It is a well known fact that any orthonormal basis in L 2 can produce a \random density". If fng is an orthonormal basis and fang is a sequence of random variables such that a 2 n = 1 a.s., then f(x) = jann(x)j 2 is a random density. In this note we deene a random density via orthogonal bases of wavelets and explore some of its basic properties.

This paper examines the use of general orthonormal bases for system identification from frequency domain data. This idea has been studied in great depth for the particular case of the orthonormal trigonometric basis. Here we show that the accuracy of the estimate can be significantly improved by rejecting the trigonometric basis in favour of a more general orthogonal basis that is able to be ad...

In the present work a newer type of black box nonlinear model in Hammerstein structure is proposed. The model has Wavelet Network coupled with Orthonormal Basis Functions which is capable of modeling a class of non-linear systems with acceptable accuracy. Wavelet basis functions have the property of localization in both the time and frequency domains which enables wavelet networks to approximat...

Existing work on the representation of operators in one-dimensional, compactly-supported, orthonormal wavelet bases is extended to two dimensions. The non-standard form of the representation of operators is given in separable two-dimensional, periodic, orthonormal wavelet bases. The matrix representation of the partial differential operators ∂x and ∂y are constructed and a closed form formula f...

This paper provides an overview of system identification using orthonormal basis function models, such as those based on Laguerre, Kautz, and generalised orthonormal basis functions. The paper is separated in two parts. In this first part, the mathematical foundations of these models as well as their advantages and limitations are discussed within the context of linear and robust system identif...

We study the following problem: describe triplets (?,g,?) where g=(g ij (x)) is (co)metric associated with symmetric second order differential operator L(f)=1 ?? ? i (g ?? j f) defined on a domain ? of ? d (that L diffusion reversible measure ?(dx)=?(x)dx) and such that there exists an orthonormal basis ? 2 (?) made polynomials which are at same time eigenvectors L, ranked according to their na...

This discussion sparse representations of signals in R. The sparsity of a signal is quantified by the number of nonzero components in its representation. Such representations of signals are useful in signal processing, lossy source coding, image processing, etc. We first speak of an uncertainty principle regarding the sparsity of any two different orthonormal basis representations of a signal S...

Given a real-analytic manifold M, a compact connected Lie group G and a principal G-bundle P ! M, there is a canonicaìgeneralized measure' on the space A=G of smooth connections on P modulo gauge transformations. This allows one to deene a Hilbert space L 2 (A=G). Here we construct a set of vectors spanning L 2 (A=G). These vectors are described in terms of`spin networks': graphs embedded in M,...

In a complex vector space of dimension N , by a full set of mutually unbiased bases (MUB’s) we mean a set of N+1 orthonormal bases such that the modulus square of the scalar product of any member of one basis with any member of any other basis is equal to 1/N . If we take e to denote the k vector in the α orthonormal basis, then having a full set of MUB’s amounts to having a collection e ; α = ...