Data adaptive signal estimation by singular value decomposition of a data matrix

A new method is presented for estimating the signal component of a noisy record of data. Only a little prior information about the signal is assumed. Specifically, the approximate value of rank of a matrix which is formed from the samples of the signal is assumed to be known or obtainable from singular value decomposition (SVD).     

Coordinate estimation of the image with unknown intensity and area

The synthesis and analysis of the quasi-likelihood and maximum likelihood algorithms have been made for estimating image coordinates. The loss in accuracy of the quasi-plausible estimate as compared with the accuracy of the maximum likelihood estimate has been found.     

Further remarks on sequential estimation of a scale parameter in exponential distributions with an unknown location

The sequential procedure developed by Govindarajulu and Sarkar [Sequential estimation of scale parameter in exponential distributions with unknown location. Utilitas Math.40, 161–178 (1991)] for estimating the scale parameter of an exponential distribution, when the location parameter is unknown, is further analyzed. Generalizing the results of Govindarajulu and Sarkar, the ‘asymptotic risk-efficiency’ of the sequential procedure is established for the general loss function. A simple method of obtaining the asymptotic distribution of the stopping time is given. For the case of quadratic loss function and linear cost of sampling, a much simpler proof for obtaining the second-order approximations for the risk is provided.     

Approaching Shannon performance by iterative decoding of linear codes with low-density generator matrix

We propose the use of linear codes with low density generator matrix to achieve a performance similar to that of turbo and standard low-density parity check codes. The use of iterative decoding techniques - message passing -over the corresponding graph achieves a performance close to the Shannon theoretical limit. As an advantage with respect to turbo and standard low-density parity check codes, the complexity of the decoding and encoding procedures is very low.     

Research on an iterative algorithm of LS channel estimation in MIMO OFDM systems

An iterative Least Square (LS) channel estimation algorithm for MIMO OFDM systems was proposed in this paper. Compared to common LS channel estimation, this algorithm can greatly improve estimation accuracy, and the low-pass filtering in time domain reduces AWGN and ICI significantly. MIMO OFDM system with this algorithm also works well in mobile situations. Simulation results have shown good MSE performance for this algorithm.     

A lower bound on the estimation error for an unknown parameter with discontinuous observations (Corresp.)

A lower bound on the mean square error for an estimate of unknown parameter is derived for the case where the observation noise is a martingale with jump discontinuities.     

A gradient-based alternating minimization approach for optimization of the measurement matrix in compressive sensing

In this paper the problem of optimization of the measurement matrix in compressive (also called compressed) sensing framework is addressed. In compressed sensing a measurement matrix that has a small coherence with the sparsifying dictionary (or basis) is of interest. Random measurement matrices have been used so far since they present small coherence with almost any sparsifying dictionary. However, it has been recently shown that optimizing the measurement matrix toward decreasing the coherence is possible and can improve the performance. Based on this conclusion, we propose here an alternating minimization approach for this purpose which is a variant of Grassmannian frame design modified by a gradient-based technique. The objective is to optimize an initially random measurement matrix to a matrix which presents a smaller coherence than the initial one. We established several experiments to measure the performance of the proposed method and compare it with those of the existing approaches. The results are encouraging and indicate improved reconstruction quality, when utilizing the proposed method.     

The efficiency of detecting an object moving in the unknown direction with unknown intensities of its image and background

The maximum likelihood algorithm for detecting a space-extended object moving in the unknown direction has been synthesized and analyzed under conditions of a priori uncertainty with respect to intensities of its image and applicative background. The impact of a priori unknown intensities of the object image and the background on the detection characteristics was also investigated.     

A Viterbi-type algorithm for efficient estimation of M-PSKsequences over the Gaussian channel with unknown carrier phase

A Viterbi-type algorithm for the efficient estimation of a convolutionally/trellis coded, or uncoded M-PSK sequence over the Gaussian channel with unknown carrier phase is presented. It performs coherent detection of M-PSK sequences with no explicit recovery of coherent references. The metric computations involve only linear operations. Theoretical and simulated performance results are presented for various carrier phase processes. The algorithm is called the suboptimum ML estimator (SMLE). Its BER in the presence of a time invariant carrier phase is obtained analytically. The simulation results for the BER with time-invariant as well as time-varying carrier phase processes allow a comparison of the performance of the SMLE with other sequence estimation algorithms, and enable the applicability of the SMLE to burst mode TDMA communications to be ascertained     

