Automated detection of puffing and smoking with wrist accelerometers

Qu Tang, Damon J. Vidrine, Eric Crowder, Stephen S. Intille

Research output: Chapter in Book/Report/Conference proceedingConference contribution

38 Scopus citations

Abstract

Real-time, automatic detection of smoking behavior could lead to novel measurement tools for smoking research and "just-in-time" interventions that may help people quit, reducing preventable deaths. This paper discusses the use of machine learning with wrist accelerometer data for automatic puffing and smoking detection. A two-layer smoking detection model is proposed that incorporates both low-level time domain features and high-level smoking topography such as inter-puff intervals and puff frequency to detect puffing then smoking. On a pilot dataset of 6 individuals observed for 11.8 total hours in real-life settings performing complex tasks while smoking, the model obtains a cross validation Fl-score of 0.70 for puffing detection and 0.79 for smoking detection over all participants, and a mean Fl-score of 0.75 for puffing detection with user-specific training data. Unresolved challenges that must still be addressed in this activity detection domain are discussed.

Original languageEnglish (US)
Title of host publicationProceedings - PERVASIVEHEALTH 2014
Subtitle of host publication8th International Conference on Pervasive Computing Technologies for Healthcare
EditorsSusanne Boll, Friedrich Kohler
PublisherICST
Pages80-87
Number of pages8
ISBN (Electronic)9781631900112
DOIs
StatePublished - Jul 23 2014
Event8th International Conference on Pervasive Computing Technologies for Healthcare, PERVASIVEHEALTH 2014 - Oldenburg, Germany
Duration: May 20 2014May 23 2014

Publication series

NameProceedings - PERVASIVEHEALTH 2014: 8th International Conference on Pervasive Computing Technologies for Healthcare

Other

Other8th International Conference on Pervasive Computing Technologies for Healthcare, PERVASIVEHEALTH 2014
Country/TerritoryGermany
CityOldenburg
Period5/20/145/23/14

Keywords

  • Behavior recognition
  • Cigarette
  • Health
  • Random forest
  • Real-time
  • Smoking
  • Supervised learning
  • Ubiquitous computing

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Science Applications
  • Information Systems
  • Health Informatics

Fingerprint

Dive into the research topics of 'Automated detection of puffing and smoking with wrist accelerometers'. Together they form a unique fingerprint.

Cite this