Informatica

In the papers (Kaminskas, 1973; Kaminskas and Nemura, 1975) the stopping rule of recursive least squares (RLS) is worked out using the length of the confidence interval for the respective current meaning of the true output signal of a linear dynamic system. The aim of the given paper is the development of techniques for calculating threshold intervals of respective criteria, used in such a stopping rule. In this connection adaptive threshold intervals based on the Cramer-Rao lower bound according to Pupeikis (1995) are proposed here, too. The results of numerical simulation by IBM PC/AT are given.

In the papers (Kaminskas, 1972; Kaminskas and Nemura, 1975; Yin, 1989) the stopping rules of recursive least squares (RLS) are worked out using the ellipsoidal confidence region for the respective parameter vector of a linear dynamic system. The aim of the given paper is the development of the technique for calculating threshold intervals of respective criterions, used in a stopping rule, which are presented in Kaminskas (1972). In this connection adaptive threshold intervals based on the Cramer-Rao lower bound are proposed here. The results of numerical simulation by IBM PC/AT are given.

In the previous paper (Pupeikis, 1992) the problem of off-line estimation of dynamic systems parameters in the presence of outliers in observations have been considered, when the filter generating an additive noise has a very special form. The aim of the given paper is the development, in such a case, of classical generalized least squares method (GLSM) algorithms for off-line estimation of unknown parameters of dynamic systems. Two approaches using batch processing of the stored data are worked out. The first approach is based on the application of S-, H-, W- algorithms used for calculation of M-estimates, and the second one rests on the replacement of the corresponding values of the sample covariance and cross-covariance functions by their robust analogues in respective matrices of GLSM and on a further application of the least squares (LS) parameter estimation algorithms. The results of numerical simulation by IBM PC/AT (Table 1) are given.

In the previous papers (Pupeikis, 1990; 1991; 1992) the problems of model oder determination and recursive estimation of dynamic systems parameters in the presence of outliers in observations have been considered. The aim of the given paper is the development, in such a case, of classical off-line algorithms for systems of unknown parameters estimation using batch processing of the stored data. An approach, based on a substitution of the corresponding values of the sample covariance and cross-covariance functions by their robust analogues in respective matrices and on a further application of the least square (LS) parameter estimation algorithm, is worked out. The results of numerical simulation by IBM PC/AT (Table 1, 2) are given.

In the previous paper (Pupeikis, 1990) the problem of model order determination in the presence of outliers in observations has been considered. The aim of the given paper is the development of the recursive algorithms of computation of M-estimates ensuring their stability conditions. In this connection the approach, based on adaptive Huber's monotone psi-function, is worked out. It is also used for the detection of the outliers in time series and for the correction both outliers and M-estimates during successive calculations. The results of numerical simulation by computer (Fig. 1 and Table 1) are given.