Enabling Dynamic Crowdsensing through Models@Runtime

Abstract

The complexity of applications in the mobile crowdsensing domain is due to factors such as interoperability among heterogeneous devices, recruiting of devices, collection of data from these devices, and adaptation of application operation in dynamic environments. This paper introduces a platform based on models at runtime (M@RT) for the development of the mobile crowdsensing functionality of applications. The platform supports model-based creation and processing of queries that target a distributed and dynamic set of sensor-capable devices. The paper also presents the results of an evaluation that shows the impact of runtime model processing on the performance of applications in mobile crowdsensing scenarios.

Keywords: participatory sensing, models at runtime, model execution engine, mobile computing.