Mobility Collector

Abstract

Despite the availability of mobile positioning technologies and scientists' interests in tracking, modelling and predicting the movements of individuals and populations, these technologies are seldom efficiently used. The continuous changes in mobile positioning and other sensor technologies overburden scientists who are interested in data collection with the task of developing, implementing and testing tracking algorithms and their efficiency in terms of battery consumption. To this extent, this article proposes an adaptive, battery conscious tracking algorithm that collects trajectory data fused with accelerometer data and presents Mobility Collector, which is a prototype platform that, using the tracking algorithm, can produce highly configurable, off-the-shelf, multi-user tracking systems suitable for research purposes. The applicability of the tracking system is tested within the transport science domain by collecting labelled movement traces and related motion data, i.e. accelerometer data and derived information (number of steps and other useful movement features based on temporal aggregates of the raw readings) to develop and evaluate a method that automatically classifies the transportation mode of users with a 90.8% prediction accuracy.

Keywords::

• movement
• location tracking
• data collection
• location awareness
• smartphones
• battery conscious
• location and accelerometer data fusion

Notes

^1. The explanation for the Android implementation used in this article is based on the authors' understanding of the explanation at Android's Official Page for Developers. http://developer.android.com/reference/android/location/LocationManager.htmlrequestLocationUpdates(long,float,android.location.Criteria,android.app.PendingIntent), as accessed on 29 March 2014.

^2. The measurements for battery consumption were performed on an HTC One X+ smartphone, and the device's screen was turned off for the duration of the measurements because its battery consumption dwarfs that of any sensor.

^3. At least four visible satellites are needed to obtain a GPS fix.

^4. The terminology is derived from http://developer.android.com/guide/topics/sensors/sensors_overview.html, as accessed on 29 March 2014.

^5. Linking of discrete/finite variables can also be done automatically by converting continuous variables via thresholding.

^6. This article focuses on inserting one spatial annotation per location to offer spatially discrete data that can be used for training real-time location-based classifiers, but an implementation in which multiple spatial annotations correspond to a location is possible.

^7. Github can be accessed at https://github.com/.

^8. OpenShift can be accessed at https://www.openshift.com/.

^9. The case study was performed in November, in Stockholm, Sweden.

^10. The equitime tracking approach can provide data suitable for the detection of stationarity periods in real time by identifying when the consecutively recorded locations are within a threshold distance of a central location.

Additional information

Funding

This work was partly supported by the Trafikverket (Swedish Transport Administration) [grant number TRV 2014/10422]; KTH Transport Research Environment with Novel Perspectives (TRENoP) Strategic Research Area and KTH innovative Transport Research Undergraduate Experience (iTRUE).