Parameter estimation for operator scaling random fields
نویسندگان
چکیده
Operator scaling random fields are useful for modeling physical phenomena with different scaling properties in each coordinate. This paper develops a general parameter estimation method for such fields which allows an arbitrary set of scaling axes. The method is based on a new approach to nonlinear regression with errors whose mean is not zero. © 2013 Elsevier Inc. All rights reserved.
منابع مشابه
Hölder Regularity for Operator Scaling Stable Random Fields
Abstract. We investigate the sample paths regularity of operator scaling α-stable random fields. Such fields were introduced in [6] as anisotropic generalizations of self-similar fields and satisfy the scaling property {X(cx);x ∈ R} (fdd) = {cX(x);x ∈ R} where E is a d× d real matrix and H > 0. In the case of harmonizable operator scaling random fields, the sample paths are locally Hölderian an...
متن کاملMulti-operator Scaling Random Fields
In this paper, we define and study a new class of random fields called harmonizable multi-operator scaling stable random fields. These fields satisfy a local asymptotic operator scaling property which generalizes both the local asymptotic self-similarity property and the operator scaling property. Actually, they locally look like operator scaling random fields whose order is allowed to vary alo...
متن کاملParametric estimation for Gaussian operator scaling random fields and anisotropy analysis of bone radiograph textures
In this paper, we consider a stochastic anisotropic model for trabecular bone x-ray images. In [1], a fractal analysis based on isotropic Fractional Brownian Fields was proposed to characterize bone microarchitecture. However anisotropy measurement is of special interest for the diagnosis of osteoporosis [7]. We propose to model trabecular bone radiographs by operator scaling Gaussian random fi...
متن کاملEnsemble Solute Transport in 2 - D Operator - Scaling
1. Abstract Motivated by field measurements of aquifer hydraulic conductivity (K), recent tech5 niques were developed to construct anisotropic fractal random fields, in which the scaling, 6 or self-similarity parameter, varies with direction and is defined by a matrix. Ensemble 7 numerical results are analyzed for solute transport through these 2-D “operator-scaling” 8 fractional Brownian motio...
متن کاملEfficient Training of Conditional Random Fields
This thesis explores a number of parameter estimation techniques for conditional random fields, a recently introduced [31] probabilistic model for labelling and segmenting sequential data. Theoretical and practical disadvantages of the training techniques reported in current literature on CRFs are discussed. We hypothesise that general numerical optimisation techniques result in improved perfor...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- J. Multivariate Analysis
دوره 123 شماره
صفحات -
تاریخ انتشار 2014