Journal:Informatica
Volume 4, Issues 1-2 (1993), pp. 94–110
Abstract
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.
Journal:Informatica
Volume 4, Issues 1-2 (1993), pp. 81–93
Abstract
An algorithm for the sequential analysis of multivariate data is, presented along with some experimental results. The algorithm is based upon the sequential nonlinear mapping of L-dimensional vectors from the L-hiperspace into a lower-dimensional (two-dimensional) vectors such that the inner structure of distances between the vectors is preserved. Expressions for the sequential nonlinear mapping are obtained. The sequential nonlinear mapping is applied to sequential c1usterization of random processes and creation of an essentially new method for sequential detection of many abrupt or slow changes in several unknown states of dynamic systems.
Journal:Informatica
Volume 4, Issues 1-2 (1993), pp. 57–80
Abstract
A review of electrocardiographic (ECG) data compression methods is presented. It shows what data compression techniques are available and what the implementation consideration are for each technique.
Journal:Informatica
Volume 4, Issues 1-2 (1993), pp. 45–56
Abstract
Speaker identification problem is investigated. The identification is carried out comparing feature vectors (parameters of LPC model) of the “criminal” and “suspicious” speakers. Both likelihood ratio and cepstral distances are used for comparing feature vectors. The feature vectors are extracted from pseudostationary parts of speech utterances. The identification approach is suitable for text-dependent and text-independent identification. Experimental results illustrate the performance of the algorithm.
Journal:Informatica
Volume 4, Issues 1-2 (1993), pp. 21–44
Abstract
As a rule, a measure is a mapping from a σ-field of sets into the set of reals, or more generally, into some Banach space. A concept of set-valued measure (SV-measure) is introduced in the paper being a specific mapping from a σ-field of sets into a power set of a set. Properties of SV-measures are analyzed and illustrated on examples. Close relationship between SV-measures and a new nonstandard approach in artificial intelligence (AI) is explained. Then, the construction of factorization of the measures is mentioned, a special class of σ-quasiatomic SV-measures is defined and corresponding characterization theorem is proved. This class involves SV-measures ranging in a countable set which were used in modelling uncertainty in AI. It enables to answer one question arising in connection with this application.
Journal:Informatica
Volume 4, Issues 1-2 (1993), pp. 3–20
Abstract
Design problems of predictor-based self-tuning digital control systems for different kinds of linear and non-linear dynamical plants are discussed. Special cases include linear plants with unstable and nonminimum-phase control channels, linear plants with inner feedbacks, nonlinear Hammerstein and Wiener-Hammerstein-type plants. Considered are control systems based on generalized minimum variance algorithms with amplitude and introduction rate restrictions for the control signal.
Journal:Informatica
Volume 3, Issue 4 (1992), pp. 582–591
Abstract
The basic properties and methods of developing max-min and max-Δ transitive approximations of resemblance matrices of observed objects are reviewed. A new algorithm of constructing max-Δ transitive closure of such matrices is presented. The conditions of applications of the max-min and max-Δ transitive measures of similarity are considered.