Behavioural Smoking Identification via Hand-Movement Dynamics

Benouis, Mohamed, Abo-Tabik, Maryam, Benn, Yael ORCID: https://orcid.org/0000-0001-7482-5927, Salmon, Olivia, Barret-Chapman, Alex and Costen, Nick ORCID: https://orcid.org/0000-0001-9454-8840 (2020) Behavioural Smoking Identification via Hand-Movement Dynamics. In: 2019 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI), pp. 1734-1739. Presented at 2019 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI), 19 August 2019 - 23 August 2019, Leicester, UK.

Preview

Accepted Version Available under License In Copyright. Download (165kB) | Preview

Abstract

Smoking is a commonly observed habit worldwide, and is a major cause of disease leading to death. Many techniques have been established in medical and psychological science to help people quit smoking. However, the existing systems are complex, and usually expensive. Recently, wearable sensors and mobile application have become an alternative method of improving health. We propose a human behavioural classification based on the use of a one-dimensional local binary pattern (LBP), combined with a Probabilistic Neural Net (PNN) to differentiate smoking from other movements as measured from a wearable device. Human activity signals were recorded from two sets of 6 and 11 participants, using a smart phones equipped with an accelerometer and gyroscope mounted on a wrist module. The data combined structured and naturalistic scenarios. The pro- posed architecture was compared to previously studied machine learning algorithms and found to out-perform them, exhibiting ceiling level performance.