A Publish/Subscribe Middleware for Body and Ambient Sensor Networks that Mediates between Sensors and Applications

摘要

Continuing development of an increasing variety of sensors has led to a vast increase in sensor-based telemedicine solutions. A growing range of modular sensors, and the need of having several applications working with those sensors, has led to an equally extensive increase in efforts for system development. In this paper, we present an event-driven middleware for on-body and ambient sensor networks that allows multiple applications to define information types of their interest in a publish/subscribe manner. Incoming sensor data is hereby transformed into the desired data representation which lifts the burden of adapting the application with respect to the connected sensors off the developer's shoulders. Furthermore, an unsupervised on-the-fly reloading of transformation rules from a remote server allows the system's adaptation to future applications and sensors at run-time. Application-specific event channels provide tailor-made information retrieval as well as control over the dissemination of critical information. The system is evaluated based on an Android implementation, with transformation rules implemented as OSGi bundles that are retrieved from a remote web server. Evaluation shows a low impact of running the transformation rules on a phone and highlights the reduced energy consumption by having fewer sensors serving multiple applications. It also points out the behavior and limits of the application-specific event channels with respect to CPU utilization, delivery ratio, and memory usage.