{"id":{"repo_id":"minho-thes","oai_identifier":"oai:repositorium.uminho.pt:1822/92959"},"canonical_url":"https://search.dev.ndltd.org/etd/minho-thes/oai:repositorium.uminho.pt:1822/92959","repository":{"repo_id":"minho-thes","name":"Universidade do Minho","base_url":"http://repositorium.sdum.uminho.pt/oai/request"},"display":{"title":"Drowsy driving monitorization using statistical and machine learning techniques","abstract":"Sleep is crucial to people’s health and well-being, that is essential for cognitive function, emotional regulation, and physical health. Therefore, the quality of sleep directly influences daily performance, influencing our emotional stability and memory consolidation to decision making. Despite its importance, inadequate sleep contributes to an array of health problems and diminished quality of life. Consequently, sleep-related issues impact not only driver safety but also that of passengers, pedestrians, and other road users. This thesis seeks to comprehend sleep disorders among Portuguese drivers, with the objective of addressing prevailing knowledge gaps across all districts. A questionnaire-based approach, covering sleep disorders provided valuable insights. Among the findings, a significant portion of drivers reported poor sleep quality (60.2%) with a subset experiencing excessive daytime sleepiness (38.8%). Additionally, the study addresses the alignment between circadian rhythms and work schedules, acknowledging its impact on productivity. The analysis reveals that while the majority of drivers have work schedules aligned with their natural circadian rhythms, those whose schedules diverge from this alignment tend to experience increased daytime sleepiness. Furthermore, the study aims to improve road safety by creating affordable solutions that seamlessly integrate into driving routines, with a specific focus on combating drowsiness while driving. Driving simulations were conducted, and data were collected using a wearable device (Empatica E4), from which heart rate variability data was acquired. This data was then utilized for the classification and prediction of drowsiness. The study addressed challenges associated with subjective drowsiness classification (awake or drowsy) and used multivariate statistical process control techniques to improve the reliability of these classifications. Therefore, a comprehensive analysis revealed promising results, with the Ensemble Tree (ET) model emerging as the best classifier. Additionally, regression models, particularly the XGBoost (XGB), exhibited the ability to predict drowsiness with a lead time of two minutes, outperforming the ET model. Notably, the superior volume of data on drowsy events raised concerns regarding the model’s ability to recognize wakefulness accurately. After adding new data, the model was able to correctly distinguish between those who are awake and those who are sleepy. These findings are significant and promising in terms of their potential to predict drowsiness in advance.","abstract_html":"Sleep is crucial to people’s health and well-being, that is essential for cognitive function, emotional regulation, and physical health. Therefore, the quality of sleep directly influences daily performance, influencing our emotional stability and memory consolidation to decision making. Despite its importance, inadequate sleep contributes to an array of health problems and diminished quality of life. Consequently, sleep-related issues impact not only driver safety but also that of passengers, pedestrians, and other road users. This thesis seeks to comprehend sleep disorders among Portuguese drivers, with the objective of addressing prevailing knowledge gaps across all districts. A questionnaire-based approach, covering sleep disorders provided valuable insights. Among the findings, a significant portion of drivers reported poor sleep quality (60.2%) with a subset experiencing excessive daytime sleepiness (38.8%). Additionally, the study addresses the alignment between circadian rhythms and work schedules, acknowledging its impact on productivity. The analysis reveals that while the majority of drivers have work schedules aligned with their natural circadian rhythms, those whose schedules diverge from this alignment tend to experience increased daytime sleepiness. Furthermore, the study aims to improve road safety by creating affordable solutions that seamlessly integrate into driving routines, with a specific focus on combating drowsiness while driving. Driving simulations were conducted, and data were collected using a wearable device (Empatica E4), from which heart rate variability data was acquired. This data was then utilized for the classification and prediction of drowsiness. The