When do you light a fire?

Abstract

An important step towards assessing smoking behavior is to detect and log smoking episodes in an unobtrusive way. Detailed information on an individual's consumption can then be used to highlight potential health risks and behavioral statistics to increase the smoker's awareness, and might be applied in smoking cessation programs. In this paper, we present an evaluation of two different monitoring prototypes which detect a user's smoking behavior, based on augmenting a lighter. Both prototypes capture and record instances when the user smokes, and are sufficiently robust and power efficient to allow deployments of several weeks. A real-world feasibility study with 11 frequently-smoking participants investigates the deployment and adoption of the system, hinting that smokers are generally unaware of their daily smoking patterns, and tend to overestimate their consumption.

Lifelogging

“…We used a motion sensor (accelerometer) which can be worn like a wrist watch to detect the typical movement of the arm while smoking (Scholl et al 2013). We used a motion sensor (accelerometer) which can be worn like a wrist watch to detect the typical movement of the arm while smoking (Scholl et al 2013).…”

“…There are also research projects which log sleeping behavior (Borazio and Laerhoven 2012), detect smoking (Scholl et al 2013), fi tness activities (Seeger et al 2014) or leisure activities (Berlin and Laerhoven 2012). The technical research mainly belongs to the fi eld of computer science, especially to ubiquitous computing.…”

VapeTracker

“…Their approach, which combined self-tracking of smoking activities and personal counselling, showed that both the personal counselling and the ability to visualize and reflect on self-tracked smoking behaviors helped participants form strategies to improve their ability to quit. Scholl et al [24] present the UbiLighter prototypes, which can capture and record instances when the user smokes. Deploying their prototypes with 11 partici-pants over several weeks, they found that smokers are generally unaware of their daily smoking patterns, and tend to overestimate their consumption.…”

“…These considerations cannot be separated from psychological models of behavioral change, therefore in parallel we need to investigate more thoroughly which model is best suited for vapers who want to quit, and the importance of immediate relapse precipitants (cf., [25]). At that stage, our plan is to build several VapeTracker prototypes and deploy to users for getting longitudinal data (order of months) as is done in smoking cessation HCI research [18,24]. Finally, a long-term goal of our work is to eventually acquire enough vaping data that machine learning models can be trained, in order to predict when a user would vape, how to personalize feedback and provide smart user-aware notifications.…”

MAM - Media Assembly Model

“…Para permitir a captura nesse cenário, ao invés de instrumentar o ambiente, pode-se instrumentar o usuário, isto é, dotá-lo de dispositivos móveis capazes de realizar o registro das atividades, tais como (smartphones, smartwatches, dispositivos montados sobre a cabeça, wearables, etc.) (LE et al, 2016;SCHOLL et al, 2015;KÜCÜKYILDIZ;LAERHOVEN, 2013). Algumas técnicas de C&A também podem ser utilizadas para registrar atividades quando poucas dimensões são conhecidas, como o lifelogging (CZERWINSKI et al, 2006) e o Buffer de Experiências e Armazenamento Sele-tivo (HAYES, 2006).…”