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

'Not Just Bad Periods': Survey of Aotearoa New Zealand Endometriosis Patients on Their Perspectives on the Impact of Endometriosis Awareness.

The Australian & New Zealand journal of obstetrics & gynaecology·2026

Same author

Nursing care for patients with endometriosis in Aotearoa New Zealand: a survey study.

Journal of research in nursing : JRN·2026

Same author

Commercial cannabis product testing: Fidelity to labels and regulations.

PloS one·2026

Same author

Endometriosis and the Hallmarks of Cancer.

Reproductive sciences (Thousand Oaks, Calif.)·2025

Same author

Evidence of spontaneous mentalizing in children with Cornelia de Lange and fragile X syndromes, but not autistic children.

Oxford open neuroscience·2025

Same author

Pupillary dynamics as a marker of acute cannabis inhalation.

Clinical toxicology (Philadelphia, Pa.)·2025

Search research articles

Related Experiment Video

Updated: Apr 30, 2026

Trajectory Data Analyses for Pedestrian Space-time Activity Study

Trajectory Data Analyses for Pedestrian Space-time Activity Study

Published on: February 25, 2013

Identifying Active Travel Behaviors in Challenging Environments Using GPS, Accelerometers, and Machine Learning

Katherine Ellis¹, Suneeta Godbole², Simon Marshall²

¹Department of Electrical and Computer Engineering, University of California San Diego , La Jolla, CA , USA.

Frontiers in Public Health

|May 6, 2014

Summary

Automated methods using machine learning accurately predict active travel modes like walking and bicycling from GPS and accelerometer data. This improves physical activity research by overcoming limitations of traditional measurement techniques.

Keywords:

physical activity random forest

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

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: Apr 30, 2026

Trajectory Data Analyses for Pedestrian Space-time Activity Study

Trajectory Data Analyses for Pedestrian Space-time Activity Study

Published on: February 25, 2013

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

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:

Physical Activity and Public Health
Transportation Science
Machine Learning Applications

Background:

Objective measurement of active travel remains a challenge in physical activity research.
Automated methods are crucial for advancing the study of travel behaviors.
Existing methods often misclassify certain active travel modes.

Purpose of the Study:

To present a supervised machine learning method for transportation mode prediction.
To utilize global positioning system (GPS) and accelerometer data for automated travel behavior analysis.
To enhance the accuracy of active travel measurement.

Main Methods:

Collected 150 hours of GPS and accelerometer data from prescribed trips.
Extracted 49 features from 1-minute data windows.
Employed a random forest algorithm and a moving average output filter for classification.

Main Results:

The random forest algorithm achieved 89.8% cross-validated accuracy.
Incorporating a moving average filter improved accuracy to 91.9%.
The model demonstrated high performance in classifying various transportation modes.

Conclusions:

Machine learning offers a viable approach for automating active travel measurement.
This method accurately classifies modes like bicycling and vehicle travel, often misclassified by traditional techniques.
Automated measurement enhances the reliability and scope of physical activity research.