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

Editorial: Technological Advances for Gait and Balance Assessment.

Bioengineering (Basel, Switzerland)·2026

Same author

Use of Wearable Technology for Measuring and Characterizing Sedentary Behavior in People With Mild Cognitive Impairment and Dementia: Systematic Review.

JMIR aging·2026

Same author

Wearable sensor technology and machine learning for anterior cruciate ligament injury diagnosis: an exploratory feasibility study.

BMJ open·2026

Same author

Deep learning for freezing of gait assessment using inertial measurement units: a multicentre validation study.

NPJ Parkinson's disease·2026

Same author

Wearable- and Mobile App-Based Activity Pacing and Fatigue Management in Post-COVID-19 Condition: Exploratory Observational Study.

JMIR formative research·2026

Same author

Laboratory-based turning performance during walking in people with mild cognitive impairment and dementia.

Journal of Alzheimer's disease : JAD·2026

Same journal

RETRACTED: Zhang et al. A Novel Framework for Reconstruction and Imaging of Target Scattering Centers via Wide-Angle Incidence in Radar Networks. <i>Sensors</i> 2025, <i>25</i>, 6802.

Sensors (Basel, Switzerland)·2026

Same journal

Enhancing Unsupervised Multi-Source Domain Adaptation for Person Re-Identification via Mixture of Experts and Graph-Based Relation.

Sensors (Basel, Switzerland)·2026

Same journal

Development of an Instrumented Glove for Palmar Pressure Assessment in Kayakers.

Sensors (Basel, Switzerland)·2026

Same journal

Development and Experimental Validation of an Autonomous IoT-Based Monitoring System for Real-Time Water Quality Assessment in the Amazon River.

Sensors (Basel, Switzerland)·2026

Same journal

Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection.

Sensors (Basel, Switzerland)·2026

Same journal

Smart Optimization Method for Safety Signs in Innovative Manufacturing Environments Integrating Industrial Field IoT Sensors and Knowledge Graphs.

Sensors (Basel, Switzerland)·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Feb 28, 2026

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

Neural Network-Based Granular Activity Recognition from Accelerometers: Assessing Generalizability Across Diverse

Metin Bicer^1,2, James Pope³, Lynn Rochester^1,2

¹Translational and Clinical Research Institute, Faculty of Medical Sciences, Newcastle University, Newcastle upon Tyne NE1 7RU, UK.

Sensors (Basel, Switzerland)

|February 27, 2026

Summary

This summary is machine-generated.

This study shows gated recurrent units excel at human activity recognition (HAR) using wearable sensors, achieving high accuracy across different age groups. Combining diverse training data further boosts performance for older adults.

Keywords:

deep learning human activity recognition wearable sensor

More Related Videos

Simulation of Human-induced Vibrations Based on the Characterized In-field Pedestrian Behavior

Simulation of Human-induced Vibrations Based on the Characterized In-field Pedestrian Behavior

Published on: April 13, 2016

Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease

Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease

Published on: July 24, 2019

Related Experiment Videos

Last Updated: Feb 28, 2026

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

Simulation of Human-induced Vibrations Based on the Characterized In-field Pedestrian Behavior

Simulation of Human-induced Vibrations Based on the Characterized In-field Pedestrian Behavior

Published on: April 13, 2016

Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease

Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease

Published on: July 24, 2019

Area of Science:

Biomedical Engineering
Computer Science
Gerontology

Background:

Human activity recognition (HAR) is crucial for digital healthcare, but traditional methods struggle with real-world data variability and cross-cohort generalization.
Adapting HAR systems to diverse populations, like young versus old cohorts, remains a significant challenge.

Purpose of the Study:

To investigate HAR using wearable sensor data with a focus on cross-cohort evaluation between young and old individuals.
To assess the impact of neural network architecture, sampling frequency, and sensor location on HAR performance.
To identify robust methods for real-world activity recognition applicable across different age groups.

Main Methods:

Utilized accelerometer data from thigh and lower back sensors (50 Hz) capturing daily activities, synchronized with video recordings.
Trained neural networks, specifically gated recurrent units (GRUs), on young cohort data and tested on older cohort data.
Evaluated performance using accuracy, recall, precision, F1-score, and confusion matrices, analyzing effects of network architecture, sampling frequency, and sensor placement.

Main Results:

The gated recurrent unit architecture demonstrated superior performance, achieving a weighted F1-score of 0.95 ± 0.05 for young and 0.93 ± 0.05 for old cohorts.
Thigh-mounted sensors generally outperformed lower back sensors, except for the 'lying' activity.
Combining datasets significantly improved performance on the old cohort (weighted F1-score: 0.97 ± 0.02) by increasing training data variability.

Conclusions:

Neural networks, particularly GRUs, offer a highly generalizable approach for robust HAR across age cohorts.
Network architecture and dataset composition are critical factors for successful HAR.
Wearable sensor-based HAR shows significant potential for digital healthcare applications, especially when accounting for cohort diversity.