methods for fear classification based on physiological features
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8271969/
https://www.ncbi.nlm.nih.gov/pubmed/34282759
http://dx.doi.org/10.3390/s21134519
work_keys_str_mv AT petresculivia machinelearningmethodsforfearclassificationbasedonphysiologicalfeatures
AT petrescucatalin machinelearningmethodsforfearclassificationbasedonphysiologicalfeatures
AT opreaana machinelearningmethodsforfearclassificationbasedonphysiologicalfeatures
AT mitrutoana machinelearningmethodsforfearclassificationbasedonphysiologicalfeatures
AT moisegabriela machinelearningmethodsforfearclassificationbasedonphysiologicalfeatures
AT moldoveanualin machinelearningmethodsforfearclassificationbasedonphysiologicalfeatures
AT moldoveanuflorica machinelearningmethodsforfearclassificationbasedonphysiologicalfeatures