Variational Sparse Bayesian Learning for Estimation of Gaussian Mixture Distributed Wireless Channels

In this paper, variational sparse Bayesian learning is utilized to estimate the multipath parameters for wireless channels. Due to its flexibility to fit any probability density function (PDF), the Gaussian mixture model (GMM) is introduced to represent the complicated fading phenomena in various communication scenarios. First, the expectation-maximization (EM) algorithm is applied to the parameter initialization. Then, the variational update scheme is proposed and implemented for the channel parameters’ posterior PDF approximation. Finally, in order to prevent the derived channel model from overfitting, an effective pruning criterion is designed to eliminate the virtual multipath components. The numerical results show that the proposed method outperforms the variational Bayesian scheme with Gaussian prior in terms of root mean squared error (RMSE) and selection accuracy of model order.     

Decomposition of acoustic fields in quantised Bessel beams

Bessel beams are non-diffracting solutions to the wave equation, which become limited diffraction beams when implemented on finite apertures. In previous work we have applied Fourier-Bessel theory to deduce theoretically that the quantization of the Bessel beam profile on annular arrays results in a field which is a sum of limited diffraction fields. Here we demonstrate this for a five-ring, 20-mm diameter, 2.5-MHz transducer. The quantized field comprises a weighted sum of a main component corresponding to the desired field, along with three other major components and 28 lesser components representing undesired field components. The three major components correspond to limited diffraction beams with narrower beamwidths and shorter depths of field than the desired beam, and we show that these account for most of the discrepancies between the desired field and actual quantized field. An estimate and an interpretation of the number of field components as a function of the wavenumber are also given.     

First-order kernel density estimation of abdomen medical image intensity and spatial information and application to segmentation

Kernel density estimators (KDE) used for many medical image applications only consider the intensity information of each pixel or its neighbors without the ability of expressing the structure and shape of tissues and organs, and they suffer from boundary bias problem. In this paper, we propose a new first-order kernel density estimation (FOKDE) method for 1D intensity information and 2D spatial information of medical image in two steps. First, the FOKDE of intensity information is estimated and applied to medical image segmentation with the multi-thresholding algorithm. Second, we estimate the FOKDE of spatial information on the initial segmentation, which can express the structure and shape of organs and tissues. In order to evaluate the FOKDE and KDE of the 2D spatial information, we apply them to medical image segmentation with the hill-climbing strategy. Density estimation experiments and segmentation application results on the simulated dataset and real abdomen CT images show us that the FOKDE has smaller boundary bias than the KDE, and that it can estimate the structure and shape of tissues and organs with spatial information effectively.     

Pulse Coupled Neural Network-Based Multimodal Medical Image Fusion via Guided Filtering and WSEML in NSCT Domain

Multimodal medical image fusion aims to fuse images with complementary multisource information. In this paper, we propose a novel multimodal medical image fusion method using pulse coupled neural network (PCNN) and a weighted sum of eight-neighborhood-based modified Laplacian (WSEML) integrating guided image filtering (GIF) in non-subsampled contourlet transform (NSCT) domain. Firstly, the source images are decomposed by NSCT, several low- and high-frequency sub-bands are generated. Secondly, the PCNN-based fusion rule is used to process the low-frequency components, and the GIF-WSEML fusion model is used to process the high-frequency components. Finally, the fused image is obtained by integrating the fused low- and high-frequency sub-bands. The experimental results demonstrate that the proposed method can achieve better performance in terms of multimodal medical image fusion. The proposed algorithm also has obvious advantages in objective evaluation indexes VIFF, Q_W, API, SD, EN and time consumption.     

