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

Do short-term responses to health warnings about product manipulations predict subsequent quitting-related behaviours? Findings from an Australian cohort study.

Tobacco control·2026

Same author

Awareness and Self-Reported Effects of the Innovative Mexican Front-of-Package Nutrition Labeling Policy Among Mexican Americans Across Different US Regions, Health Literacy Levels, and Educational Attainment, 2021-2023.

American journal of health promotion : AJHP·2026

Same author

'Light at the end of the tunnel': reactions to targeted and generally applicable reduced nicotine policy messages among priority populations of people who smoke.

Tobacco control·2026

Same author

Trends in noticing and responses to cigarette and heated tobacco product warnings among Koreans who use tobacco: findings from the 2020-2023 ITC Korea Surveys.

Tobacco control·2026

Same author

Social Network Determinants of Cigarette Forgoing and Quit-Related Conversations in a 15-Day Ecological Momentary Assessment Study in Mexico and the US.

Tobacco use insights·2026

Same author

Exposure to e-Cigarette Posts Across Social Media Platforms and Its Associations With Susceptibility and e-Cigarette Use: Comparative Cross-Sectional Study of High Schoolers in Jalisco (Mexico) and Southern California (United States).

JMIR pediatrics and parenting·2026

Search research articles

Related Experiment Video

Updated: Feb 17, 2026

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

Detecting Smoking Events Using Accelerometer Data Collected Via Smartwatch Technology: Validation Study.

Casey A Cole¹, Dien Anshari², Victoria Lambert²

¹Computational Biology Research Group, Department of Computer Science, University of South Carolina, Columbia, SC, United States.

JMIR Mhealth and Uhealth

|December 15, 2017

Summary

Smartwatches can accurately detect smoking behavior using machine learning, offering a nonintrusive alternative to self-reporting for smoking cessation studies. This technology enhances data collection for ecological momentary assessment.

Keywords:

automated pattern recognition data mining digital signal processing ecological momentary assessment machine learning neural networks smoking cessation

More Related Videos

Setup of Consumer Wearable Devices for Exposure and Health Monitoring in Population Studies

Setup of Consumer Wearable Devices for Exposure and Health Monitoring in Population Studies

Published on: February 3, 2023

An Application for Pairing with Wearable Devices to Monitor Personal Health Status

An Application for Pairing with Wearable Devices to Monitor Personal Health Status

Published on: February 3, 2022

Related Experiment Videos

Last Updated: Feb 17, 2026

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

Setup of Consumer Wearable Devices for Exposure and Health Monitoring in Population Studies

Setup of Consumer Wearable Devices for Exposure and Health Monitoring in Population Studies

Published on: February 3, 2023

An Application for Pairing with Wearable Devices to Monitor Personal Health Status

An Application for Pairing with Wearable Devices to Monitor Personal Health Status

Published on: February 3, 2022

Area of Science:

Digital Health
Behavioral Science
Machine Learning Applications

Background:

Smoking remains a leading cause of preventable death globally.
Current ecological research on smoking relies on self-reported behavior, which can be inaccurate.
Smartwatch technology offers potential for objective, automated detection of smoking behavior via machine learning.

Purpose of the Study:

To assess the feasibility of using smartwatches to detect smoking behavior.
To compare the accuracy of smartwatch-based smoking detection with traditional self-reporting methods.

Main Methods:

Ten participants recorded 12 hours of accelerometer data using a smartwatch and mobile phone.
Participants logged the start and end times of their smoking sessions.
A machine learning model classified data as smoking or non-smoking, with accuracy compared against logged sessions.

Main Results:

The smartwatch-based model detected 81% of recorded smoking sessions (100/123).
After protocol adherence adjustments, the true positive detection rate exceeded 90%.
A low false positive rate of 2.8% (22/120 hours) was observed.

Conclusions:

Smartwatches provide an accurate and nonintrusive method for monitoring smoking behavior in real-world settings.
Machine learning algorithms for passive smoking detection can enhance ecological momentary assessment and cessation interventions.
This technology allows for more targeted data collection and communication around smoking events compared to self-report.