Cigarette Smoking Detection with An Inertial Sensor and A Smart Lighter

Abstract

In recent years, a number of wearable approaches have been introduced for objective monitoring of cigarette smoking based on monitoring of hand gestures, breathing or cigarette lighting events. However, non-reactive, objective and accurate measurement of everyday cigarette consumption in the wild remains a challenge. This study utilizes a wearable sensor system (Personal Automatic Cigarette Tracker 2.0, PACT2.0) and proposes a method that integrates information from an instrumented lighter and a 6-axis Inertial Measurement Unit (IMU) on the wrist for accurate detection of smoking events. The PACT2.0 was utilized in a study of 35 moderate to heavy smokers in both controlled (1.5–2 h) and unconstrained free-living conditions (~24 h). The collected dataset contained approximately 871 h of IMU data, 463 lighting events, and 443 cigarettes. The proposed method identified smoking events from the cigarette lighter data and estimated puff counts by detecting hand-to-mouth gestures (HMG) in the IMU data by a Support Vector Machine (SVM) classifier. The leave-one-subject-out (LOSO) cross-validation on the data from the controlled portion of the study achieved high accuracy and F1-score of smoking event detection and estimation of puff counts (97%/98% and 93%/86%, respectively). The results of validation in free-living demonstrate 84.9% agreement with self-reported cigarettes. These results suggest that an IMU and instrumented lighter may potentially be used in studies of smoking behavior under natural conditions.

Wearable Sensors for Monitoring of Cigarette Smoking in Free-Living: A Systematic Review

“…Signal Processing and Pattern Recognition: Senyurek et al (Jan. 2019) [108] proposed an algorithm to identify the smoking session and smoking-related HMGs, integrating two PACT2.0 sensors: The instrumented lighter and the 6D wrist IMU. In the preprocessing steps, the raw IMU sensor signal was filtered by a 2nd order low pass Butterworth filter.…”

A Report on Smoking Detection and Quitting Technologies

“…Such a structured and constrained way to record the signals associated to activities affects the interpretation of the very high achieved performances. Hand-to-mouth and chest sensors Research Prototype 61% Lopez-Meyer et al [3] Hand-to-mouth sensor Research Prototype 90% Cole et al [4] App + Smartwatch Research Prototype 89% Smokesense [7] Smartwatch Research Prototype 89% Research by CWRU [8] App + 2 Armbands Not on the market 98% CigFree [9] App + Property Smartband Starting from $69 100 N/A SmokeBeat [10] App + Smartwatch Free 80% StopWatch [11] Smartwatch Research Prototype 92% Lu et al [12] Prototypal wrist sensors Research Prototype 5 88% Senyurek et al [13] Prototypal wrist sensors Research Prototype 93% Senyurek et al [14] Prototypal wrist sensors Research Prototype 97% RisQ [15] App + wrist sensors Research Prototype 81%…”

“…Senyurek et al [13] exploited a wearable sensor system named PACT2.0 (Personal Automatic Cigarette Tracker 2.0) and proposed a method that combines information from an instrumented lighter and a 6-axis IMU (Inertial Measurement Unit) placed on the wrist for the detection of smoking events. An instrumented lighter captures the lighter press and release events, however no details of smoking duration can be found from this information.…”

“…Also, the work in Reference [14] exploited the PACT2.0 wrist module and the smart lighter used in Reference [13]. However, the approach in Reference [14] aimed to detect the smoking events by analysing the regularity of hand gestures.…”

“…Furthermore, this system is based on two armbands, such a setting can be considered only in an experimental scenario, and this makes it difficult to transfer this scientific result to a real product. The works in Reference [13] and in Reference [14] achieved interesting performances in challenging experimental settings, which include a high number and variety of involved subjects, as well as several hours of free-living evaluation. However, the employed hardware (e.g., smart lighter) only allows for experimental evaluation that is far from a commercial solution.…”