study addressed challenges associated with subjective drowsiness classification (awake or drowsy) and used multivariate statistical process control techniques to improve the reliability of these classifications. Therefore, a comprehensive analysis revealed promising results, with the Ensemble Tree (ET) model emerging as the best classifier. Additionally, regression models, particularly the XGBoost (XGB), exhibited the ability to predict drowsiness with a lead time of two minutes, outperforming the ET model. Notably, the superior volume of data on drowsy events raised concerns regarding the model’s ability to recognize wakefulness accurately. After adding new data, the model was able to correctly distinguish between those who are awake and those who are sleepy. These findings are significant and promising in terms of their potential to predict drowsiness in advance.","abstract_has_math":false,"creators":["Antunes, Ana Rita Oliveira"],"institution":"Universidade do Minho","degree_name":"Programa doutoral em Industrial and Systems Engineering","degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":["Braga, A. C.","Gonçalves, Joaquim José de Almeida Soares"],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024-07-18","date_published":"2024-07-18","updated_at":"2026-08-21T16:46:39Z","subjects":["Drowsiness at the wheel","Feature selection","Machine learning","Sleep disorders","Statistic","Aprendizagem automática","Distúrbios de sono","Estatística","Seleção das variáveis","Sonolência ao volante"],"languages":["eng"],"rights":["openAccess"],"rights_urls":["http://creativecommons.org/licenses/by-nc-sa/4.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1822/92959","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"source_record":{"url":"http://repositorium.sdum.uminho.pt/oai/request?verb=GetRecord&metadataPrefix=dim&identifier=oai%3Arepositorium.uminho.pt%3A1822%2F92959","prefix":"dim"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Braga, A. C.","Gonçalves, Joaquim José de Almeida Soares"]},{"key":"dc:creator","label":"Author","values":["Antunes, Ana Rita Oliveira"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2024-09-09T11:24:45Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2024-09-09T11:24:45Z"]},{"key":"dc:date.issued","label":"Date","values":["2024-07-18"]},{"key":"dc:type","label":"Dc Type","values":["doctoralThesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Programa doutoral em Industrial and Systems Engineering"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Universidade do Minho"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Drowsiness at the wheel","Feature selection","Machine learning","Sleep disorders","Statistic","Aprendizagem automática","Distúrbios de sono","Estatística","Seleção das variáveis","Sonolência ao volante"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["openAccess"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://creativecommons.org/licenses/by-nc-sa/4.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1822/92959"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Sleep is crucial to people’s health and well-being, that is essential for cognitive function, emotional regulation, and physical health. Therefore, the quality of sleep directly influences daily performance, influencing our emotional stability and memory consolidation to decision making. Despite its importance, inadequate sleep contributes to an array of health problems and diminished quality of life. Consequently, sleep-related issues impact not only driver safety but also that of passengers, pedestrians, and other road users. This thesis seeks to comprehend sleep disorders among Portuguese drivers, with the objective of addressing prevailing knowledge gaps across all districts. A questionnaire-based approach, covering sleep disorders provided valuable insights. Among the findings, a significant portion of drivers reported poor sleep quality (60.2%) with a subset experiencing excessive daytime sleepiness (38.8%). Additionally, the study addresses the alignment between circadian rhythms and work schedules, acknowledging its impact on productivity. The analysis reveals that while the majority of drivers have work schedules aligned with their natural circadian rhythms, those whose schedules diverge from this alignment tend to experience increased daytime sleepiness. Furthermore, the study aims to improve road safety by creating affordable solutions that seamlessly integrate into driving routines, with a specific focus on combating drowsiness while driving. Driving simulations were conducted, and data were collected using a wearable device (Empatica E4), from which heart rate variability data was acquired. This data was then utilized for