Machine Learning Models for Mental Stress Classification based on Multimodal Biosignal Input
Autor(a) principal: | |
---|---|
Data de Publicação: | 2022 |
Tipo de documento: | Dissertação |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10362/153937 |
Resumo: | Mental stress is a largely prevalent condition directly or indirectly responsible for almost half of all work-related diseases. Work-Related Stress is the second most impactful occupational health problem in Europe, behind musculoskeletal diseases. When mental health is adequately handled, a worker’s well-being, performance, and productivity can be considerably improved. This thesis presents machine learning models to classify mental stress experienced by computer users using physiological signals including heart rate, acquired using a smart- watch; respiration, derived from a smartphone’s acc placed on the chest; and trapezius electromyography, using proprietary electromyography sensors. Two interactive proto- cols were implemented to collect data from 12 individuals. Time and frequency domain features were extracted from the heart rate and electromyography signals, and statistical and temporal features were extracted from the derived respiration signal. Three algorithms: Support Vector Machine, Random Forest, and K-Nearest-Neighbor were employed for mental stress classification. Different input modalities were tested for the machine learning models: one for each physiological signal and a multimodal one, combining all of them. Random Forest obtained the best mean accuracy (98.5%) for the respiration model whereas K-Nearest-Neighbor attained higher mean accuracies for the heart rate (89.0%) left, right and total electromyography (98.9%, 99.2%, and 99.3%) models. KNN algorithm was also able to achieve 100% mean accuracy for the multimodal model. A possible future approach would be to validate these models in real-time. |
id |
RCAP_24b392995713a27d1af8e0add8983115 |
---|---|
oai_identifier_str |
oai:run.unl.pt:10362/153937 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Machine Learning Models for Mental Stress Classification based on Multimodal Biosignal InputStress DetectionBiosignalsOccupational HealthMachine LearningMultimodal InputDomínio/Área Científica::Engenharia e Tecnologia::Outras Engenharias e TecnologiasMental stress is a largely prevalent condition directly or indirectly responsible for almost half of all work-related diseases. Work-Related Stress is the second most impactful occupational health problem in Europe, behind musculoskeletal diseases. When mental health is adequately handled, a worker’s well-being, performance, and productivity can be considerably improved. This thesis presents machine learning models to classify mental stress experienced by computer users using physiological signals including heart rate, acquired using a smart- watch; respiration, derived from a smartphone’s acc placed on the chest; and trapezius electromyography, using proprietary electromyography sensors. Two interactive proto- cols were implemented to collect data from 12 individuals. Time and frequency domain features were extracted from the heart rate and electromyography signals, and statistical and temporal features were extracted from the derived respiration signal. Three algorithms: Support Vector Machine, Random Forest, and K-Nearest-Neighbor were employed for mental stress classification. Different input modalities were tested for the machine learning models: one for each physiological signal and a multimodal one, combining all of them. Random Forest obtained the best mean accuracy (98.5%) for the respiration model whereas K-Nearest-Neighbor attained higher mean accuracies for the heart rate (89.0%) left, right and total electromyography (98.9%, 99.2%, and 99.3%) models. KNN algorithm was also able to achieve 100% mean accuracy for the multimodal model. A possible future approach would be to validate these models in real-time.O stress mental é uma condição amplamente prevalente direta ou indiretamente responsável por quase metade de todas doenças relacionadas com trabalho. O stress expe- rienciado no trabalho é o segundo problema de saúde ocupacional com maior impacto na Europa, depois das doenças músculo-esqueléticas. Quando a saúde mental é adequada- mente cuidada, o bem-estar, o desempenho e a produtividade de um trabalhador podem ser consideravelmente melhorados. Esta tese apresenta modelos de aprendizagem automática que classificam o stress mental experienciado por utilizadores de computadores recorrendo a sinais fisiológi- cos, incluindo a frequência cardíaca, adquirida pelo sensor de fotopletismografia de um smartwatch; a respiração, derivada de um acelerómetro incorporado no smartphone po- sicionado no peito; e electromiografia de cada um dos músculos trapézios, utilizando sensores electromiográficos proprietários. Foram implementados dois protocolos inte- ractivos para recolha de dados de 12 indivíduos. Características do domínio temporal e de frequência foram extraídas dos sinais de frequência cardíaca e