even, jani juhani luc (Nara Inst. of Science and Tech.), Sugimoto, Kenji (Nara Inst. of Science and Tech.)

Blind Identification of Non Minimal Phase Systems Using Higher Order Statistics: Nonlinear Optimization Approach

Scheduled for presentation during the Regular Session "Linear System Identification III" (WeA09), Wednesday, July 26, 2006, 10:50−11:15, Room J

17th International Symposium on Mathematical Theory of Networks and Systems, July 24-28, 2006, Kyoto, Japan

This information is tentative and subject to change. Compiled on April 25, 2024

Abstract

This paper proposes a method to identify blindly non-minimal phase SISO systems based on a blind deconvolution criterion. Most blind deconvolution methods rely on some approximations because of instability of the inverse system, but here we propose not to use these approximations. Assuming batch processing is possible, the time is reversed in order to implement the non causal part of the exact inverse system. This approach enables us to provide an analytical expression of the cost function used for blind deconvolution. Thus rather than using a traditional gradient-like approach, we propose a method that relies on the resolution of a system of nonlinear algebraic equations in order to perform the blind identification.