Estimating the parameters of a Rice distribution: A Bayesian approach

Lauwers, Lieve; Barbé, Kurt; Moer, Wendy Van; Pintelon, Rik

doi:10.1109/imtc.2009.5168426

Cited by 26 publications

(12 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The fast fading behavior was extracted from measurement data and the obtained distributions were fitted to commonly used Probability Density Functions (PDFs) [24], using Maximum Likelihood Estimation (MLE) [26], implemented in Matlab R . Fast fading extraction was implemented as follows:…”

Section: B Measurement Resultsmentioning

confidence: 99%

Fast Fading Characterization for Body Area Networks in Circular Metallic Indoor Environments

et al. 2020

View full text Add to dashboard Cite

With the increasing development of 5G and Body Area Network based systems being implemented in unusual environments, propagation inside metallic structures is a key aspect to characterize propagation effects inside ships and other similar environments, mostly composed of metallic walls. In this paper, indoor propagation inside circular metallic structures is addressed and fast fading statistical distributions parameters are obtained from simulation, being assessed with measurements at 2.45 GHz in a passenger ferry discotheque with an 8 m diameter circular shape. It is observed that, in this kind of environments, second order reflections are particularly relevant due to the walls' high reflective nature. Globally, it is concluded that the Rayleigh distribution can be used to characterize fast fading effects with no significant loss of accuracy compared to the Rice one, since a low value of the Rice parameter is observed, being below 3.1 dB, even under Line-of-Sight conditions. Moreover, it is observed that, from the fast fading viewpoint, the best transmitter position is at the circle center. INDEX TERMS Body area networks, fading characterization, metallic structures, propagation modelling.

show abstract

Section: B Measurement Resultsmentioning

confidence: 99%

Fast Fading Characterization for Body Area Networks in Circular Metallic Indoor Environments

et al. 2020

View full text Add to dashboard Cite

show abstract

“…with m n (z) the CPD model mapping the variables in z to the tensor elements in M. Each f n is a twice differentiable fit function for the corresponding model entry m n . Examples of such alternative cost functions are β-divergences [15], the maximum likelihood estimator for data that follows a Rician distribution [16] and the correntropy function [17].…”

Section: A Ggn For Non-ls Cost Functionsmentioning

confidence: 99%

Inexact Generalized Gauss–Newton for Scaling the Canonical Polyadic Decomposition With Non-Least-Squares Cost Functions

Vandecappelle

Vervliet

Lathauwer

2021

IEEE J. Sel. Top. Signal Process.

View full text Add to dashboard Cite

The canonical polyadic decomposition (CPD) allows one to extract compact and interpretable representations of tensors. Several optimization-based methods exist to fit the CPD of a tensor for the standard least-squares (LS) cost function. Extensions have been proposed for more general cost functions such as β-divergences as well. For these non-LS cost functions, a generalized Gauss-Newton (GGN) method has been developed. This is a second-order method that uses an approximation of the Hessian of the cost function to determine the next iterate and with this algorithm, fast convergence can be achieved close to the solution. Unfortunately, for large tensors, the exact GGN approach becomes too expensive. In this paper, we therefore propose an inexact GGN method. The approximation of the Hessian is only used implicitly, which greatly improves the scalability of the method. Next, we show that by using a compressed instance of the GGN Hessian approximation, the computation time of the inexact GGN method can be lowered even more, with only limited influence on the convergence speed. Further, the maximum likelihood estimator for Rician distributed data is examined in detail as an example of an alternative cost function. This cost function is useful for the analysis of the moduli of complex data, as in functional magnetic resonance imaging, for instance. Finally, we compare the proposed method to the existing CPD methods and demonstrate the method's speed and effectiveness on synthetic and simulated real-life data.

show abstract

“…Samples in W 1 are used to approximate b, whereas samples in W 2 are used to approximate ν, σ. For an explicit computation of their values we refer the reader to the existing literature [18], [20], [22], [25]. Once the ML estimates b M L , ν M L , σ M L are computed, we use their values as the initial set of parameters Θ 0 for triggering the EM algorithm:…”

Section: Initialization Of the Algorithmmentioning

confidence: 99%

“…Because of the latter property, the solution of the ML problem becomes an optimization problem. Some papers propose adaptive techniques for selecting the initial starting values [18], [20], while in other cases slightly different Bayesian estimators are proposed in order to stabilize the problem [25].…”

Section: Introductionmentioning

confidence: 99%

Rayleigh-Rice Mixture Parameter Estimation via EM Algorithm for Change Detection in Multispectral Images

Zanetti

Bovolo

Bruzzone

2015

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

The problem of estimating the parameters of a Rayleigh-Rice mixture density is often encountered in image analysis (e.g., remote sensing and medical image processing). In this paper we address this general problem in the framework of change detection (CD) in multitemporal and multispectral images. One widely used approach to change detection in multispectral images is based on Change Vector Analysis (CVA). Here, the distribution of the magnitude of the difference image can be theoretically modeled by a Rayleigh-Rice mixture density. However, given the complexity of this model, in applications a Gaussian-mixture approximation is often considered, which may affect the change detection results. In this paper we present a novel technique for parameter estimation of the Rayleigh-Rice density that is based on a specific definition of the Expectation-Maximization (EM) algorithm. The proposed technique, which is characterized by good theoretical properties, iteratively updates the parameters and does not depend on specific optimization routines. Several numerical experiments on synthetic data demonstrate the effectiveness of the method which is general and can be applied to any image processing problem involving the Rayleigh-Rice mixture density. In the change detection context, the Rayleigh-Rice model (which is theoretically derived) outperforms other empirical models. Experiments on real multitemporal and multispectral remote sensing images confirm the validity of the model by returning significantly higher change detection accuracies than those obtained by using state-of-the-art approaches.

show abstract

Estimating the parameters of a Rice distribution: A Bayesian approach

Cited by 26 publications

References 13 publications

Fast Fading Characterization for Body Area Networks in Circular Metallic Indoor Environments

Fast Fading Characterization for Body Area Networks in Circular Metallic Indoor Environments

Inexact Generalized Gauss–Newton for Scaling the Canonical Polyadic Decomposition With Non-Least-Squares Cost Functions

Rayleigh-Rice Mixture Parameter Estimation via EM Algorithm for Change Detection in Multispectral Images

Contact Info

Product

Resources

About