A case study in applying QoS adaptation and model-based design to the design-time optimization of signal analyzer applications

The capture and classification of digital signals is an important part of military communications and of signal intelligence (SIGINT). A typical signal analyzer is built from a set of elementary signal processing operations, which often include parameters whose values can affect the quality of the signal classification. In this paper we present a case study we have conducted to evaluate the efficacy of automated parameter tuning for improving signal classification. We use a prototype signal analyzer parameter tuner, which augments a signal analyzer design with a search space controller driven by a utility function based on correct classification. It tunes parameters by automatically tweaking parameter values in a systematic way and evaluating the utility of the signal analyzer with different parameter values over a set of representative signals with known ground truth. We developed the parameter tuner using a QoS adaptive design tool we developed under the DARPA MoBIES program. We have achieved improved signal classification in three signal analyzers studied. In addition, the automated parameter tuning exercise has the side effect of providing increased understanding of how parameters contribute to signal analysis. The paper describes the signal analyzer parameter tuner, the experiments that we conducted as a part of our case study, and the empirical results of the experiments.