the classification and prediction of drowsiness. The study addressed challenges associated with subjective drowsiness classification (awake or drowsy) and used multivariate statistical process control techniques to improve the reliability of these classifications. Therefore, a comprehensive analysis revealed promising results, with the Ensemble Tree (ET) model emerging as the best classifier. Additionally, regression models, particularly the XGBoost (XGB), exhibited the ability to predict drowsiness with a lead time of two minutes, outperforming the ET model. Notably, the superior volume of data on drowsy events raised concerns regarding the model’s ability to recognize wakefulness accurately. After adding new data, the model was able to correctly distinguish between those who are awake and those who are sleepy. These findings are significant and promising in terms of their potential to predict drowsiness in advance.","O sono é importante na saúde e no bem-estar das pessoas, sendo fundamental para funções cognitivas, regulação emocional e saúde física. A qualidade do sono influencia o desempenho diário, afetando a estabilidade emocional e a consolidação da memória para a tomada de decisões, que podem contribuir para problemas de saúde e diminuição da qualidade de vida. Consequentemente, impactam a segurança dos condutores, assim como a de passageiros, peões e outros utilizadores da estrada. Deste modo, esta tese analisa os distúrbios do sono, nos condutores portugueses, procurando preencher lacunas existentes na literatura, e que tenha em consideração os distritos de Portugal. O desenvolvimento de um questionário, sobre distúrbios de sono, forneceu informações valiosas, em que uma parte significativa apresenta má qualidade do sono (60,2%) e, 38,8% tem sonolência excessiva diurna. Além disso, o estudo compara os ritmos circadianos e os horários de trabalho e resultou que na maioria dos condutores existe sincronização. No entanto, nos restantes condutores foi identificada a prevalência de sonolência excessiva diurna. Nesse sentido, o estudo visa melhorar a segurança rodoviária, criando soluções acessíveis que se integrem facilmente nas rotinas de condução, abordando especificamente o problema da sonolência ao volante. Através de simulações de condução e recolha de dados usando um dispositivo inteligente (Empatica E4), foram obtidos dados da variabilidade do batimento cardíaca e utilizados para classificação e previsão de sonolência. O estudo abordou desafios na classificação subjetiva de sonolência (acordado ou sonolento) e enfatizou a importância das técnicas de controlo estatístico multivariado para melhorar as classificações. Através de uma análise analítica foram atingidos resultados promissores, onde o modelo Ensemble Tree (Extremely Randomized Trees (ET)) obteve os melhores resultados. O modelo de regressão XGBoost (eXtreme Gradient Boosting (XGB)) demonstrou a capacidade de prever a sonolência dois minutos antes, superando o modelo ET. Com mais informações sobre eventos sonolentos, surgiu a preocupação de o modelo não estar a distinguir o estado acordado de sonolento. Após a adição de novos dados, o modelo foi capaz de distinguir corretamente entre aqueles que estão acordados e aqueles que estão sonolentos. Assim, estes resultados são bastante promissores para prever a sonolência antecipadamente."]},{"key":"dc:title","label":"Title","values":["Drowsy driving monitorization using statistical and machine learning techniques"]}]}],"canonical_facts":{"dc:contributor.advisor":["Braga, A. C.","Gonçalves, Joaquim José de Almeida Soares"],"dc:creator":["Antunes, Ana Rita Oliveira"],"dc:date.accessioned":["2024-09-09T11:24:45Z"],"dc:date.available":["2024-09-09T11:24:45Z"],"dc:date.issued":["2024-07-18"],"dc:description.abstract":["Sleep is crucial to people’s health and well-being, that is essential for cognitive function, emotional regulation, and physical health. Therefore, the quality of sleep directly influences daily performance, influencing our emotional stability and memory consolidation to decision making. Despite its importance, inadequate sleep contributes to an array of health problems and diminished quality of life. Consequently, sleep-related issues impact not only driver safety but also that of passengers, pedestrians, and other road users. This thesis seeks to comprehend sleep disorders among Portuguese drivers, with the objective of addressing prevailing knowledge gaps across all districts. A questionnaire-based approach, covering sleep disorders provided valuable insights. Among the findings, a significant portion of drivers reported poor sleep quality (60.2%) with a subset experiencing excessive daytime sleepiness (38.8%). Additionally, the study addresses