Mental stress is a physiological state that directly correlates to the quality of life of individuals. Generally speaking, but especially true for disabled or elderly subjects, the assessment of such condition represents a very strong indicator correlated to the difficulties, and, in some case, to the frustration that derives from the execution of a task that results troublesome to be accomplished. This article describes a novel procedure for the assessment of the mental stress level through the use of low invasive wireless wearable devices. The information contained in electrocardiogram, respiratory signal, blood volume pulse, and electroencephalogram was extracted to set up an estimator for the cognitive workload level. A random forest classifier was implemented to assess the level of mental stress starting from a pool of 3481 features computed from the aforementioned physiological quantities. The proposed system was applied in a scenario in which two different mental states were elicited in the subject under investigation: first, a baseline resting condition was induced by the presentation of a relaxing video; then a stressful cognitive state was provoked by the administration of a mental arithmetic task. The random forest classifier shows an accuracy of 97.5% in discerning between these two mental states.

Zanetti, M., Faes, L., De Cecco, M., Fornaser, A., Valente, M., Guandalini, G., et al. (2019). Assessment of mental stress through the analysis of physiological signals acquired from wearable devices. In Ambient Assisted Living (ForItAAL 2018) (pp. 243-256). Springer Verlag [10.1007/978-3-030-05921-7_20].

Assessment of mental stress through the analysis of physiological signals acquired from wearable devices

Faes, Luca;
2019-01-01

Abstract

Mental stress is a physiological state that directly correlates to the quality of life of individuals. Generally speaking, but especially true for disabled or elderly subjects, the assessment of such condition represents a very strong indicator correlated to the difficulties, and, in some case, to the frustration that derives from the execution of a task that results troublesome to be accomplished. This article describes a novel procedure for the assessment of the mental stress level through the use of low invasive wireless wearable devices. The information contained in electrocardiogram, respiratory signal, blood volume pulse, and electroencephalogram was extracted to set up an estimator for the cognitive workload level. A random forest classifier was implemented to assess the level of mental stress starting from a pool of 3481 features computed from the aforementioned physiological quantities. The proposed system was applied in a scenario in which two different mental states were elicited in the subject under investigation: first, a baseline resting condition was induced by the presentation of a relaxing video; then a stressful cognitive state was provoked by the administration of a mental arithmetic task. The random forest classifier shows an accuracy of 97.5% in discerning between these two mental states.
2019
Zanetti, M., Faes, L., De Cecco, M., Fornaser, A., Valente, M., Guandalini, G., et al. (2019). Assessment of mental stress through the analysis of physiological signals acquired from wearable devices. In Ambient Assisted Living (ForItAAL 2018) (pp. 243-256). Springer Verlag [10.1007/978-3-030-05921-7_20].
File in questo prodotto:
File Dimensione Formato  
B07-Zanetti_LectureNotes2018.pdf

Solo gestori archvio

Tipologia: Post-print
Dimensione 1.92 MB
Formato Adobe PDF
1.92 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
faes 2019.pdf

Solo gestori archvio

Tipologia: Versione Editoriale
Dimensione 4 MB
Formato Adobe PDF
4 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10447/352684
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 17
  • ???jsp.display-item.citation.isi??? ND
social impact