Multimodal classification of anxiety based on physiological signals

Detalhes bibliográficos
Autor(a) principal: Vaz, Mariana
Data de Publicação: 2023
Outros Autores: Summavielle, Teresa, Sebastião, Raquel, Ribeiro, Rita P.
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/10400.22/23674
Resumo: Multiple studies show an association between anxiety disorders and dysregulation in the Autonomic Nervous System (ANS). Thus, understanding how informative the physiological signals are would contribute to effectively detecting anxiety. This study targets the classification of anxiety as an imbalanced binary classification problem using physiological signals collected from a sample of healthy subjects under a neutral condition. For this purpose, the Electrocardiogram (ECG), Electrodermal Activity (EDA), and Electromyogram (EMG) signals from the WESAD publicly available dataset were used. The neutral condition was collected for around 20 min on 15 participants, and anxiety scores were assessed through the shortened 6-item STAI. To achieve the described goal, the subsequent steps were followed: signal pre-processing; feature extraction, analysis, and selection; and classification of anxiety. The findings of this study allowed us to classify anxiety with discriminatory class features based on physiological signals. Moreover, feature selection revealed that ECG features play a relevant role in anxiety classification. Supervised feature selection and data balancing techniques, especially Borderline SMOTE 2, increased the performance of most classifiers. In particular, the combination of feature selection and Borderline SMOTE 2 achieved the best ROC-AUC with the Random Forest classifier.
id RCAP_0bfe0a81d25f1d0220f58f7377a6a2e2
oai_identifier_str oai:recipp.ipp.pt:10400.22/23674
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Multimodal classification of anxiety based on physiological signalsAnxietyClassificationWearable sensorsMultimodal datasetMachine learningPhysiological signalsSelf-reportsMultiple studies show an association between anxiety disorders and dysregulation in the Autonomic Nervous System (ANS). Thus, understanding how informative the physiological signals are would contribute to effectively detecting anxiety. This study targets the classification of anxiety as an imbalanced binary classification problem using physiological signals collected from a sample of healthy subjects under a neutral condition. For this purpose, the Electrocardiogram (ECG), Electrodermal Activity (EDA), and Electromyogram (EMG) signals from the WESAD publicly available dataset were used. The neutral condition was collected for around 20 min on 15 participants, and anxiety scores were assessed through the shortened 6-item STAI. To achieve the described goal, the subsequent steps were followed: signal pre-processing; feature extraction, analysis, and selection; and classification of anxiety. The findings of this study allowed us to classify anxiety with discriminatory class features based on physiological signals. Moreover, feature selection revealed that ECG features play a relevant role in anxiety classification. Supervised feature selection and data balancing techniques, especially Borderline SMOTE 2, increased the performance of most classifiers. In particular, the combination of feature selection and Borderline SMOTE 2 achieved the best ROC-AUC with the Random Forest classifier.MDPIRepositório Científico do Instituto Politécnico do PortoVaz, MarianaSummavielle, TeresaSebastião, RaquelRibeiro, Rita P.2023-10-11T17:03:44Z2023-05-232023-05-23T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10400.22/23674engVaz, M., Summavielle, T., Sebastião, R., & Ribeiro, R. P. (2023). Multimodal Classification of Anxiety Based on Physiological Signals. Applied Sciences, 13(11), Artigo 11. https://doi.org/10.3390/app1311636810.3390/app131163682076-3417info:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-10-18T01:45:55Zoai:recipp.ipp.pt:10400.22/23674Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T20:35:51.950510Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse
dc.title.none.fl_str_mv Multimodal classification of anxiety based on physiological signals
title Multimodal classification of anxiety based on physiological signals
spellingShingle Multimodal classification of anxiety based on physiological signals
Vaz, Mariana
Anxiety
Classification
Wearable sensors
Multimodal dataset
Machine learning
Physiological signals
Self-reports
title_short Multimodal classification of anxiety based on physiological signals
title_full Multimodal classification of anxiety based on physiological signals
title_fullStr Multimodal classification of anxiety based on physiological signals
title_full_unstemmed Multimodal classification of anxiety based on physiological signals
title_sort Multimodal classification of anxiety based on physiological signals
author Vaz, Mariana
author_facet Vaz, Mariana
Summavielle, Teresa
Sebastião, Raquel
Ribeiro, Rita P.
author_role author
author2 Summavielle, Teresa
Sebastião, Raquel
Ribeiro, Rita P.
author2_role author
author
author
dc.contributor.none.fl_str_mv Repositório Científico do Instituto Politécnico do Porto
dc.contributor.author.fl_str_mv Vaz, Mariana
Summavielle, Teresa
Sebastião, Raquel
Ribeiro, Rita P.
dc.subject.por.fl_str_mv Anxiety
Classification
Wearable sensors
Multimodal dataset
Machine learning
Physiological signals
Self-reports
topic Anxiety
Classification
Wearable sensors
Multimodal dataset
Machine learning
Physiological signals
Self-reports
description Multiple studies show an association between anxiety disorders and dysregulation in the Autonomic Nervous System (ANS). Thus, understanding how informative the physiological signals are would contribute to effectively detecting anxiety. This study targets the classification of anxiety as an imbalanced binary classification problem using physiological signals collected from a sample of healthy subjects under a neutral condition. For this purpose, the Electrocardiogram (ECG), Electrodermal Activity (EDA), and Electromyogram (EMG) signals from the WESAD publicly available dataset were used. The neutral condition was collected for around 20 min on 15 participants, and anxiety scores were assessed through the shortened 6-item STAI. To achieve the described goal, the subsequent steps were followed: signal pre-processing; feature extraction, analysis, and selection; and classification of anxiety. The findings of this study allowed us to classify anxiety with discriminatory class features based on physiological signals. Moreover, feature selection revealed that ECG features play a relevant role in anxiety classification. Supervised feature selection and data balancing techniques, especially Borderline SMOTE 2, increased the performance of most classifiers. In particular, the combination of feature selection and Borderline SMOTE 2 achieved the best ROC-AUC with the Random Forest classifier.
publishDate 2023
dc.date.none.fl_str_mv 2023-10-11T17:03:44Z
2023-05-23
2023-05-23T00:00:00Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10400.22/23674
url http://hdl.handle.net/10400.22/23674
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv Vaz, M., Summavielle, T., Sebastião, R., & Ribeiro, R. P. (2023). Multimodal Classification of Anxiety Based on Physiological Signals. Applied Sciences, 13(11), Artigo 11. https://doi.org/10.3390/app13116368
10.3390/app13116368
2076-3417
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv MDPI
publisher.none.fl_str_mv MDPI
dc.source.none.fl_str_mv reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron:RCAAP
instname_str Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron_str RCAAP
institution RCAAP
reponame_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
collection Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository.name.fl_str_mv Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
repository.mail.fl_str_mv
_version_ 1799133621822423040