基于高斯混合模型的多区域并行增长图像分割算法

为克服经典区域增长算法中生长规则以及特征选取的困难,提出了基于高斯混合模型的多区域并行区域增长图像分割算法。首先交互选择多个不同区域的种子点,并利用交互式选择的属于每个区域的子块得到混合模型的个数;然后利用最大期望估计混合模型参数作为区域增长的初始参数,并在增长过程中不停地调节模型参数。为了避免初始种子点位置选择对算法性能的影响,采用了多区域并行竞争增长策略。仿真实验获得了较好的分割效果,表明所提出的算法是合理可行的。     

单幅模糊图像点扩散函数估计的梯度倒谱分析方法研究

针对单幅图像复原算法引入先验信息导致复杂度高、运算效率低的问题, 提出了单幅模糊图像点扩散函数估计的梯度倒谱分析方法. 首先给出了单幅模糊图像梯度倒谱估计其点扩散函数的基本原理, 利用相位恢复策略复原了二维点扩散函数相位信息, 实现了点扩散函数的快速估计; 其次, 为鉴别点扩散函数估计精度, 建立了图像梯度保真约束的全变分正则化图像复原模型, 并采用快速稳定收敛的交替方向策略优化能量函数; 通过对仿真和实拍单幅模糊图像进行的测试实验结果表明, 该方法快速准确地估计出点扩散函数, 克服了传统复原算法收敛速度慢的缺点, 有效抑制了振铃效应、保护了边缘信息, 为大尺寸单幅图像复原的工程化实现提供了理论和技术基础. 关键词： 图像复原 点扩散函数 梯度倒谱分析 全变分     

一种基于粒子群优化的高斯混合灰度图像增强算法

提出一种采用粒子群优化(PSO)的高斯混合灰度图像增强算法。该算法首先采用高斯混合模型(GMM)对输入图像的灰度直方图建模,并采用模型中高斯成分的有效交点来分割直方图。随后,该算法将每个直方图区间的灰度值转换到合适的输出区间,生成增强后的灰度图像,其中转换函数由输入直方图区间的高斯成分和累积分布经过粒子群优化后的参数决定。实验结果显示,该方法生成的图像视觉效果较好,对原图像和纹理细节丰富图像分别进行图像增强,增强后的图像信息熵分别是4.746 6和7.952 6,灰度平均梯度为6.970 6和37.386 1。     

Probability Distribution on Full Rooted Trees

The recursive and hierarchical structure of full rooted trees is applicable to statistical models in various fields, such as data compression, image processing, and machine learning. In most of these cases, the full rooted tree is not a random variable; as such, model selection to avoid overfitting is problematic. One method to solve this problem is to assume a prior distribution on the full rooted trees. This enables the optimal model selection based on Bayes decision theory. For example, by assigning a low prior probability to a complex model, the maximum a posteriori estimator prevents the selection of the complex one. Furthermore, we can average all the models weighted by their posteriors. In this paper, we propose a probability distribution on a set of full rooted trees. Its parametric representation is suitable for calculating the properties of our distribution using recursive functions, such as the mode, expectation, and posterior distribution. Although such distributions have been proposed in previous studies, they are only applicable to specific applications. Therefore, we extract their mathematically essential components and derive new generalized methods to calculate the expectation, posterior distribution, etc.     

Improved Treatment of the Independent Variables for the Deployment of Model Selection Criteria in the Analysis of Complex Systems

Model selection criteria are widely used to identify the model that best represents the data among a set of potential candidates. Amidst the different model selection criteria, the Bayesian information criterion (BIC) and the Akaike information criterion (AIC) are the most popular and better understood. In the derivation of these indicators, it was assumed that the model’s dependent variables have already been properly identified and that the entries are not affected by significant uncertainties. These are issues that can become quite serious when investigating complex systems, especially when variables are highly correlated and the measurement uncertainties associated with them are not negligible. More sophisticated versions of this criteria, capable of better detecting spurious relations between variables when non-negligible noise is present, are proposed in this paper. Their derivation is obtained starting from a Bayesian statistics framework and adding an a priori Chi-squared probability distribution function of the model, dependent on a specifically defined information theoretic quantity that takes into account the redundancy between the dependent variables. The performances of the proposed versions of these criteria are assessed through a series of systematic simulations, using synthetic data for various classes of functions and noise levels. The results show that the upgraded formulation of the criteria clearly outperforms the traditional ones in most of the cases reported.     

