JMIR Publications

ABSTRACT

Background:

Mobile and wearable technology presents exciting opportunities for monitoring behaviour using widely available sensor data. This could support clinical research and practice aimed at improving quality of life among the growing number of people with dementia, but requires suitable tools for measuring behaviour in a natural, real-life setting that can be easily implemented by others.

Objective:

The objectives of this study are to develop and test a set of algorithms and metrics for measuring mobility and activity, and describe a technical setup for collecting the sensor data these require using off-the-shelf devices.

Methods:

A mobility measurement module is developed to extract GPS trajectories and home location from raw location data, and use these to calculate a set of spatial, temporal and count-based mobility metrics. Activity measurement comprises activity bout extraction from recognised activity data, and daily step counts. Location, activity and step count data is collected using smartwatches and smartphones, relying on open-source resources as far as possible for accessing data from device sensors. The behavioural monitoring solution is evaluated among five healthy subjects who simultaneously logged their movements for one week.

Results:

Evaluation showed that the behavioural monitoring solution successfully measures GPS trajectories and mobility metrics from location data, extracts multimodal activity bouts during travel between locations, and that step count from a wearable device could supplement this with information about daily activity including during stay periods between trips.

Conclusions:

The work contributes to clinical research and practice by providing a comprehensive behavioural monitoring solution for use in a real-life setting that can be replicated for a range of applications where knowledge about individual mobility and activity is relevant.