puffMarker: a multi-sensor approach for pinpointing the timing of first lapse in smoking cessation

@article{Saleheen2015puffMarkerAM,
  title={puffMarker: a multi-sensor approach for pinpointing the timing of first lapse in smoking cessation},
  author={Nazir Saleheen and Amin Ahsan Ali and Syed Monowar Hossain and Hillol Sarker and Soujanya Chatterjee and Benjamin M. Marlin and Emre Ertin and Mustafa al'Absi and Santosh Kumar},
  journal={Proceedings of the ... ACM International Conference on Ubiquitous Computing . UbiComp},
  year={2015},
  volume={2015},
  pages={
          999-1010
        }
}
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… CONTINUE READING

Figures, Tables, Results, and Topics from this paper.

Key Quantitative Results

  • 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%.
  • 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%.

Citations

Publications citing this paper.
SHOWING 1-10 OF 40 CITATIONS

Machine Learning Methods for Activity Detection in Wearable Sensor Data Streams

VIEW 10 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Detecting Eating and Smoking Behaviors Using Smartwatches

  • Mobile Health - Sensors, Analytic Methods, and Applications
  • 2017
VIEW 10 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

A hierarchical lazy smoking detection algorithm using smartwatch sensors

  • 2016 IEEE 18th International Conference on e-Health Networking, Applications and Services (Healthcom)
  • 2016
VIEW 5 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Chronodes: Interactive Multifocus Exploration of Event Sequences

VIEW 4 EXCERPTS
CITES METHODS, BACKGROUND & RESULTS
HIGHLY INFLUENCED

mCrave: continuous estimation of craving during smoking cessation

VIEW 3 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

References

Publications referenced by this paper.
SHOWING 1-5 OF 5 REFERENCES

Actual causes of death

A. Mokdad, J. Marks, D. Stroup, J. Gerberding
  • in the united states,
  • 2000
VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

First lapses to smoking: within-subjects analysis of real-time reports.

  • Journal of consulting and clinical psychology
  • 1996
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Similar Papers

Loading similar papers…