An On-Device Cognitive Dynamic Systems Inspired Sensing Framework for the IoT

Abstract

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.