Optimal reception of digital data over the Gaussian channel with unknown delay and phase jitter

Asymptotically optimum (in the sense of minimum per-symbol error rate) receiver structures for data communication over the white Gaussian channel with unknown time delay and carrier phase jitter are developed. The receiver structures apply to the following suppressed-carrier modulation systems: double sideband (DSB), quadrature amplitude modulation (QAM) with an arbitrary constellation, vestigial sideband (VSB) and single sideband. The resulting minimum error probability receivers are asymptotically equivalent to maximum-likelihood digital {em sequence}-estimating receivers. The optimum structures implicitly derive joint maximum-likelihood estimates of the unknown parameters and of the sequence of data symbols. It is shown that the parameter estimates can be obtained from two data-directed stochastic approximation algorithms. Unlike traditional theoretical treatments of this communication situation, which have separated the highly important carrier phase and timing recovery problem from the detection problem, a unified theory is presented from which the complete ideal receiver structure can be deduced.     

Minimax estimation of deterministic parameters in linear models with a random model matrix

We consider the problem of estimating an unknown deterministic parameter vector in a linear model with a random model matrix, with known second-order statistics. We first seek the linear estimator that minimizes the worst-case mean-squared error (MSE) across all parameter vectors whose (possibly weighted) norm is bounded above. We show that the minimax MSE estimator can be found by solving a semidefinite programming problem and develop necessary and sufficient optimality conditions on the minimax MSE estimator. Using these conditions, we derive closed-form expressions for the minimax MSE estimator in some special cases. We then demonstrate, through examples, that the minimax MSE estimator can improve the performance over both a Baysian approach and a least-squares method. We then consider the case in which the norm of the parameter vector is also bounded below. Since the minimax MSE approach cannot account for a nonzero lower bound, we consider, in this case, a minimax regret method in which we seek the estimator that minimizes the worst-case difference between the MSE attainable using a linear estimator that does not know the parameter vector, and the optimal MSE attained using a linear estimator that knows the parameter vector. For analytical tractability, we restrict our attention to the scalar case and develop a closed-form expression for the minimax regret estimator.     

Solving inverse problems by Bayesian iterative inversion of aforward model with applications to parameter mapping using SMMR remotesensing data

Inverse problems have been often considered ill-posed, i.e., the statement of the problem does not thoroughly constrain the solution space. In this paper the authors take advantage of this lack of information by adding additional informative constraints to the problem solution using Bayesian methodology. Bayesian modeling gains much of its power from its ability to isolate and incorporate causal models as conditional probabilities. As causal models are accurately represented by forward models, the authors convert implicit functional models into data driven forward models represented by neural networks, to be used as engines in a Bayesian modeling setting. Remote sensing problems afford opportunities for inclusion of ground truth information, prior probabilities, noise distributions, and other informative constraints within a Bayesian probabilistic framework. They first apply these Bayesian methods to a synthetic remote sensing problem, showing that the performance is superior to a previously published method of iterative inversion of neural networks. Next, microwave brightness temperatures obtained from the Scanning Multichannel Microwave Radiometer (SMMR) over the African continent are inverted. The values of soil moisture, surface air temperature and vegetation moisture retrieved from the inversion produced contours that agree with the expected trends for that region     

Computation of fields in an arbitrary shaped heterogeneousdielectric or biological body by an iterative conjugate gradient method

Electromagnetic (EM) fields in a three-dimensional, arbitrarily shaped, heterogeneous dielectric or biological body illuminated by a plane wave are computed by an iterative conjugate gradient method. The method is a generalized method of moments applied to the volume integral equation. Because no matrix is explicitly involved or stored, the method is capable of computing EM fields in objects an order of magnitude larger than those that can be handled by the conventional method of moments. Excellent numerical convergence is achieved. Perfect convergence to the result of the conventional moment method using the same basis and weighted with delta functions is consistently achieved in all the cases computed, indicating that these two algorithms (direct and iterative) are equivalent     

Maximum likelihood estimation of the Burr XII parameters with censored and uncensored data

This paper presents the methodology for obtaining point and interval estimates of the parameters of the Burr Type XII distribution with multiple-censored and singly-censored data (Type I censoring or Type II censoring) as well as complete data, using the maximum likelihood method. The basis is the likelihood expression for multiple-censored data. The other types of censoring and complete data are treated as special cases. A FORTRAN language program was used. Some illustrative examples are included.     

