A novel algorithm for determining the contextual characteristics of movement behaviors by combining accelerometer features and wireless beacons: development and implementation
journal contributionposted on 10.04.2018 by Daniele Magistro, Salvatore Sessa, Andrew Kingsnorth, Adam Loveday, Alessandro Simeone, Massimiliano Zecca, Dale Esliger
Any type of content formally published in an academic journal, usually following a peer-review process.
Unfortunately, global efforts to promote ‘how much’ physical activity people should be undertaking have been largely unsuccessful. Given the difficulty of achieving?? a sustained lifestyle behaviour change, many scientists are re-examining their approaches. One such approach is to focus on understanding the context of the lifestyle behaviour (i.e., where, when and with who) with a view to identifying promising intervention targets. Therefore, the aim of this study was to develop and implement an innovative algorithm to determine ‘where’ physical activity occurs using proximity sensors coupled with a widely-used physical activity monitor. Nineteen Bluetooth beacons were placed in fixed locations within a multi-level, mixed-use building. Four receiver-mode sensors were fitted to the wrists of a roving technician that moved throughout the building. The experiment was divided into four trials with different walking speeds and dwelling times. The data were analysed using an original and innovative algorithm based on graph generation and Bayesian filters. Linear regression models revealed significant correlations between beacon-derived location and ground-truth tracking time, with intraclass correlations suggesting a high goodness of fit (Rsquare=.9780). The algorithm reliably predicted indoor location (insert R-square), and the robustness of the algorithm improved with a longer dwell time (>100 seconds; error<10%, R-square=.9775). Increased error was observed for transitions between areas due to the device sampling rate, currently manufacturer limited to 0.1 Hz. This study shows that our algorithm can accurately predict the location of an individual within an indoor environment. This novel implementation of 'context sensing' will facilitate a wealth of new research questions from promoting healthy behaviour change, the optimisation of patient care, and efficient health care planning (e.g., patient/clinician flow; patient/clinician interaction).
This work was supported by the Medical Research Councils’ Lifelong Health and Wellbeing Initiative in partnership with the Department of Health (grant number MR/K025090/1), and partially by the LU-HEFCE Catalyst grant and by the LU-EESE startup grant. Also, this research is part of the research portfolio supported by the National Institute for Health Research Collaboration for Leadership in Applied Health Research and Care East Midlands (NIHR CLAHRC for EM) and by the National Institute for Health Research (NIHR) Leicester Biomedical Research Centre based at University Hospitals of Leicester and Loughborough University.
- Sport, Exercise and Health Sciences