Identification and Equalization

This book chapter summarizes the three major ways that people analyze adaptive algorithms (the expected value, deterministic averaging, and ODE approaches), and contains applications in several signal processing areas.

W. A. Sethares, The LMS Family, in Efficient System Identification and Signal Processing Algorithms, Ed. N. Kalouptsidis and S. Theodoridis Springer-Verlag, 1993.

Uses "dispersion functions" for a correlation- style analysis that is applicable to the identification of nonlinear systems.

H. E. Liao and W. A. Sethares, "Suboptimal identification of nonlinear ARMA models using an orthogonality approach," IEEE Trans. on Circuits and System, Vol. 42, No. 1, pg. 14-22, Jan. 95.

H. E. Liao and W. A. Sethares, "Cross-term analysis of LNL models," IEEE Trans. on Circuits and Systems, Vol. 43, No. 4, April 1996. [Use of dispersion functions to determine structural properties of nonlinear models, focusing on those which can be described as a static nonlinearity sandwiched between two linear dynamic systems.]

The blind equalization problem attempts system identification without access to the true inputs. This paper asks the question: what are sensible cost functions for blind equalization? Behavioral aspects of these choices are examined.

S. Vembu, S. Verdu, R. A. Kennedy, and W. A. Sethares, "Convex cost functions in blind equalization," IEEE Trans. on Signal Processing, Vol. 42, No. 8, pg. 1952-1960, August 1994.

Application of (real time, adaptive) system identification to the problem of thermal estimation in semiconductors. Replaces a graphical method of thermal design that has been in place since the mid 60's. Conference version of paper wins best paper award at IEEE Industrial Applications Society meeting in 1990.

G. L. Skibinski and W. A. Sethares, "Thermal parameter estimation using recursive identification," IEEE Trans. on Power Electronics, Vol. 6, No. 2, pp. 228-239, April 1991.

To get to my homepage, click here.