Cargando…

An Investigation of Various Machine and Deep Learning Techniques Applied in Automatic Fear Level Detection and Acrophobia Virtual Therapy

In this paper, we investigate various machine learning classifiers used in our Virtual Reality (VR) system for treating acrophobia. The system automatically estimates fear level based on multimodal sensory data and a self-reported emotion assessment. There are two modalities of expressing fear ratin...

Descripción completa

Detalles Bibliográficos
Autores principales: Bălan, Oana, Moise, Gabriela, Moldoveanu, Alin, Leordeanu, Marius, Moldoveanu, Florica
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7013944/
https://www.ncbi.nlm.nih.gov/pubmed/31952289
http://dx.doi.org/10.3390/s20020496
_version_ 1783496515209134080
author Bălan, Oana
Moise, Gabriela
Moldoveanu, Alin
Leordeanu, Marius
Moldoveanu, Florica
author_facet Bălan, Oana
Moise, Gabriela
Moldoveanu, Alin
Leordeanu, Marius
Moldoveanu, Florica
author_sort Bălan, Oana
collection PubMed
description In this paper, we investigate various machine learning classifiers used in our Virtual Reality (VR) system for treating acrophobia. The system automatically estimates fear level based on multimodal sensory data and a self-reported emotion assessment. There are two modalities of expressing fear ratings: the 2-choice scale, where 0 represents relaxation and 1 stands for fear; and the 4-choice scale, with the following correspondence: 0—relaxation, 1—low fear, 2—medium fear and 3—high fear. A set of features was extracted from the sensory signals using various metrics that quantify brain (electroencephalogram—EEG) and physiological linear and non-linear dynamics (Heart Rate—HR and Galvanic Skin Response—GSR). The novelty consists in the automatic adaptation of exposure scenario according to the subject’s affective state. We acquired data from acrophobic subjects who had undergone an in vivo pre-therapy exposure session, followed by a Virtual Reality therapy and an in vivo evaluation procedure. Various machine and deep learning classifiers were implemented and tested, with and without feature selection, in both a user-dependent and user-independent fashion. The results showed a very high cross-validation accuracy on the training set and good test accuracies, ranging from 42.5% to 89.5%. The most important features of fear level classification were GSR, HR and the values of the EEG in the beta frequency range. For determining the next exposure scenario, a dominant role was played by the target fear level, a parameter computed by taking into account the patient’s estimated fear level.
format Online
Article
Text
id pubmed-7013944
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-70139442020-03-09 An Investigation of Various Machine and Deep Learning Techniques Applied in Automatic Fear Level Detection and Acrophobia Virtual Therapy Bălan, Oana Moise, Gabriela Moldoveanu, Alin Leordeanu, Marius Moldoveanu, Florica Sensors (Basel) Article In this paper, we investigate various machine learning classifiers used in our Virtual Reality (VR) system for treating acrophobia. The system automatically estimates fear level based on multimodal sensory data and a self-reported emotion assessment. There are two modalities of expressing fear ratings: the 2-choice scale, where 0 represents relaxation and 1 stands for fear; and the 4-choice scale, with the following correspondence: 0—relaxation, 1—low fear, 2—medium fear and 3—high fear. A set of features was extracted from the sensory signals using various metrics that quantify brain (electroencephalogram—EEG) and physiological linear and non-linear dynamics (Heart Rate—HR and Galvanic Skin Response—GSR). The novelty consists in the automatic adaptation of exposure scenario according to the subject’s affective state. We acquired data from acrophobic subjects who had undergone an in vivo pre-therapy exposure session, followed by a Virtual Reality therapy and an in vivo evaluation procedure. Various machine and deep learning classifiers were implemented and tested, with and without feature selection, in both a user-dependent and user-independent fashion. The results showed a very high cross-validation accuracy on the training set and good test accuracies, ranging from 42.5% to 89.5%. The most important features of fear level classification were GSR, HR and the values of the EEG in the beta frequency range. For determining the next exposure scenario, a dominant role was played by the target fear level, a parameter computed by taking into account the patient’s estimated fear level. MDPI 2020-01-15 /pmc/articles/PMC7013944/ /pubmed/31952289 http://dx.doi.org/10.3390/s20020496 Text en © 2020 by the authors. 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 (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Bălan, Oana
Moise, Gabriela
Moldoveanu, Alin
Leordeanu, Marius
Moldoveanu, Florica
An Investigation of Various Machine and Deep Learning Techniques Applied in Automatic Fear Level Detection and Acrophobia Virtual Therapy
title An Investigation of Various Machine and Deep Learning Techniques Applied in Automatic Fear Level Detection and Acrophobia Virtual Therapy
title_full An Investigation of Various Machine and Deep Learning Techniques Applied in Automatic Fear Level Detection and Acrophobia Virtual Therapy
title_fullStr An Investigation of Various Machine and Deep Learning Techniques Applied in Automatic Fear Level Detection and Acrophobia Virtual Therapy
title_full_unstemmed An Investigation of Various Machine and Deep Learning Techniques Applied in Automatic Fear Level Detection and Acrophobia Virtual Therapy
title_short An Investigation of Various Machine and Deep Learning Techniques Applied in Automatic Fear Level Detection and Acrophobia Virtual Therapy
title_sort investigation of various machine and deep learning techniques applied in automatic fear level detection and acrophobia virtual therapy
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7013944/
https://www.ncbi.nlm.nih.gov/pubmed/31952289
http://dx.doi.org/10.3390/s20020496
work_keys_str_mv AT balanoana aninvestigationofvariousmachineanddeeplearningtechniquesappliedinautomaticfearleveldetectionandacrophobiavirtualtherapy
AT moisegabriela aninvestigationofvariousmachineanddeeplearningtechniquesappliedinautomaticfearleveldetectionandacrophobiavirtualtherapy
AT moldoveanualin aninvestigationofvariousmachineanddeeplearningtechniquesappliedinautomaticfearleveldetectionandacrophobiavirtualtherapy
AT leordeanumarius aninvestigationofvariousmachineanddeeplearningtechniquesappliedinautomaticfearleveldetectionandacrophobiavirtualtherapy
AT moldoveanuflorica aninvestigationofvariousmachineanddeeplearningtechniquesappliedinautomaticfearleveldetectionandacrophobiavirtualtherapy
AT balanoana investigationofvariousmachineanddeeplearningtechniquesappliedinautomaticfearleveldetectionandacrophobiavirtualtherapy
AT moisegabriela investigationofvariousmachineanddeeplearningtechniquesappliedinautomaticfearleveldetectionandacrophobiavirtualtherapy
AT moldoveanualin investigationofvariousmachineanddeeplearningtechniquesappliedinautomaticfearleveldetectionandacrophobiavirtualtherapy
AT leordeanumarius investigationofvariousmachineanddeeplearningtechniquesappliedinautomaticfearleveldetectionandacrophobiavirtualtherapy
AT moldoveanuflorica investigationofvariousmachineanddeeplearningtechniquesappliedinautomaticfearleveldetectionandacrophobiavirtualtherapy