Model order selection in unknown correlated noise: A supervised approach

The purpose of this paper is to propose the design and the use of a Neural Network for model order selection The proposed neural network learns from real life situation by constructing an input/output mapping (for detection) which brings to mind the notion of non parametric statistical inference. Such a strategy can improve performances of traditional tests relying on linearity, stationarity and second order statistics. We focus on the case where the noise covariance matrix is unknown but is a band matrix. This paper includes simulations which show improvements obtained by supervised approach.