Significant Physiological Features to Identify High Performance States

Pelaez Coca, María Dolores ; Lozano Albalate, María Teresa ; Aiger, Montserrat ; Hernando, Alberto ; Gil, Eduardo (Universidad de Zaragoza)

Resumen: Our long-term goal is the development of an automaticidentifier of attentional states. In order to accomplish it, we should firstly be able to identify different states. So, the first aim of this work is to identify the most appropriate features, to detect a subject high performance state. For that, a database of electrocardiographic (ECG) signal of two unequivocally defined states (rest and attention task) is needed. To achieve this goal, ECG signal is recorded, in those cognitive states from up to 54 subjects as a sample of the population.
Temporal and frequency parameters of heart rate variability have been computed from ECG signal. Additionally, the respiratory rate has been estimated from the same signal. In total, ten features are obtained for each subject. They provide information about the physiological response of the subject and about his autonomic nervous system. Results show that eight from these features present significant differences between subject’s baseline and subject’s attentional state; and selecting only four of them, state classification accuracy reaches a mean of 75.91%.

Idioma: Inglés

DOI: 10.22489/cinc.2017.280-141

Año: 2018

Publicado en: Computing in Cardiology 44 (2018), [4 pp.]
ISSN: 2325-8861

Factor impacto SCIMAGO: 0.202 - Computer Science (miscellaneous) - Cardiology and Cardiovascular Medicine

Financiación: info:eu-repo/grantAgreement/ES/DGA/T04-FSE
Financiación: info:eu-repo/grantAgreement/ES/MINECO/TEC2014-54143-P
Financiación: info:eu-repo/grantAgreement/ES/MINECO/TIN2014-5356-R
Financiación: info:eu-repo/grantAgreement/ES/UZ/CUD2013-11
Financiación: info:eu-repo/grantAgreement/ES/UZ/CUD2016-TEC-03
Financiación: info:eu-repo/grantAgreement/ES/UZ/CUD2016-18

Tipo y forma: Article (Published version)

Área (Departamento): Área Ingen.Sistemas y Automát. (Dpto. Informát.Ingenie.Sistms.)