Full On-Device Stay Points Detection in Smartphones for Location-Based Mobile Applications

Abstract

The tracking of frequently visited places, also known as stay points, is a critical feature in location-aware mobile applications as a way to adapt the information and services provided to smartphones users according to their moving patterns. Location based applications usually employ the GPS receiver along with Wi-Fi hot-spots and cellular cell tower mechanisms for estimating user location. Typically, fine-grained GPS location data are collected by the smartphone and transferred to dedicated servers for trajectory analysis and stay points detection. Such Mobile Cloud Computing approach has been successfully employed for extending smartphone’s battery lifetime by exchanging computation costs, assuming that on-device stay points detection is prohibitive. In this article, we propose and validate the feasibility of having an alternative event-driven mechanism for stay points detection that is executed fully on-device, and that provides higher energy savings by avoiding communication costs. Our solution is encapsulated in a sensing middleware for Android smartphones, where a stream of GPS location updates is collected in the background, supporting duty cycling schemes, and incrementally analyzed following an event-driven paradigm for stay points detection. To evaluate the performance of the proposed middleware, real world experiments were conducted under different stress levels, validating its power efficiency when compared against a Mobile Cloud Computing oriented solution.

A framework for assessing neuropsychiatric phenotypes by using smartphone-based location data

“…We show that the stay point detection algorithm 23 is able to detect stationary and non-stationary states with relatively high efficiency. Despite the relatively small size of sample 1 (n = 10), these results are in accordance with earlier findings that demonstrated the efficiency of this same algorithm in accurately detecting stationary and nonstationary states from smartphone-based location data 26,27 . Importantly, we found that the efficiency of the stay point detection algorithm is dependent on the interaction between the parameters as used by the algorithm and the precision of the collected geospatial coordinates.…”

“…The sensitivity and usability of these behavioral phenotypes in detecting behavioral deviations is dependent on the efficiency of the preprocessing procedures. We demonstrate the efficiency of a two-step preprocessing procedure that utilizes a set of methods that are validated in the context of geospatial data 26,27 . Evaluation of this framework in terms of efficiency revealed an overall high accuracy in detecting stationary, non-stationary and recurrent stationary states correctly.…”

A Spatio-Temporal Approach to Individual Mobility Modeling in On-Device Cognitive Computing Platforms

“…Existing off-line algorithms require a complete trajectory to detect POIs [30]. Nevertheless, differential algorithms (Differential algorithms calculate the spatio-temporal differences between pairs of location fixes, rather than using a density-based or clustering approach), as the proposed in [21], are suitable for an incremental stream-based approach [25]. Using this idea, the pois_detector module in Figure 1 detects POIs (the evnormalpoi event) as follows.…”

“…Nevertheless, the distance evaluation and the queuing of fixes in a cluster requires the frequent recalculation of a cluster’s centroid, which can be an issue if many fixes are to be queued. Similarly, the connections between detected POIs are not investigated, and as a result such work merely acts as a yet efficient [24] POIs detection mechanism, very much alike the ideas we explored before in [25].…”

Identifying and Querying Regularly Visited Places

“…These regions are usually called popular places, hotspots, interesting places, stops, or stay points in the literature. There are several definitions of stay points and different techniques have been presented to find them [1,3,5,8,9,10,12,13]. However, from a geometric perspective, which is the focus of the present paper, few papers are dedicated to a formal algorithmic study of this problem.…”