Wearable sensor systems to study the physiological and behavioral manifestation of cigarette smoking in free-living

Show simple item record

dc.contributor Sazonov, Edward
dc.contributor Hu, Fei
dc.contributor Song, Aijun
dc.contributor Shen, Xiangrong
dc.contributor Tiffany, Stephen
dc.contributor.advisor Sazonov, Edward
dc.contributor.author Imtiaz, Masudul
dc.date.accessioned 2020-01-16T15:03:33Z
dc.date.available 2020-01-16T15:03:33Z
dc.date.issued 2019
dc.identifier.other u0015_0000001_0003391
dc.identifier.other Imtiaz_alatus_0004D_13924
dc.identifier.uri http://ir.ua.edu/handle/123456789/6448
dc.description Electronic Thesis or Dissertation
dc.description.abstract Worldwide, cigarette smoking is one of the major causes of preventable death. A single cigarette contains more than a hundred toxins that have detrimental effects on the smoker himself and the people in his or her surroundings. Despite knowledge of these harms, smokers often struggle to quit. Accurate information on daily smoking might help for evaluating the smoking behavior of an individual and the effectiveness of related intervention process. Self-reporting, puff topography meters, and biomarkers are the primary tools available for the estimation of daily cigarette consumption. However, these methods have been proved to be either biased, inaccurate, obtrusive, or not suitable for all smokers. Thus, there was a need for the development of solutions for objective, accurate and automatic detection of cigarette smoking, especially under free-living conditions. This dissertation proposes new wearable sensor systems and related signal/image processing and pattern recognition methods for the objective, accurate and automatic detection of cigarette smoking with minimal effort from the person being observed. Main accomplishments of this dissertation are a) development and validation of a novel multi-sensory wearable system (Personal Automatic Cigarette Tracker v2 aka PACT 2.0) to facilitate studying the behavioral and physiological manifestations of cigarette smoking. The validation study involving forty participants suggests that this wearable system presents a reliable platform for collecting objective information on smoking behavior in the free-living; b) development and validation of a method to identify smoking events from the associated changes in heart rate parameters of the wearer. The proposed method also accounts for the breathing rate and body motion of the smoker to better distinguish these changes from intense physical activities. The validation study involving twenty participants suggests that these physiological parameters could be a useful indicator of cigarette smoking even in the free-living; c) validation of a wearable egocentric camera system to capture minute details of smoking events from the eye-level such as hand to mouth gestures during smoking puff, smoking environment, body posture or activities during smoking, etc. The human study involving ten participants demonstrates that this novel sensor system may facilitate the objective monitoring of cigarette smoking, categorizing smoking environment, and obtaining an overview of the smoking habit in free-living; d) development and validation of computer models to automatically extract behavioral metrics of cigarette smoking (such as smoking time of day, frequency, inter-cigarette interval, etc.) from images captured by the egocentric camera. The validation study performed on a large free-living image set shows the applicability of proposed models to extract an objective summary of daily smoking.
dc.format.extent 187 p.
dc.format.medium electronic
dc.format.mimetype application/pdf
dc.language English
dc.language.iso en_US
dc.publisher University of Alabama Libraries
dc.relation.ispartof The University of Alabama Electronic Theses and Dissertations
dc.relation.ispartof The University of Alabama Libraries Digital Collections
dc.relation.hasversion born digital
dc.rights All rights reserved by the author unless otherwise indicated.
dc.subject.other Electrical engineering
dc.title Wearable sensor systems to study the physiological and behavioral manifestation of cigarette smoking in free-living
dc.type thesis
dc.type text
etdms.degree.department University of Alabama. Department of Electrical and Computer Engineering
etdms.degree.discipline Electrical and Computer Engineering
etdms.degree.grantor The University of Alabama
etdms.degree.level doctoral
etdms.degree.name Ph.D.

Files in this item

This item appears in the following Collection(s)

Show simple item record

Search DSpace


My Account