Detection in multivariate non-Gaussian noise

The applications of multivariate Edgeworth series and higher-order statistics to the discrete-time detection of a known constant signal in multivariate non-Gaussian noise are considered. A technique to derive suboptimum detectors from the Neyman-Pearson optimum and locally optimum detectors is described. A numerical algorithm based on knowledge of the noise cumulants is presented in order to analyze the finite-sample size performance of the suboptimum detectors. As an example, the performance of the detectors as compared with the linear detector in multivariate Gaussian-Gaussian mixture noise is presented via receiver operating characteristic curves. Numerical results indicate that the suboptimum detectors, when exploiting knowledge of the dependence structure of the noise, can have very good performance with respect to the linear detector