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

Using context mapping for planning implementation of movement behavior change in physiotherapy.

BMC health services research·2025

Same author

Examining the Gaze Behaviour and Decision-Making of Field Hockey Players In Situ.

European journal of sport science·2025

Same author

Development and evaluation of the keep moving support tool: Empowering self-management and patient-centred interventions for sustained physical activity.

Patient education and counseling·2025

Same author

Development of the Food Boost Challenge: A Participatory Action Research Approach to Enhance Vegetable and Fruit Consumption among Adolescents.

Nutrients·2023

Same author

Evaluation of a school-based multicomponent behavioural intervention in deprived urban areas for children classified as overweight, obese or at risk for overweight.

BMC research notes·2021

Same author

Understanding Vocational Students' Motivation for Dietary and Physical Activity Behaviors.

International journal of environmental research and public health·2021

Search research articles

Related Experiment Video

Updated: Jun 3, 2026

Artificial Intelligence-Based System for Detecting Attention Levels in Students

Artificial Intelligence-Based System for Detecting Attention Levels in Students

Published on: December 15, 2023

Identification of children's activity type with accelerometer-based neural networks.

Sanne I de Vries¹, Marjolein Engels, Francisca Galindo Garre

¹TNO, Leiden, The Netherlands. sanne.devries@tno.nl

Medicine and Science in Sports and Exercise

|March 31, 2011

Summary

Artificial neural network (ANN) models effectively identify children's physical activities using hip-worn accelerometers. Triaxial sensors on the hip provided the highest accuracy for classifying movements like running and cycling.

More Related Videos

Physical Activity Measurement in Children Accepting Table Tennis Training

Physical Activity Measurement in Children Accepting Table Tennis Training

Published on: July 27, 2022

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

Published on: October 4, 2015

Related Experiment Videos

Last Updated: Jun 3, 2026

Artificial Intelligence-Based System for Detecting Attention Levels in Students

Artificial Intelligence-Based System for Detecting Attention Levels in Students

Published on: December 15, 2023

Physical Activity Measurement in Children Accepting Table Tennis Training

Physical Activity Measurement in Children Accepting Table Tennis Training

Published on: July 27, 2022

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

Published on: October 4, 2015

Area of Science:

Pediatrics
Biomedical Engineering
Sports Science

Background:

Accurate assessment of children's physical activity is crucial for understanding health behaviors.
Wearable sensor technology, like accelerometers, offers objective measurement of movement patterns.
Developing robust algorithms is key to interpreting complex accelerometer data in pediatric populations.

Purpose of the Study:

To evaluate the efficacy of artificial neural network (ANN) models in classifying children's physical activities.
To compare the performance of ANN models using uniaxial versus triaxial accelerometer data.
To determine the optimal placement (hip or ankle) for accelerometers in children's activity recognition.

Main Methods:

Fifty-eight children (9-12 years) performed seven activities (sitting, standing, walking, running, rope skipping, soccer, cycling) in a field setting.
Uniaxial and triaxial ActiGraph accelerometers were worn on both the hip and ankle.
Four ANN models were trained using signal characteristics (percentiles, deviation, variability, autocorrelation) and validated using leave-one-subject-out cross-validation.

Main Results:

ANN models using hip-mounted accelerometers achieved higher classification accuracy (72% uniaxial, 77% triaxial) than ankle-mounted ones (57% uniaxial, 68% triaxial).
Hip models excelled at identifying walking, rope skipping, and running, while ankle models were better for sitting.
Triaxial data from the hip yielded superior classification for standing, running, rope skipping, soccer, and cycling compared to uniaxial data.

Conclusions:

Artificial neural network models show significant promise for classifying physical activities in children using accelerometer data.
The combination of triaxial accelerometer data and hip placement offers the most accurate method for children's physical activity classification.
This approach can enhance objective monitoring and analysis of physical activity in pediatric research and interventions.