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.

Mobile Edge Computing (MEC) relates to the deployment of decision-making processes at the network edge or mobile devices rather than in a centralized network entity like the cloud. This paradigm shift is acknowledged as one key pillar to enable autonomous operation and self-awareness in mobile devices in IoT. Under this paradigm, we focus on mobility-based services (MBSs), where mobile devices are expected to perform energy-efficient GPS data acquisition while also providing location accuracy. We rely on a fully on-device Cognitive Dynamic Systems (CDS) platform to propose and evaluate a cognitive controller aimed at both tackling the presence of uncertainties and exploiting the mobility information learned by such CDS toward energy-efficient and accurate location tracking via mobility-aware sampling policies. We performed a set of experiments and validated that the proposed control strategy outperformed similar approaches in terms of energy savings and spatio-temporal accuracy in LBS and MBS for smartphone devices.

The advent of IoT represents the next step in the evolution of Internet technologies and applications, which demand the autonomous operation of resource-constrained devices for surfing and processing the myriad of online generated data toward self-decision making. MEC is aimed at enabling such capabilities on connected devices, whereas CDSs have been proposed recently as a promising path for addressing such tasks, and to enable truly distributed intelligence in the mobile and IoT environment. As an example of these demanding IoT scenarios, the mobility understanding of individuals could provide decisive information toward city planning, crowd studies, mHealth, and so on. However, efficient implementations are a titanic challenge due to energy limitations on mobile devices. Under cognitive computing, we intend to provide mobile devices with the ability for online recognition of user mobility changes and for learning ways to adapt to those changes for different purposes, including energy savings in sensing. We present a fully autonomous on-device implementation of a CDS inspired framework that learns and exploits an expanded spatio-temporal model from stay points detection for human mobility understanding. Experimental results show benefits in both mobility mining and energy savings, showing the potential of using embeddable CDSs for future cognitive IoT-oriented applications.

The increased availability of GPS-enabled devices makes possible to collect location data for mining purposes and to develop mobility-based services (MBS). For most of the MBSs, determining interesting locations and frequent Points of Interest (POIs) is of paramount importance to study the semantic of places visited by an individual and the mobility patterns as a spatio-temporal phenomenon. In this paper, we propose a novel approach that uses mobility-based services for on-device and individual-centered mobility understanding. Unlike existing approaches that use crowd data for cloud-assisted POI extraction, the proposed solution autonomously detects POIs and mobility events to incrementally construct a cognitive map (spatio-temporal model) of individual mobility suitable to constrained mobile platforms. In particular, we focus on detecting POIs and enter-exits events as the key to derive statistical properties for characterizing the dynamics of an individual’s mobility. We show that the proposed spatio-temporal map effectively extracts core features from the user-POI interaction that are relevant for analytics such as mobility prediction. We also demonstrate how the obtained spatio-temporal model can be exploited to assess the relevance of daily mobility routines. This novel cognitive and on-line mobility modeling contributes toward the distributed intelligence of IoT connected devices without strongly compromising energy.