语言判断矩阵在确定多属性决策问题权重中的应用

在多属性决策问题中,由于易受人为因素的影响,所得权重值的客观性是确定权重的最基本的要求。但以往确定权重方法都在一定程度上受人为因素影响较大。在此介绍一种新的方法——语言判断矩阵方法,并运用该方法对防空作战中影响目标威胁度因素的权重进行了分析计算,其结果较为合理,且该方法与其他方法相比,在确定多属性决策的权重问题时受人的主观因素影响较小。     

Analysis of the accuracy of an iterative algorithm for calculating the field scattered by a rough surface

The accuracy of an iterative algorithm for calculating the field scattered by a rough surface in the mirror direction is estimated for grazing angles of incidence.     

改进的非负矩阵分解在基因表达数据中的应用

对非负矩阵分解算法的发展历史做了简要综述,并介绍了非负矩阵分解算法的基本原理,及一种改进的非负矩阵分解算法,并将此方法应用于一组阿尔茨海默症微阵列数据的聚类中,将此结果与传统的非负矩阵分解算法进行了比较,证明了算法的有效性.     

Uncertainties in the estimation of ACF-based texture in syntheticaperture radar image data

Spatial analysis of synthetic aperture radar (SAR) image data holds much promise for characterizing and discriminating environmental scene elements. The autocorrelation function (ACF) has been identified as a potentially useful spatial metric because it admits an analysis with conventional linear system theory. Recent models of spatial scattering suggest that ACF-based texture analysis of SAR image data is capable of discriminating between a variety of area extensive targets. The incorporation of texture in an image classification or segmentation system requires some understanding of the uncertainties in the texture estimates. In this paper, the authors introduce a particular ACF model and examine the errors associated with estimating its parameters from image measurements. They also conduct an analysis of two important classes of errors: imaging system errors and estimation errors. They found that as the proportion of raw signal used to create the image increases the effects of system errors rapidly degrade ACF performance. This has implications for operationally produced image products that do not use an autofocusing procedure. They also found that the agreement between theoretical and observed estimation errors is quite good, so that the scale of these errors may be accurately estimated during a spatial analysis of the image data. They found some residual bias that may be attributed to both the use of the ACF itself and to the way the ACF model was constructed     

Comparison of the multilayer perceptron with neuro-fuzzy techniquesin the estimation of cover class mixture in remotely sensed data

Mixed pixels are a major source of inconvenience in the classification of remotely sensed data. This paper compares MLP with so-called neuro-fuzzy algorithms in the estimation of pixel component cover classes. Two neuro-fuzzy networks are selected from the literature as representatives of soft classifiers featuring different combinations of fuzzy set-theoretic principles with neural network learning mechanisms. These networks are: 1) the fuzzy multilayer perceptron (FMLP) and 2) a two-stage hybrid (TSH) learning neural network whose unsupervised first stage consists of the fully self-organizing simplified adaptive resonance theory (FOSART) clustering model, FMLP, TSH, and MLP are compared on CLASSITEST, a standard set of synthetic images where per-pixel proportions of cover class mixtures are known a priori. Results are assessed by means of evaluation tools specifically developed for the comparison of soft classifiers. Experimental results show that classification accuracies of FMLP and TSH are comparable, whereas TSH is faster to train than FMLP. On the other hand, FMLP and TSW outperform MLP when little prior knowledge is available for training the network, i.e., when no fuzzy training sites, describing intermediate label assignments, are available     

非均匀噪声背景下混合信号DOA估计算法

针对非均匀噪声背景下非相关信源与相干信源并存时波达方向(DOA)估计问题，提出了基于迭代最小二乘和空间差分平滑的混合信号DOA估计算法。首先，该算法利用迭代最小二乘方法得到噪声协方差矩阵估计，然后对数据协方差矩阵进行“去噪”处理，利用子空间旋转不变技术实现非相关信源DOA估计；其次，基于空间差分法消除非相关信号并构造新矩阵进行前后向空间平滑，利用求根MUSIC算法估计相干信源DOA。相比于传统算法，该算法能估计更多的信源数，在低信噪比情况下DOA估计性能更优越。仿真实验结果验证了该算法的有效性。