Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2018 Apr 20;6(4):e100.
doi: 10.2196/mhealth.8516.

A Novel Algorithm for Determining the Contextual Characteristics of Movement Behaviors by Combining Accelerometer Features and Wireless Beacons: Development and Implementation

Daniele Magistro  1   2 , Salvatore Sessa  3 , Andrew P Kingsnorth  1   2 , Adam Loveday  1   2 , Alessandro Simeone  4 , Massimiliano Zecca  2   5 , Dale W Esliger  1   2
Affiliations

A Novel Algorithm for Determining the Contextual Characteristics of Movement Behaviors by Combining Accelerometer Features and Wireless Beacons: Development and Implementation

Daniele Magistro et al. JMIR Mhealth Uhealth. .

Abstract

Background: 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 behavior change, many scientists are reexamining their approaches. One such approach is to focus on understanding the context of the lifestyle behavior (ie, where, when, and with whom) with a view to identifying promising intervention targets.

Objective: 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.

Methods: A total of 19 Bluetooth beacons were placed in fixed locations within a multilevel, mixed-use building. In addition, 4 receiver-mode sensors were fitted to the wrists of a roving technician who moved throughout the building. The experiment was divided into 4 trials with different walking speeds and dwelling times. The data were analyzed using an original and innovative algorithm based on graph generation and Bayesian filters.

Results: Linear regression models revealed significant correlations between beacon-derived location and ground-truth tracking time, with intraclass correlations suggesting a high goodness of fit (R2=.9780). The algorithm reliably predicted indoor location, and the robustness of the algorithm improved with a longer dwelling time (>100 s; error <10%, R2=.9775). Increased error was observed for transitions between areas due to the device sampling rate, currently limited to 0.1 Hz by the manufacturer.

Conclusions: 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 on promoting healthy behavior change, the optimization of patient care, and efficient health care planning (eg, patient-clinician flow, patient-clinician interaction).

Keywords: activity monitor; algorithm; beacons/proximity; behavior; context; indoor location; physical activity; sedentary behavior; wearable sensor.

PubMed Disclaimer

Conflict of interest statement

Conflicts of Interest: None declared.

Figures

Figure 1
Figure 1
A visual representation, based on the areas order, of the dwelling time for each trial. Trial 1 at normal walking speed (self-paced at approximately 1.4 m/s); Trial 2 at slow walking speed (self-paced at approximately 0.9 m/s or slower); Trial 3 at fast walking speed (self-paced at approximately 2.0 m/s); Trial 4, the walking speed, dwelling time and route were not prescribed (ie, not previously decided). The locations are named as follows: First number indicates the floor: "1" indicates the first floor and "2" indicates the second floor; Uppercase letter indicates the type of room where the beacon was installed: "S" indicates a social area, "R" indicates a standard room, "C" indicates a corridor; Second number is a counter for the same type of room on the same floor; Lowercase letter is used only for long corridors or a large social area to indicate when multiple beacons were used; The label “Stairs” indicates the beacon placed in the stairway (same beacon on both floors).
Figure 2
Figure 2
Building floorplan and beacon positions: Top: First floor; Bottom: Ground floor. Each beacon is shown in red with an accompanying Bluetooth symbol showing its direction.
Figure 3
Figure 3
A schematic representation of how the localization algorithm was derived.
Figure 4
Figure 4
Map graph: the position of the beacons in the map transposed as a graph.
Figure 5
Figure 5
Tracking quality graphs for trials 1-4 (model 3; w=1.0). The red line represents location derived from the criterion measurement (camera), and the blue lines represent the locations obtained from the algorithm.
Figure 6
Figure 6
Linear regression model between accelerometry and criterion measure (video) tracking time in seconds.
Figure 7
Figure 7
Confusion matrices of model 3 (w=1.0) for trials 1-4. Column A represents all the transition and nontransition states, and B only nontransition states.
Figure 8
Figure 8
The combination of localization tracking and activity data of trial 1. The green, yellow, and red color indicate low, middle, and high level of activity, respectively.
Figure 9
Figure 9
Lasagna plots representing the combination of localization tracking and activity levels. Areas are sorted in descending order depending on the absolute time. The color between blue (time equal to zero) and yellow (time equal to 230 s) represents the activity level spent-time.
Figure 10
Figure 10
Lasagna plots representing the combination of localization tracking and activity levels. Areas are sorted in descending order depending on the relative time. The color between blue (time equal to zero) and yellow (time equal to 230 s) represents the activity level spent-time.
See this image and copyright information in PMC

References

    1. Berrigan D, Hipp JA, Hurvitz PM, James P, Jankowska MM, Kerr J, Laden F, Leonard T, McKinnon RA, Powell-Wiley TM, Tarlov E, Zenk SN, TREC Spatial and Contextual Measures and Modeling Work Group Geospatial and contextual approaches to energy balance and health. Ann GIS. 2015;21(2):157–168. doi: 10.1080/19475683.2015.1019925. http://europepmc.org/abstract/MED/27076868 - DOI - PMC - PubMed
    1. Cummins S, Curtis S, Diez-Roux AV, Macintyre S. Understanding and representing 'place' in health research: a relational approach. Soc Sci Med. 2007 Nov;65(9):1825–38. doi: 10.1016/j.socscimed.2007.05.036. - DOI - PubMed
    1. Kirchner TR, Shiffman S. Spatio-temporal determinants of mental health and well-being: advances in geographically-explicit ecological momentary assessment (GEMA) Soc Psychiatry Psychiatr Epidemiol. 2016 Dec;51(9):1211–23. doi: 10.1007/s00127-016-1277-5. http://europepmc.org/abstract/MED/27558710 - DOI - PMC - PubMed
    1. Popay J, Thomas C, Williams G, Bennett S, Gatrell A, Bostock L. A proper place to live: health inequalities, agency and the normative dimensions of space. Soc Sci Med. 2003 Jul;57(1):55–69. - PubMed
    1. Sampson RJ, Morenoff JD, Gannon-Rowley T. Assessing “ neighborhood effects”: Social processes and new directions in research. Annu Rev Sociol. 2002;28:443–478. doi: 10.1146/annurev.soc.28.110601.141114. https://www.annualreviews.org/doi/10.1146/annurev.soc.28.110601.141114 - DOI - DOI