Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Leveraging imperfection with MEDLEY: a multi-model approach harnessing bias in medical AI.

Frontiers in artificial intelligence·2026

Same author

HealthProcessAI: a technical framework and proof-of-concept for LLM-enhanced healthcare process mining.

Frontiers in artificial intelligence·2026

Same author

Data Poisoning Vulnerabilities Across Health Care Artificial Intelligence Architectures: Analytical Security Framework and Defense Strategies.

Journal of medical Internet research·2026

Same author

Editorial: Editorial on multidimensional physiology: novel techniques and discoveries with bioimpedance measurements, volume II.

Frontiers in physiology·2025

Same author

Longitudinal trajectories unravel the complex interplay of medication, cardiovascular events, chronic kidney disease, and mortality.

Scientific reports·2025

Same author

Smart Textile Technology for the Monitoring of Mental Health.

Sensors (Basel, Switzerland)·2025

Search research articles

Related Experiment Video

Updated: Jan 1, 2026

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

Activity Recognition Using Wearable Physiological Measurements: Selection of Features from a Comprehensive Literature

Inma Mohino-Herranz¹, Roberto Gil-Pita¹, Manuel Rosa-Zurera¹

¹Department of Signal Theory and Communications, University of Alcala, 28805 Alcala de Henares, Madrid, Spain.

Sensors (Basel, Switzerland)

|December 19, 2019

Summary

This summary is machine-generated.

This study analyzes physiological signals for activity and emotion recognition in healthcare. It identifies the optimal 40 features for accurate recognition, achieving a 22.2% error rate.

Keywords:

activity recognition electrocardiogram electrodermal activity physiological signals thoracic electrical bioimpedance

More Related Videos

Assessing the Accuracy of Fitness Smartwatch Data for Cardiovascular and Physical Activity Monitoring: A Validation Study in Digital Health

Assessing the Accuracy of Fitness Smartwatch Data for Cardiovascular and Physical Activity Monitoring: A Validation Study in Digital Health

Published on: February 21, 2025

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment

Published on: December 11, 2015

Related Experiment Videos

Last Updated: Jan 1, 2026

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

Assessing the Accuracy of Fitness Smartwatch Data for Cardiovascular and Physical Activity Monitoring: A Validation Study in Digital Health

Assessing the Accuracy of Fitness Smartwatch Data for Cardiovascular and Physical Activity Monitoring: A Validation Study in Digital Health

Published on: February 21, 2025

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment

Published on: December 11, 2015

Area of Science:

Physiological signal processing
Healthcare applications
Biomedical engineering

Background:

Activity and emotion recognition using physiological signals is crucial for healthcare.
Applications include workplace health monitoring and preventive care.
Electrocardiogram, thoracic electrical bioimpedance, and electrodermal activity signals are key data sources.

Purpose of the Study:

To deeply analyze features for extracting information from physiological signals.
To identify the optimal subset of features for activity recognition.
To determine the best number of features to minimize error probability and avoid overfitting.

Main Methods:

Comprehensive analysis of 533 features for activity recognition (neutral, emotional, mental, physical).
Evaluation considering prediction accuracy, feature calculation, window length, and classifier type.
Feature selection using a genetic algorithm to identify the most relevant features.

Main Results:

The study identified the optimal number of features and the best subset for activity recognition.
A minimum error probability of 22.2% was achieved.
Optimal conditions included 40 features, a least squares error classifier, and a 40-second window length.

Conclusions:

Feature selection is vital for accurate physiological signal-based activity recognition.
The identified feature subset and parameters offer a robust approach for healthcare applications.
This research contributes to advancing preventive care and workplace health monitoring.