Recognizing cigarette smoke inhalations using hidden Markov models

Previous studies with the Personal Automatic Cigarette Tracker (PACT) wearable system have found that smoking presents a distinct temporal breathing pattern, which might be well-suited for recognition by hidden Markov models (HMMs). In this work, we explored the feasibility of using HMMs to characterize the temporal information of smoking inhalations contained in the respiratory signals such as tidal volume, airflow, and the signal from the hand-to-mouth proximity sensor. Left-to-right HMMs were built to classify smoking and non-smoking inhalations using either only the respiratory signals, or both respiratory and hand proximity signals. Using a data set of 20 subjects, a leave-one-out cross-validation was performed on each HMM. In the recognition of smoke inhalations, the highest average recall, precision and F-score perceived by the HMMs was 42.39%, 88.19% and 56.38%, respectively, providing a 7.3% improvement in recall against a previously reported Support Vector Machines.

[1]  Dario Pompili,et al.  Laboratory Validation of Inertial Body Sensors to Detect Cigarette Smoking Arm Movements , 2014, Electronics.

[2]  Edward Sazonov,et al.  Monitoring of Cigarette Smoking Using Wearable Sensors and Support Vector Machines , 2013, IEEE Transactions on Biomedical Engineering.

[3]  Michael R Neuman,et al.  Toward Objective Monitoring of Ingestive Behavior in Free‐living Population , 2009, Obesity.

[4]  Xin Xu,et al.  Annual healthcare spending attributable to cigarette smoking: an update. , 2015, American journal of preventive medicine.

[5]  Edward Sazonov,et al.  Detection of Hand-to-Mouth Gestures Using a RF Operated Proximity Sensor for Monitoring Cigarette Smoking , 2013, The open biomedical engineering journal.

[6]  Koichiro Matsuo,et al.  Respiration during feeding on solid food: alterations in breathing during mastication, pharyngeal bolus aggregation, and swallowing. , 2008, Journal of applied physiology.

[7]  Wen-Chuan Wu,et al.  Detection System of Smoking Behavior Based on Face Analysis , 2011, 2011 Fifth International Conference on Genetic and Evolutionary Computing.

[8]  Evangelos Kalogerakis,et al.  RisQ: recognizing smoking gestures with inertial sensors on a wristband , 2014, MobiSys.

[9]  C. Mathers,et al.  Projections of Global Mortality and Burden of Disease from 2002 to 2030 , 2006, PLoS medicine.

[10]  Edward Sazonov,et al.  A wearable sensor system for monitoring cigarette smoking. , 2013, Journal of studies on alcohol and drugs.

[11]  Douglas A. Reynolds,et al.  Robust text-independent speaker identification using Gaussian mixture speaker models , 1995, IEEE Trans. Speech Audio Process..

[12]  A Eberhard,et al.  Comparison between the respiratory inductance plethysmography signal derivative and the airflow signal. , 2001, Advances in experimental medicine and biology.

[13]  Edward Sazonov,et al.  Automatic breathing segmentation from wearable respiration sensors , 2011, 2011 Fifth International Conference on Sensing Technology.

[14]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[15]  Syed Monowar Hossain,et al.  mPuff: automated detection of cigarette smoking puffs from respiration measurements , 2012, IPSN.

[16]  Edward Sazonov,et al.  Identification of cigarette smoke inhalations from wearable sensor data using a Support Vector Machine classifier , 2012, 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.