electromiografia, e características estatísticas e temporais foram extraídas do sinal respiratório. Três algoritmos entitulados K-Nearest-Neighbor, Random Forest, e Support Vector Machine foram utilizados para a classificação do stress mental. Foram testadas diferentes modalidades de dados para os modelos de aprendizagem automática: uma para cada sinal fisiológico e uma multimodal, combinando os três. O Random Forest obteve a melhor precisão média (98,5%) para o modelo de respiração enquanto que o K-Nearest-Neighbor atingiu uma maior precisão média nos modelos de frequência cardíaca (89,0%) e electro- miografia esquerda, direita e total (98,9%, 99,2%, e 99,3%). O algoritmo KNN conseguiu ainda atingir uma precisão média de 100% para o modelo multimodal. Uma possível abordagem futura seria efetuar uma validação destes modelos em tempo real.Gamboa, HugoBastos, CátiaRUNJustino, Maria Veríssimo Duarte2023-06-15T11:31:57Z2022-122022-12-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10362/153937enginfo: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:RCAAP2024-03-11T05:36:24Zoai:run.unl.pt:10362/153937Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T03:55:26.071041Repositório 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 |
Machine Learning Models for Mental Stress Classification based on Multimodal Biosignal Input |
title |
Machine Learning Models for Mental Stress Classification based on Multimodal Biosignal Input |
spellingShingle |
Machine Learning Models for Mental Stress Classification based on Multimodal Biosignal Input Justino, Maria Veríssimo Duarte Stress Detection Biosignals Occupational Health Machine Learning Multimodal Input Domínio/Área Científica::Engenharia e Tecnologia::Outras Engenharias e Tecnologias |
title_short |
Machine Learning Models for Mental Stress Classification based on Multimodal Biosignal Input |
title_full |
Machine Learning Models for Mental Stress Classification based on Multimodal Biosignal Input |
title_fullStr |
Machine Learning Models for Mental Stress Classification based on Multimodal Biosignal Input |
title_full_unstemmed |
Machine Learning Models for Mental Stress Classification based on Multimodal Biosignal Input |
title_sort |
Machine Learning Models for Mental Stress Classification based on Multimodal Biosignal Input |
author |
Justino, Maria Veríssimo Duarte |
author_facet |
Justino, Maria Veríssimo Duarte |
author_role |
author |
dc.contributor.none.fl_str_mv |
Gamboa, Hugo Bastos, Cátia RUN |
dc.contributor.author.fl_str_mv |
Justino, Maria Veríssimo Duarte |
dc.subject.por.fl_str_mv |
Stress Detection Biosignals Occupational Health Machine Learning Multimodal Input Domínio/Área Científica::Engenharia e Tecnologia::Outras Engenharias e Tecnologias |
topic |
Stress Detection Biosignals Occupational Health Machine Learning Multimodal Input Domínio/Área Científica::Engenharia e Tecnologia::Outras Engenharias e Tecnologias |
description |
Mental stress is a largely prevalent condition directly or indirectly responsible for almost half of all work-related diseases. Work-Related Stress is the second most impactful occupational health problem in Europe, behind musculoskeletal diseases. When mental health is adequately handled, a worker’s well-being, performance, and productivity can be considerably improved. This thesis presents machine learning models to classify mental stress experienced by computer users using physiological signals including heart rate, acquired using a smart- watch; respiration, derived from a smartphone’s acc placed on the chest; and trapezius electromyography, using proprietary electromyography sensors. Two interactive proto- cols were implemented to collect data from 12 individuals. Time and frequency domain features were extracted from the heart rate and electromyography signals, and statistical and temporal features were extracted from the derived respiration signal. Three algorithms: Support Vector Machine, Random Forest, and K-Nearest-Neighbor were employed for mental stress classification. Different input modalities were tested for the machine learning models: one for each physiological signal and a multimodal one, combining all of them. Random Forest obtained the best mean accuracy (98.5%) for the respiration model whereas K-Nearest-Neighbor attained higher mean accuracies for the heart rate (89.0%) left, right and total electromyography (98.9%, 99.2%, and 99.3%) models. KNN algorithm was also able to achieve 100% mean accuracy for the multimodal model. A possible future approach would be to validate these models in real-time. |
publishDate |
2022 |
dc.date.none.fl_str_mv |
2022-12 2022-12-01T00:00:00Z 2023-06-15T11:31:57Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/masterThesis |
format |
masterThesis |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10362/153937 |
url |
http://hdl.handle.net/10362/153937 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
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.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_ |
1799138141497458688 |