In large-scale wireless sensor networks, sensor-processor elements (nodes) are densely deployed to monitor the environment; consequently, their observations form a random field that is highly correlated in space. We consider a fusion sensor-network architecture where, due to the bandwidth and energy constraints, the nodes transmit quantized data to a fusion center. The fusion center provides feedback by broadcasting summary information to the nodes. In addition to saving energy, this feedback ensures reliability and robustness to node and fusion-center failures. We assume that the sensor observations follow a linear-regression model with known spatial covariances between any two locations within a region of interest. We propose a Bayesian framework for adaptive quantization, fusion-center feedback, and estimation of the random field and its parameters. We also derive a simple suboptimal scheme for estimating the unknown parameters, apply our estimation approach to the no-feedback scenario, discuss field prediction at arbitrary locations within the region of interest, and present numerical examples demonstrating the performance of the proposed methods.

We propose maximum likelihood (ML) methods for estimating the parameters of composite gamma-lognormal fading channels. Newton-Raphson and expectation-maximization (EM) algorithms are developed to compute the ML estimates of the mean and variance of the shadowing component, and the Nakagami-m parameter of the fading component. We also derive Crame/spl acute/r-Rao bounds (CRBs) for the unknown parameters. Numerical simulations demonstrate the performance of the proposed method.

We develop a hierarchical Bayesian approach for estimating defect signals from noisy measurements and apply it to nondestructive evaluation (NDE) of materials. We propose a parametric model for the shape of the defect region and assume that the defect signals within this region are random with unknown mean and variance. Markov chain Monte Carlo (MCMC) algorithms are derived for simulating from the posterior distributions of the model parameters and defect signals. These algorithms are then utilized to identify potential defect regions and estimate their size and reflectivity parameters. Our approach provides Bayesian confidence regions (credible sets) for the estimated parameters, which are important in NDE applications. We specialize the proposed framework to elliptical defect shape and Gaussian signal and noise models and apply it to experimental ultrasonic C-scan data from an inspection of a cylindrical titanium billet. We also outline a simple classification scheme for separating defects from nondefects using estimated mean signals and areas of the potential defects

Generalized multivariate analysis of variance (GMANOVA) and related reduced-rank regression are general statistical models that comprise versions of regression, canonical correlation, and profile analyses as well as analysis of variance (ANOVA) and covariance in univariate and multivariate settings. It is a powerful and, yet, not very well-known tool. We develop a unified framework for explaining, analyzing, and extending signal processing methods based on GMANOVA. We show the applicability of this framework to a number of detection and estimation problems in signal processing and communications and provide new and simple ways to derive numerous existing algorithms. Many of the methods were originally derived "from scratch", without knowledge of their close relationship with the GMANOVA model. We explicitly show this relationship and present new insights and guidelines for generalizing these methods. Our results could inspire applications of the general framework of GMANOVA to new problems in signal processing. We present such an application to flaw detection in nondestructive evaluation (NDE) of materials. A promising area for future growth is image processing.

Compound-Gaussian models are used in radar signal processing to describe heavy-tailed clutter distributions. The important problems in compound-Gaussian clutter modeling are choosing the texture distribution, and estimating its parameters. Many texture distributions have been studied, and their parameters are typically estimated using statistically suboptimal approaches. We develop maximum likelihood (ML) methods for jointly estimating the target and clutter parameters in compound-Gaussian clutter using radar array measurements. In particular, we estimate i) the complex target amplitudes, ii) a spatial and temporal covariance matrix of the speckle component, and iii) texture distribution parameters. Parameter-expanded expectation-maximization (PX-EM) algorithms are developed to compute the ML estimates of the unknown parameters. We also derived the Cramer-Rao bounds (CRBs) and related bounds for these parameters. We first derive general CRB expressions under an arbitrary texture model then simplify them for specific texture distributions. We consider the widely used gamma texture model, and propose an inverse-gamma texture model, leading to a complex multivariate t clutter distribution and closed-form expressions of the CRB. We study the performance of the proposed methods via numerical simulations.