Link to the University of Pittsburgh Homepage
Link to the University Library System Homepage Link to the Contact Us Form

Classifying Smoking Urges Via Machine Learning

Dumortier, Antoine (2015) Classifying Smoking Urges Via Machine Learning. Master's Thesis, University of Pittsburgh. (Unpublished)

PDF (Edited version, after corrections)
Updated Version

Download (1MB)


Smoking is the largest preventable cause of death and diseases in the developed world, and advances in modern electronics and machine learning can help us deliver therapies to smokers in novel ways. If a mobile device monitoring a smoker's situation could detect when the smoker is likely to have an urge to smoke, it would be helpful for optimizing the timing of real-time intervention. In this thesis, we examine different machine learning approaches to use situational features associated with having or not having urges to smoke during a quit attempt in order to accurately classify high-urge states. To test our machine learning approaches --specifically naive Bayes, discriminant analysis and decision tree learning methods-- we used a dataset collected from over 300 participants who had recently initiated a quit attempt. The three classification approaches are evaluated observing sensitivity, specificity, accuracy and precision. The outcome of the analysis showed that algorithms based on feature selection make it possible to obtain high classification rates with only a few features selected from the entire dataset. The classification tree method outperformed the naive Bayes and discriminant analysis methods, with an accuracy of the classifications up to 86%.


Social Networking:
Share |


Item Type: University of Pittsburgh ETD
Status: Unpublished
CreatorsEmailPitt UsernameORCID
Dumortier, Antoineand148@pitt.eduAND148
ETD Committee:
TitleMemberEmail AddressPitt UsernameORCID
Committee ChairSejdić, Ervinesejdic@pitt.eduESEJDIC
Committee MemberMao, Zhi-Hongzhm4@pitt.eduZHM4
Committee MemberEl-Jaroudi, Amroamro@pitt.eduAMRO
Date: 9 September 2015
Date Type: Publication
Defense Date: 15 July 2015
Approval Date: 9 September 2015
Submission Date: 16 July 2015
Access Restriction: 5 year -- Restrict access to University of Pittsburgh for a period of 5 years.
Number of Pages: 69
Institution: University of Pittsburgh
Schools and Programs: Swanson School of Engineering > Electrical and Computer Engineering
Degree: MS - Master of Science
Thesis Type: Master's Thesis
Refereed: Yes
Uncontrolled Keywords: smoking urges, smoking cessation, machine learning, supervised learning, discriminant analysis classification, naive Bayes classification, decision tree classification, feature selection
Date Deposited: 09 Sep 2015 20:38
Last Modified: 09 Sep 2020 05:15


Monthly Views for the past 3 years

Plum Analytics

Actions (login required)

View Item View Item