the alignment between circadian rhythms and work schedules, acknowledging its impact on productivity. The analysis reveals that while the majority of drivers have work schedules aligned with their natural circadian rhythms, those whose schedules diverge from this alignment tend to experience increased daytime sleepiness. Furthermore, the study aims to improve road safety by creating affordable solutions that seamlessly integrate into driving routines, with a specific focus on combating drowsiness while driving. Driving simulations were conducted, and data were collected using a wearable device (Empatica E4), from which heart rate variability data was acquired. This data was then utilized for the classification and prediction of drowsiness. The study addressed challenges associated with subjective drowsiness classification (awake or drowsy) and used multivariate statistical process control techniques to improve the reliability of these classifications. Therefore, a comprehensive analysis revealed promising results, with the Ensemble Tree (ET) model emerging as the best classifier. Additionally, regression models, particularly the XGBoost (XGB), exhibited the ability to predict drowsiness with a lead time of two minutes, outperforming the ET model. Notably, the superior volume of data on drowsy events raised concerns regarding the model’s ability to recognize wakefulness accurately. After adding new data, the model was able to correctly distinguish between those who are awake and those who are sleepy. These findings are significant and promising in terms of their potential to predict drowsiness in advance.","O sono é importante na saúde e no bem-estar das pessoas, sendo fundamental para funções cognitivas, regulação emocional e saúde física. A qualidade do sono influencia o desempenho diário, afetando a estabilidade emocional e a consolidação da memória para a tomada de decisões, que podem contribuir para problemas de saúde e diminuição da qualidade de vida. Consequentemente, impactam a segurança dos condutores, assim como a de passageiros, peões e outros utilizadores da estrada. Deste modo, esta tese analisa os distúrbios do sono, nos condutores portugueses, procurando preencher lacunas existentes na literatura, e que tenha em consideração os distritos de Portugal. O desenvolvimento de um questionário, sobre distúrbios de sono, forneceu informações valiosas, em que uma parte significativa apresenta má qualidade do sono (60,2%) e, 38,8% tem sonolência excessiva diurna. Além disso, o estudo compara os ritmos circadianos e os horários de trabalho e resultou que na maioria dos condutores existe sincronização. No entanto, nos restantes condutores foi identificada a prevalência de sonolência excessiva diurna. Nesse sentido, o estudo visa melhorar a segurança rodoviária, criando soluções acessíveis que se integrem facilmente nas rotinas de condução, abordando especificamente o problema da sonolência ao volante. Através de simulações de condução e recolha de dados usando um dispositivo inteligente (Empatica E4), foram obtidos dados da variabilidade do batimento cardíaca e utilizados para classificação e previsão de sonolência. O estudo abordou desafios na classificação subjetiva de sonolência (acordado ou sonolento) e enfatizou a importância das técnicas de controlo estatístico multivariado para melhorar as classificações. Através de uma análise analítica foram atingidos resultados promissores, onde o modelo Ensemble Tree (Extremely Randomized Trees (ET)) obteve os melhores resultados. O modelo de regressão XGBoost (eXtreme Gradient Boosting (XGB)) demonstrou a capacidade de prever a sonolência dois minutos antes, superando o modelo ET. Com mais informações sobre eventos sonolentos, surgiu a preocupação de o modelo não estar a distinguir o estado acordado de sonolento. Após a adição de novos dados, o modelo foi capaz de distinguir corretamente entre aqueles que estão acordados e aqueles que estão sonolentos. Assim, estes resultados são bastante promissores para prever a sonolência antecipadamente."],"dc:identifier.uri":["https://hdl.handle.net/1822/92959"],"dc:language.iso":["eng"],"dc:rights":["openAccess"],"dc:rights.uri":["http://creativecommons.org/licenses/by-nc-sa/4.0/"],"dc:subject":["Drowsiness at the wheel","Feature selection","Machine learning","Sleep disorders","Statistic","Aprendizagem automática","Distúrbios de sono","Estatística","Seleção das variáveis","Sonolência ao volante"],"dc:title":["Drowsy driving monitorization using statistical and machine learning techniques"],"dc:type":["doctoralThesis"],"thesis:degree_name":["Programa doutoral em Industrial and Systems Engineering"],"thesis:institution_name":["Universidade do Minho"]},"updated_at":"2026-08-21T16:46:39Z"}