ABSTRACT
Smoking has been conclusively proved to be the leading cause of mortality that accounts for one in five deaths in the United States. Extensive research is conducted on developing effective smoking cessation programs. Most smoking cessation programs achieve low success rate because they are unable to intervene at the right moment. Identification of high-risk situations that may lead an abstinent smoker to relapse involve discovering the associations among various contexts that precede a smoking session or a smoking lapse. In the absence of an automated method, detection of smoking events still relies on subject self-report that is prone to failure to report and involves subject burden. Automated detection of smoking events in the natural environment can revolutionize smoking research and lead to effective intervention.
In this paper, we present mpuff, a novel system to automatically detect smoking puffs from respiration measurements, using which a model can be developed to automatically detect entire smoking episodes in the field. We introduce several new features from respiration that can help classify individual respiration cycles into smoking puffs or non-puffs. We then propose supervised and semi-supervised support vector models to detect smoking puffs. We train our models on data collected from 10 daily smokers and find that smoking puffs can be detected with an accuracy of 91% within a smoking session. We then consider respiration measurements during confounding events such as stress, speaking, and walking, and show that our model can still identify smoking puffs with an accuracy of 86.7%. The smoking detector presented here opens the opportunity to develop effective interventions that can be delivered on a mobile phone when and where smoking urges may occur, thereby improving the abysmal low rate of success in smoking cessation.
- Smoking-attributable mortality, years of potential life lost, and productivity losses - United States, 2000 - 2004. Morbidity and Mortality Weekly Report, 57(45):1226--1228, 2008.Google Scholar
- Fieldstream. http://www.github.com/FieldStream/FieldStream, Accessed: October 2011.Google Scholar
- How tobacco smoke causes disease - the biology and behavioral basis for smoking-attributable disease - a report of the surgeon general. http://www.surgeongeneral.gov/library/tobaccosmoke/report/index.html, Accessed: October 2011.Google Scholar
- Smokerlyzer. http://www.bedfont.com/smokerlyzer, Accessed: October 2011.Google Scholar
- Substance abuse and mental health administration: Results from the 2009 national survey on drug use and health: National findings. http://www.oas.samhsa.gov/NSDUH/2k9NSDUH/tabs/Cover.pdf, Accessed: October 2011.Google Scholar
- Svmlin. http://vikas.sindhwani.org/svmlin.html, Accessed: October 2011.Google Scholar
- Treating tobacco use and dependence: 2008 update - clinical practice guideline. http://www.surgeongeneral.gov/tobacco/treating_tobacco_use08.pdf, Accessed: October 2011.Google Scholar
- CReSS. http://www.borgwaldt.de/cms/borgwaldt-kc/produkte/rauchmaschinen/geraete-zur-rauchtopographie/cress-pocket.html, Accessed: October 2011.Google Scholar
- H. Ashton, D. Watson, R. Marsh, and J. Sadler. Puffing frequency and nicotine intake in cigarette smokers. The British Medical Journal, pages 679--681, 1970.Google ScholarCross Ref
- C. Bishop. Pattern Recognition and Machine Learning. Springer, 2006. Google ScholarDigital Library
- H. Brendryen, P. Kraft, and H. Schaalma. Looking inside the black box: Using intervention mapping to describe the development of the automated smoking cessation intervention 'happy ending'. The Journal of Smoking Cessation, 5(1):29--56, 2010.Google ScholarCross Ref
- R. Bridges, J. Combs, J. Humble, J. Turbek, S. Rehm, and N. Haley. Puffing topography as a determinant of smoke exposure. Pharmacology Biochemistry and Behavior, 37(1):29--39, 1990.Google ScholarCross Ref
- F. Charles, G. Krautter, and D. Mariner. Post-puff respiration measures on smokers of different tar yield cigarettes. Inhalation toxicology, 21(8):712--718, 2009.Google ScholarCross Ref
- C. Collins, D. Epstein, C. Parzynski, D. Zimmerman, E. Moolchan, and S. Heishman. Puffing behavior during the smoking of a single cigarette in tobacco-dependent adolescents. Nicotine & tobacco research, 12(2):164--167, 2010.Google Scholar
- K. Doherty, T. Kinnunen, F. Militello, and A. Garvey. Urges to smoke during the first month of abstinence: relationship to relapse and predictors. Psychopharmacology, 119(2):171--178, 1995.Google ScholarCross Ref
- E. Ertin, N. Stohs, S. Kumar, A. Raij, M. al'Absi, T. Kwon, S. Mitra, S. Shah, and J. W. Jeong. Autosense: Unobtrusively wearable sensor suite for inferencing of onset, causality, and consequences of stress in the field. In ACM Conference on Embedded Networked Sensor Systems (SenSys), pages 274--287, 2011. Google ScholarDigital Library
- D. Hammond, G. Fong, K. Cummings, and A. Hyland. Smoking topography, brand switching, and nicotine delivery: results from an in vivo study. Cancer Epidemiology Biomarkers & Prevention, 14(6):1370--1375, 2005.Google ScholarCross Ref
