• JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
 
  Bookmark and Share
 
 
Master's Dissertation
DOI
https://doi.org/10.11606/D.45.2021.tde-08072021-002641
Document
Author
Full name
Carlos Enrique Paucar Farfán
Institute/School/College
Knowledge Area
Date of Defense
Published
São Paulo, 2021
Supervisor
Committee
Fujita, André (President)
Steiner, Alexandre Alarcon
Takahashi, Daniel Yasumasa
Title in Portuguese
Classificação dos estados cognitivos orientados pelo sujeito baseada na variabilidade da frequência cardíaca
Keywords in Portuguese
Biomarcador
Classificação
Eletrocardiograma
Estado cognitivo
Variabilidade da frequência cardíaca
Abstract in Portuguese
A decodificação cerebral ganhou muita atenção durante as últimas décadas. Os primeiros estudosforam baseados em eventos discretos. Recentemente, foram desenvolvidos métodos para decodificarestados cognitivos mais contínuos e puramente subjetivos. Entretanto, todos eles requerem disposi-tivos caros, difíceis de manusear e desconfortáveis para o uso diário. Aqui propomos uma alternativabaseada na frequência cardíaca (FC). Já é bem conhecido que podemos discriminar algumas ativi-dades físicas com base na FC. Entretanto, a questão não intuitiva é: podemos discriminar tarefascognitivas com base na FC? Submetemos 25 sujeitos a quatro tarefas cognitivas: descansar em silên-cio, lembrar dos eventos do dia anterior, cantar e subtrair números. Coletamos o eletrocardiogramaduas vezes para cada indivíduo, separados por aproximadamente uma semana. Para coletar a FC,usamos uma faixa de sensor de tórax comercial utilizada por atletas. Treinamos uma máquina ve-torial de suporte usando os dados coletados no primeiro dia. Depois a validamos no conjunto dedados coletados no segundo dia. Nossos resultados mostram precisão mais significativa do que oque esperamos ao acaso(p <0,001). Dependendo do indivíduo e do conjunto de tarefas cognitivas,obtivemos quase 100% de acurácia. Também verificamos o potencial da FC de ser um biomarcadorpara identificar o indivíduo (acurácia de aproximadamente 18%, p= 0,001). Assim, concluímos quea FC apresenta informações sobre os estados mentais.
Title in English
Classification of subject-driven cognitive states based on heart rate variability
Keywords in English
Biomarker
Classification
Cognitive state
Electrocardiogram
Heart rate variability
Abstract in English
Brain decodification has gained much attention over the last decades. The first studies were ba-sed on discrete events. Recently, methods for decoding more continuous and purely subject-drivencognitive states have been developed. However, all of them require expensive, difficult to handle,and uncomfortable devices for daily use. Here we propose an alternative based on heart rate (HR).It is already well known that we can discriminate some physical activities based on HR. However,the not intuitive question is, can we discriminate cognitive tasks based on HR? We submitted 25subjects to four cognitive tasks: resting quietly, remembering their days events, singing lyrics, orsubtracting numbers. We collected the electrocardiogram twice for each individual, separated byapproximately one week. To collect the HR, we used a commercial chest sensor band used by athle-tes. We trained a support vector machine using data collected on day one. Then we validated it inthe dataset collected on day two. Our results show accuracy more significant than what we expectat random (p <0.001). Depending on the individual and set of cognitive tasks, we obtained almost100% accuracy. We also verified the HRs potential to be a biomarker to identify the individual (ac-curacy of approximately 18%,p= 0.001). Altogether, we conclude the HR presents mental statesinformation and can help for daily use in the future.
 
WARNING - Viewing this document is conditioned on your acceptance of the following terms of use:
This document is only for private use for research and teaching activities. Reproduction for commercial use is forbidden. This rights cover the whole data about this document as well as its contents. Any uses or copies of this document in whole or in part must include the author's name.
Publishing Date
2021-09-03
 
WARNING: Learn what derived works are clicking here.
All rights of the thesis/dissertation are from the authors
CeTI-SC/STI
Digital Library of Theses and Dissertations of USP. Copyright © 2001-2024. All rights reserved.