Living++/GAMBAS paper and demo will be presented at PERCOM 2012

The paper title is "Enabling Energy-Efficient Context Recognition with Configuration Folding" and the authors are Muhammad Umer Iqbal, Marcus Handte, Stephan Wagner, Wolfgang Apolinarski, Pedro José Marrón.
Abstract: Existing context recognition applications for personal mobile devices are usually fine-tuned to recognize the set of characteristics required to support a particular user task. Outside of a laboratory environment, however, users are often involved in multiple tasks at a time which requires the simultaneous execution of several applications. Yet, due to the energy constraints of most personal mobile devices this approach is inherently limited in scale. In this paper, we show how this problem can be avoided by applying a component-based approach to application development and execution. We present a component system that enables developers to build individual applications in isolation without compromising runtime efficiency. When applications are executed simultaneously, the component system applies a novel technique called configuration folding to automatically remove redundancies. Our experimental evaluation of configuration folding shows that it can save up to 48 percent of energy when applied to a music and a speech detection application, thus, amortizing energy costs after a few seconds of execution.

The demonstration is titled "Configuration Folding: An Energy Efficient Technique for Context Recognition". The authors are Muhammad Umer Iqbal, Marcus Handte, Stephan Wagner, Wolfgang Apolinarski, Pedro José Marrón.
Abstract: This demonstration presents configuration folding, a novel technique which enables the energy efficient execution of multiple context recognition applications on a personal mobile device. Configuration folding achieves energy efficiency by identifying and removing the redundant functionalities in different context recognition applications at runtime. The demonstration shows the effectiveness of configuration folding. To do this, we have implemented two non-trivial sound-based context recognition applications that are able to detect speech and music. During the demonstration, we will execute these applications with folded and unfolded configurations and we will show how the resulting energy gains can be measured. Furthermore, we present how similar applications can be built by means of composition.