- J. Hughes and D. Hatsukami. Signs and symptoms of tobacco withdrawal. Archives of General Psychiatry, 43(3):289, 1986.Google ScholarCross Ref
- N. Hymowitz, M. Sexton, J. Ockene, and G. Grandits.Baseline factors associated with smoking cessation and relapse. Preventive Medicine, 20(5):590--601, 1991.Google ScholarCross Ref
- D. Kalman. The subjective effects of nicotine: methodological issues, a review of experimental studies, and recommendations for future research. Nicotine & Tobacco Research, 4(1):25--70, 2002.Google ScholarCross Ref
- J. Killen and S. Fortmann. Craving is associated with smoking relapse: Findings from three prospective studies. Experimental and Clinical Psychopharmacology, 5(2):137, 1997.Google ScholarCross Ref
- S. Kolonen, J. Tuomisto, P. Puusteinen, and M. Airaksinen. Puffing behavior during the smoking of a single cigarette in a naturalistic environment. Pharmacology, biochemistry and behavior, 41(4):701--706, 1992.Google Scholar
- K. Matheny and K. Weatherman. Predictors of smoking cessation and maintenance. Journal of Clinical Psychology, 54(2):223--235, 1998.Google ScholarCross Ref
- A. Mokdad, J. Marks, D. Stroup, and J. Gerberding. Actual causes of death in the united states, 2000. JAMA: the journal of the American Medical Association, 291(10):1238, 2004.Google Scholar
- K. Plarre, A. Raij, S. M. Hossain, A. A. Ali, M. Nakajima, M. al'Absi, T. Kamarck, S. Kumar, M. Scott, D. Siewiorek, A. Smailagic, and L. E. Wittmers. Continuous inference of psychological stress from sensory measurements collected in the natural environment. In ACM Information Processing in Sensor Networks (IPSN), pages 97--108, 2011.Google Scholar
- M. M. Rahman, A. A. Ali, K. Plarre, M. al'Absi, E. Ertin, and S. Kumar. mconverse: Inferring conversation episodes from respiratory measurements collected in the field. In ACM Wireless Health, 2011. Google ScholarDigital Library
- S. Shiffman. Reections on smoking relapse research. Drug and alcohol review, 25(1):15--20, 2006.Google Scholar
- S. Shiffman, J. Paty, M. Gnys, J. Kassel, and M. Hickcox. First lapses to smoking: Within-subjects analysis of real-time reports. Journal of Consulting and Clinical Psychology, 64(2):366--379, 1996.Google ScholarCross Ref
- S. Shiffman, D. Scharf, W. Shadel, C. Gwaltney, Q. Dang, S. Paton, and D. Clark. Analyzing milestones in smoking cessation: illustration in a nicotine patch trial in adult smokers. Journal of consulting and clinical psychology, 74(2):276--285, 2006.Google Scholar
- S. Shiffman and A. Waters. Negative affect and smoking lapses: A prospective analysis. Journal of Consulting and Clinical Psychology, 72(2):192--201, 2004.Google ScholarCross Ref
- M. Stitzer and J. Gross. Smoking relapse: the role of pharmacological and behavioral factors. Progress in clinical and biological research, 261:163--184, 1988.Google Scholar
- G. Swan, M. Ward, and L. Jack. Abstinence effects as predictors of 28-day relapse in smokers* 1. Addictive Behaviors, 21(4):481--490, 1996.Google ScholarCross Ref
- J. Veilleux, J. Kassel, A. Heinz, A. Braun, M. Wardle, J. Greenstein, D. Evatt, and M. Conrad. Predictors and sequelae of smoking topography over the course of a single cigarette in adolescent light smokers. Journal of Adolescent Health, 48(2):176--181, 2011.Google ScholarCross Ref
- P. Wu, J. Hsieh, J. Cheng, S. Cheng, and S. Tseng. Human smoking event detection using visual interaction clues. In International Conference on Pattern Recognition, pages 4344--4347. IEEE, 2010. Google ScholarDigital Library
- X. Zhu and A. Goldberg. Introduction to Semi-Supervised Learning. Morgan & Claypool Publishers, 2009. Google ScholarDigital Library
Index Terms
- mPuff: automated detection of cigarette smoking puffs from respiration measurements
Recommendations
puffMarker: a multi-sensor approach for pinpointing the timing of first lapse in smoking cessation
UbiComp '15: Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous ComputingRecent 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 ...
Evaluating the ChillFish Biofeedback Game with Children with ADHD
IDC '16: Proceedings of the The 15th International Conference on Interaction Design and ChildrenBreathing exercises have been shown to have multiple benefits for children with Attention Deficit Hyperactivity Disorder (ADHD). However, these children can have issues retaining attention to such an exercise. In this paper we present a study of ...
An Audio-based Hierarchical Smoking Behavior Detection System Based on A Smart Neckband Platform
MOBIQUITOUS 2016: Proceedings of the 13th International Conference on Mobile and Ubiquitous Systems: Computing, Networking and ServicesSmoking behavior detection has attracted much research interest for its significant impact on smokers' physical and mental health. Existing research has shown the potential of using wearable devices for fine-grained smoking puff and session detection by ...
Comments