Wearable Smoking Detection

Tobacco is the only legally available consumer product which kills people when entirely used as intended. Quitting to smoke is however extremely hard. This project is about quantifying one's personal smoking behaviour in an inconspicuous way. A smoker can gain insight into his smoking triggers, gain more insights about his addiction and get personalized smoking cessation material.

We investigate different ways of tracking smoking behaviour. Using inertial sensors worn on the wrist, its motion allows to detect typical hand-to-mouth gestures. This is even possible for multiple days on a single battery charge. Alternatively a Smart Lighter, a lighter that can track whenever it is lit, provides the same data without having to wear a sensor on the wrist.

The gathered smoking data is used to provide personalized smoking cessation information on a mobile device. This includes personal statistics, but also information which led others with a similar profile to reduce or quit smoking - efficient smoking cessation material can be detected automatically. The objective quantification of smoking behaviour is also used to test the efficacy of smoking interventions.


When Do You Light a Fire? Capturing Tobacco Use with Situated, Wearable Sensors, Philipp M. Scholl and Nagihan Kücükyildiz and Van Laerhoven, Kristof. In First Workshop on Human Factors and Activity Recognition in Healthcare, Wellness and Assisted Living (Recognize2Interact), ACM Press, 09/2013, 2013. [pdf] [scholar] [bibtex]

Bridging the Last Gap: LedTX - Optical Data Transmission of Sensor Data for Web-Services, Philipp M. Scholl and Nagihan Kücükyildiz and Van Laerhoven, Kristof. In Proceedings of the 2013 ACM conference on Pervasive and ubiquitous computing adjunct publication., ACM Press, 09/2013, 2013. [pdf] [scholar] [bibtex]

A Feasibility Study of Wrist-Worn Accelerometer Based Detection of Smoking Habits, Philipp M. Scholl and Van Laerhoven, Kristof. In esIoT 2012, IEEE Press, 2012. [pdf] [scholar] [bibtex]


Philipp M. Scholl
Log in