Wearable Physiological Signals under Acute Stress and Exercise Conditions

Abstract In this work, a novel dataset containing physiological signals recorded non invasevely during structured acute stress induction, as well as aerobic and anaerobic exercise sessions is presented. The physiological data were collected using the Empatica E4, a wearable device that measures elec...

Full description

Saved in:
Bibliographic Details
Main Authors: Andrea Hongn, Facundo Bosch, Lara Eleonora Prado, José Manuel Ferrández, María Paula Bonomini
Format: Article
Language:English
Published: Nature Portfolio 2025-03-01
Series:Scientific Data
Online Access:https://doi.org/10.1038/s41597-025-04845-9
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849688395535613952
author Andrea Hongn
Facundo Bosch
Lara Eleonora Prado
José Manuel Ferrández
María Paula Bonomini
author_facet Andrea Hongn
Facundo Bosch
Lara Eleonora Prado
José Manuel Ferrández
María Paula Bonomini
author_sort Andrea Hongn
collection DOAJ
description Abstract In this work, a novel dataset containing physiological signals recorded non invasevely during structured acute stress induction, as well as aerobic and anaerobic exercise sessions is presented. The physiological data were collected using the Empatica E4, a wearable device that measures electrodermal activity, skin temperature, three-axis accelerometry and blood volume pulse, from which heart rate and heart rate variability features can be derived. A stress induction protocol was designed using mathematical and emotional tasks to elicit physiological responses. For aerobic and anaerobic exercise, a stationary bike routine was developed to distinguish between the two types of activity. The dataset includes records from 36 healthy individuals during the stress protocol, 30 during aerobic exercise, and 31 during anaerobic exercise. Several machine learning algorithms were applied to validate the dataset, with XGBoost achieving an accuracy of 93% in classifying stress versus rest, 91% in distinguishing between aerobic and anaerobic exercise, and 84% in a four-label classification task involving stress, rest, aerobic, and anaerobic activities. The dataset is publicly available for further research.
format Article
id doaj-art-d258ca244b7b4b4d9269354ce5db16dc
institution DOAJ
issn 2052-4463
language English
publishDate 2025-03-01
publisher Nature Portfolio
record_format Article
series Scientific Data
spelling doaj-art-d258ca244b7b4b4d9269354ce5db16dc2025-08-20T03:22:00ZengNature PortfolioScientific Data2052-44632025-03-0112111010.1038/s41597-025-04845-9Wearable Physiological Signals under Acute Stress and Exercise ConditionsAndrea Hongn0Facundo Bosch1Lara Eleonora Prado2José Manuel Ferrández3María Paula Bonomini4Universidad de Buenos Aires. Facultad de Ingeniería, Instituto de Ingeniería Biomédica (IIBM)Departamento de Ciencias de la Vida, Instituto Tecnológico de Buenos Aires (ITBA)Departamento de Ciencias de la Vida, Instituto Tecnológico de Buenos Aires (ITBA)Departamento de Electrónica, Tecnología de Computadoras y Proyectos, Universidad Politécnica de CartagenaInstituto Argentino de Matemática “Alberto P. Calderón” (IAM), CONICETAbstract In this work, a novel dataset containing physiological signals recorded non invasevely during structured acute stress induction, as well as aerobic and anaerobic exercise sessions is presented. The physiological data were collected using the Empatica E4, a wearable device that measures electrodermal activity, skin temperature, three-axis accelerometry and blood volume pulse, from which heart rate and heart rate variability features can be derived. A stress induction protocol was designed using mathematical and emotional tasks to elicit physiological responses. For aerobic and anaerobic exercise, a stationary bike routine was developed to distinguish between the two types of activity. The dataset includes records from 36 healthy individuals during the stress protocol, 30 during aerobic exercise, and 31 during anaerobic exercise. Several machine learning algorithms were applied to validate the dataset, with XGBoost achieving an accuracy of 93% in classifying stress versus rest, 91% in distinguishing between aerobic and anaerobic exercise, and 84% in a four-label classification task involving stress, rest, aerobic, and anaerobic activities. The dataset is publicly available for further research.https://doi.org/10.1038/s41597-025-04845-9
spellingShingle Andrea Hongn
Facundo Bosch
Lara Eleonora Prado
José Manuel Ferrández
María Paula Bonomini
Wearable Physiological Signals under Acute Stress and Exercise Conditions
Scientific Data
title Wearable Physiological Signals under Acute Stress and Exercise Conditions
title_full Wearable Physiological Signals under Acute Stress and Exercise Conditions
title_fullStr Wearable Physiological Signals under Acute Stress and Exercise Conditions
title_full_unstemmed Wearable Physiological Signals under Acute Stress and Exercise Conditions
title_short Wearable Physiological Signals under Acute Stress and Exercise Conditions
title_sort wearable physiological signals under acute stress and exercise conditions
url https://doi.org/10.1038/s41597-025-04845-9
work_keys_str_mv AT andreahongn wearablephysiologicalsignalsunderacutestressandexerciseconditions
AT facundobosch wearablephysiologicalsignalsunderacutestressandexerciseconditions
AT laraeleonoraprado wearablephysiologicalsignalsunderacutestressandexerciseconditions
AT josemanuelferrandez wearablephysiologicalsignalsunderacutestressandexerciseconditions
AT mariapaulabonomini wearablephysiologicalsignalsunderacutestressandexerciseconditions