EEMCS

Home > Publications
Home University of Twente
Education
Research
Prospective Students
Jobs
Publications
Intranet (internal)
 
 Nederlands
 Contact
 Search
 Organisation

EEMCS EPrints Service


27529 A hierarchical lazy smoking detection algorithm using smartwatch sensors
Home Policy Brochure Browse Search User Area Contact Help

Shoaib, M. and Scholten, J. and Havinga, P.J.M. and Durmaz Incel, O. (2016) A hierarchical lazy smoking detection algorithm using smartwatch sensors. In: Proceedings of the IEEE 18th International Conference on e-Health Networking, Applications and Services (Healthcom 2016), 14-17 Sep 2016, Munich, Germany. pp. 117-122. IEEE Computer Society. ISBN 978-1-5090-3370-6

Full text available as:

PDF (Publisher's version)

363 Kb

Official URL: http://dx.doi.org/10.1109/HealthCom.2016.7749439

Exported to Metis

Abstract

Smoking is known to be one of the main causes for premature deaths. A reliable smoking detection method can enable applications for an insight into a user’s smoking behaviour and for use in smoking cessation programs. However, it is difficult to accurately detect smoking because it can be performed in various postures or in combination with other activities, it is lessrepetitive, and it may be confused with other similar activities, such as drinking and eating. In this paper, we propose to use a two-layer hierarchical smoking detection algorithm (HLSDA) that uses a classifier at the first layer, followed by a lazy contextrule-based correction method that utilizes neighbouring segments to improve the detection. We evaluated our algorithm on a dataset of 45 hours collected over a three month period where 11 participants performed 17 hours (230 cigarettes) of smoking while sitting, standing, walking, and in a group conversation. The rest of 28 hours consists of other similar activities, such as eating, and drinking. We show that our algorithm improves recall as well as precision for smoking compared to a single layer classification approach. For smoking activity, we achieve an Fmeasure of 90-97% in person-dependent evaluations and 83-94% in person-independent evaluations. In most cases, our algorithm corrects up to 50% of the misclassified smoking segments. Our algorithm also improves the detection of eating and drinking in a similar way. We make our dataset and data logger publicly available for the reproducibility of our work.

Item Type:Conference or Workshop Paper (Full Paper, Talk)
Research Group:EWI-PS: Pervasive Systems
Research Program:CTIT-General
Research Project:COMMIT/SWELL: User Centric Reasoning for Well-working
ID Code:27529
Status:Published
Deposited On:17 January 2017
Refereed:Yes
International:Yes
More Information:statisticsmetis

Export this item as:

To correct this item please ask your editor

Repository Staff Only: edit this item