E. Sazonov, P. Lopez-Meyer, S. Tiffany, accepted to Journal of Studies on Alcohol and Drugs.


Objective: Available methods of smoking assessment (e.g., self-report, portable puff-topography instruments) do not permit the collection of accurate measures of smoking behavior while minimizing reactivity to the assessment procedure. This paper suggests a new method for monitoring of cigarette smoking based on a wearable sensor system (Personal Automatic Cigarette Tracker – PACT) that is completely transparent to the end user and does not require any conscious effort to achieve reliable monitoring of smoking in free-living individuals.
Method: The proposed sensor system consists of a Respiratory Inductive Plethysmograph for monitoring of breathing and a hand gesture sensor for detecting a cigarette at the mouth. The wearable sensor system was tested in a laboratory study of 20 individuals that performed 12 different activities including cigarette smoking. Signal processing was applied to evaluate uniqueness of breathing patterns and their correlation with hand gestures.
Results: The results indicate that smoking manifests unique breathing patterns that are highly correlated with the hand-to-mouth cigarette gestures and suggest that these signals can potentially be used to identify and characterize individual smoke inhalations.
Conclusions: With future development of signal processing and pattern recognition methods, PACT can be used to automatically assess the frequency of smoking and inhalation patterns (such as depth of inhalation and smoke holding) throughout the day and provide an objective method of assessing the effectiveness of behavioral and pharmacological smoking interventions.