ROBUST AND SIMPLE ALGORITHMS FOR MAXIMUM LIKELIHOOD ESTIMATION OF MULTIVARIABLE SYSTEMS

Abstract This paper presents novel algorithms for the estimation of dynamic systems. These new methods offer several advantages of being parameterisation free, numerically robust, convergent to statistically optimal estimates, and applicable in a simple fashion to a wide range of multivariable, non-linear and time varying problems. The key tool underlying the new techniques presented here is the 'Expectation-Maximisation' (EM) algorithm.

[1]  Karl Johan Åström,et al.  BOOK REVIEW SYSTEM IDENTIFICATION , 1994, Econometric Theory.

[2]  Lennart Ljung,et al.  System Identification: Theory for the User , 1987 .

[3]  B. Moor,et al.  Subspace identification for linear systems , 1996 .

[4]  Graham C. Goodwin,et al.  Model Identification and Adaptive Control , 2001 .

[5]  Antonio Vicino,et al.  Optimal estimation theory for dynamic systems with set membership uncertainty: An overview , 1991, Autom..

[6]  Manfred Deistler,et al.  System Identification - General Aspects and Structure , 2001 .

[7]  R. Fisher.  001: On an Absolute Criterion for Fitting Frequency Curves. , 1912 .

[8]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[9]  Manfred Deistler,et al.  Consistency and relative efficiency of subspace methods , 1994, Autom..

[10]  D. Titterington.  Recursive Parameter Estimation Using Incomplete Data , 1984 .

[11]  Roberto Guidorzi,et al.  Discussion: 'On the Use of Minimal Parametrisations in Multivariable ARMAX Identification' by R. P. Guidorzi , 1998, Eur. J. Control.

[12]  J. P. Norton,et al.  Identification and application of bounded-parameter models , 1985, Autom..

[13]  D K Smith,et al.  Numerical Optimization , 2001, J. Oper. Res. Soc..

[14]  Wallace E. Larimore,et al.  Canonical variate analysis in identification, filtering, and adaptive control , 1990, 29th IEEE Conference on Decision and Control.

[15]  Fionn Murtagh,et al.  Image processing and data analysis , 1998 .

[16]  John E. Dennis,et al.  Numerical methods for unconstrained optimization and nonlinear equations , 1983, Prentice Hall series in computational mathematics.

[17]  E. L. Lehmann,et al.  Theory of point estimation , 1950 .

[18]  E. Hannan,et al.  The statistical theory of linear systems , 1989 .

[19]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.