Convergence of minimum-entropy robust estimators: applications in DSP and instrumentation

We continue the research line initiated by L. Pronzato and E. Thierry (2000, 2001); recent works inspired by minimum-entropy estimation have been published by J.I. De la Rosa and G. Fleury (2002, 2003) in the instrumentation framework. A statistical model has been established to represent some instrument signals; similarly, some limited hypotheses over such a model have been made. In fact, we assume limited knowledge of the noise or external perturbations distribution that interact into the system. The use of robust estimators in such situations is very helpful, since real systems are always exposed to continuous perturbations of unknown nature. Some applications, where the last is true, are medical instrumentation, industrial processes, and telecommunications, among others. Some results of the new minimum-entropy estimators for linear and nonlinear models are presented; such results complement those presented by Pronzato and Thierry.