DETECTION OF NON-GAUSSIAN SIGNALS - A PARADIGM FOR MODERN STATISTICALSIGNAL-PROCESSING

Non-Gaussian signals arise in a wide variety of applications, includin g sonar, digital communications, seismology, and radio astronomy. In t his tutorial overview, a hierarchical approach to signal modeling and detector design for non-Gaussian signals is described. In addition to being of interest in applications, this problem serves as a paradigm w ithin which most of the areas of active research in statistical signal processing arise. In particular, the methodologies of nonlinear signa l processing, higher order statistical analysis, signal representation s, and learning algorithms, all can be juxtaposed quite naturally in t his framework.