Abstract
Recent researches have demonstrated the feasibility of detecting smoking from wearable sensors, but their performance on real-life smoking lapse detection is unknown. In this paper, we propose a new model and evaluate its performance on 61 newly abstinent smokers for detecting a first lapse. We use two wearable sensors - breathing pattern from respiration and arm movements from 6-Axis inertial sensors worn on wrists. In 10-fold cross-validation on 40 hours of training data from 6 daily smokers, our model achieves a recall rate of 96.9%, for a false positive rate of 1.1%. When our model is applied to 3 days of post-quit data from 32 lapsers, it correctly pinpoints the timing of first lapse in 28 participants. Only 2 false episodes are detected on 20 abstinent days of these participants. When tested on 84 abstinent days from 28 abstainers, the false episode per day is limited to 1/6.
Original language | English (US) |
---|---|
Title of host publication | UbiComp 2015 - Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing |
Publisher | Association for Computing Machinery, Inc |
Pages | 999-1010 |
Number of pages | 12 |
ISBN (Electronic) | 9781450335744 |
DOIs | |
State | Published - Sep 7 2015 |
Externally published | Yes |
Event | 3rd ACM International Joint Conference on Pervasive and Ubiquitous Computing, UbiComp 2015 - Osaka, Japan Duration: Sep 7 2015 → Sep 11 2015 |
Publication series
Name | UbiComp 2015 - Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing |
---|
Other
Other | 3rd ACM International Joint Conference on Pervasive and Ubiquitous Computing, UbiComp 2015 |
---|---|
Country/Territory | Japan |
City | Osaka |
Period | 9/7/15 → 9/11/15 |
Bibliographical note
Publisher Copyright:© ACM 978-1-4503-3574-4/15/09..15.00.
Keywords
- Mobile health (mHealth)
- Smartwatch
- Smoking cessation
- Smoking detection
- Wearable sensors