In non-linear system identification the set of non-linear models is very rich and the number of parameters usually grows very rapidly with the number of regressors. In order to reduce the large variety of possible models as well as the number of parameters, it is of great interest to exclude irrelevant regressors before estimating any model. In this work, three existing approaches for regressor...

We study p-adic multiresolution analyses (MRAs). A complete characterisation of test functions generating MRAs (scaling functions) is given. We prove that only 1-periodic test functions may be taken as orthogonal scaling functions. We also suggest a method for the construction of wavelet functions and prove that any wavelet function generates a p-adic wavelet frame.

Multi-dimensional Bayesian network classifiers (MDCs) generalise the popular robustly performing one-dimensional classifiers (ODCs) to application domains that require an instance to be classified into a combination of classes. In previous work we compared the sensitivity of MDC and ODC output probabilities to small parameter inaccuracies. In this paper we extend our analyses and study the robu...

1. In poultry investigations, the main interest is often to study the effects of many factors simultaneously. Two or three level factorial designs are the most commonly used for this type of investigation. However, it is often too costly to perform when number of factors increase. So a fractional factorial design, which is a subset or a fraction of a full factorial design, is an alternative. Th...

Software quality processes can be assessed with the Orthogonal Defect Classification COnstructive QUALity MOdel (ODC COQUALMO) that predicts defects introduced and removed, classified by ODC types. Using parametric cost and defect removal inputs, static and dynamic versions of the model help one determine the impacts of quality strategies on defect profiles, cost and risk. The dynamic version p...

Developed in this article are theories of the so-called linear estimation techniques. The methods are exclusively based on the space-time empirical orthogonal functions which describe nonuniform covariance statistics of background uctuations of investigated variable. Two speciic methods to be discussed are the detection and the estimation algorithms with speciic emphasis on the description of e...

In the paper [Y. Okuyama, {it On the absolute generalized N"{o}rlund summability of orthogonal series},Tamkang J. Math. Vol. 33, No. 2, (2002), 161-165] the author has found some sufficient conditions under which an orthogonal seriesis summable $|N,p,q|$ almost everywhere. These conditions are expressed in terms of coefficients of the series. It is the purpose ofthis paper to extend this result...

Background: Suicide may be conceptualized as an escape from intolerable predicaments, in particular, mental illness and environmental stressors. The operationalized predicaments of suicide (OPS) is a 4 category framework designed to assist in the classification of suicide. The objective was to examine whether this framework is potentially useful. Method: 18 psychiatrists from 6 different countr...

In this note, we announce a general method for the construction of nonseparable orthogonal wavelet bases of L2(Rn), where n ≥ 2. Hence, we prove the existence of such type of wavelet bases for any integer n ≥ 2. Moreover, we show that this construction method can be extended to the construction of n-D multiwavelet matrix filters.

In this paper we study the algebraic and geometric structure of the space of compactly supported biorthogonal wavelets. We prove that any biorthogonal wavelet matrix pair (which consists of the scaling lters and wavelet lters) can be factored as the product of primitive parau-nitary matrices, a pseudo identity matrix pair, an invertible matrix, and the canonical Haar matrix. Compared with the f...