An improved Chan–Vese model by regional fitting for infrared image segmentation

In this paper, a regional fitting method is proposed for infrared image segmentation. In our model, the intensity of each pixel in a region is described by using the sum of the class center and the weighted variance of the region, in order to build energy function for encouraging the similarity pixels to be clustered together. The adoption of such way can thereby eliminate the issue associated with the drift of the class center that is existed in Chan–Vese model. Particularly, followed by incorporating energy function into the level set evolution without re-initialization framework, the variational formulation can force the level set function to be closed to object boundaries. Experiments on some representative and real infrared images have demonstrated that our model has higher performance of segmentation in comparison with Chan–Vese model without re-initialization, and some existing methods, including LBF and LCV model.     

基于Markov随机场的新型景像匹配算法

为了提高景像匹配导航系统的定位精度,给出了一种基于Markov随机场理论和极大后验概率估计的新型景像匹配算法。考虑到在x方向和y方向位置偏差的实时图与基准图之间的灰度分布关系,利用图像上的灰度分布服从Markvov随机场分布这一特性,建立了景像匹配问题的条件概率分布模型。应用最小二乘法和噪声的先验统计信息估计位置偏差的方差,给出了描述基准图与实时图之间灰度偏差的测量模型,确定了测量的统计特性。基于极大后验概率估计准则计算了位置偏差的估值。由于新算法在计算位置偏差估值时用到了被估量和噪声的统计信息,因此具有很高的精度。将该算法与最小二乘景像匹配算法进行了仿真比较。仿真结果表明,新算法的匹配精度达到了0.1~0.2像素,高于最小二乘匹配算法的匹配精度。     

时延匹配加权的舷外异常噪声源曲面投影定位方法

对现有的"滤波-时延估计-双曲面定位"的声源定位方法进行改进。结合经验模态分解消噪方法和广义平均幅度差函数时延估计方法,利用能量分布准则和频谱一致性准则进行源信号本征模态函数筛选和信号重构,提取多组分析信号求取时延,并利用时延匹配准则对真实时延值进行筛选和加权处理。考虑水听器贴近壳体布放,对壳体进行建模,并按照象限投影到平面再进行双曲线定位。分别进行模型系泊及航行实验,实验结果表明,改进后的定位方法有更高的定位精度,且减小了时延估计误差造成的定位精度影响。      

数字图像识别在混合油类三维荧光光谱分析中的应用

海上溢油已成为全球环境污染的重要问题之一,溢油严重破坏了海洋生态的平衡,并导致人类健康受到危害。因此,研究高效的溢油检测方法对保护海洋生态环境具有重要意义。三维荧光光谱技术因能获得溢油的“指纹”图谱而成为溢油鉴别领域的有效分析手段,其与平行因子分析算法相结合获得了良好的溢油鉴别效果。但平行因子算法在使用过程中需要确定不同石油产品本身所适用的浓度范围,且其对预估计组分数敏感,组分数选择是否准确直接影响最终定性定量结果,这些问题都会对油类检测造成使用上的限制。油类组分极为复杂,其中各组分间不存在统一的线性浓度范围,其相互之间还受到荧光猝灭效应的影响。直接对未经稀释的油类样本进行光谱数据采集,所获得的三维荧光光谱会因样本中组分的种类及其含量不同而存在较大差异,导致对三维荧光光谱数据进行解析的平行因子分析算法不再适用。但组分的种类及含量相近的油样其光谱特征相似度较高,并且随着特定组分及其含量的改变,其光谱形状的变化规律也较为明显。基于此,将三维荧光光谱和数字图像识别相结合,提出一种针对混合油类样本的辨识方法。首先,利用五种矿物油（汽油、柴油、航空煤油、机油和润滑油）配制三类混合油样本,其中每类混合油是用其中两种不同矿物油以不同体积比直接混合配制而成;然后利用FS920荧光光谱仪获取样本的三维荧光光谱数据,并对该数据进行求导及灰度化预处理,进而得到三维荧光导数光谱灰度图;其次提取样本三维荧光导数光谱灰度图的颜色、纹理和形状等数字图像特征;最后,通过Fisher判别分析建立样本的分类模型,采用逐步回归建立混合油样本各组分相对体积的定量模型。分类模型对三类混合油样本的分类及识别效果良好。所建立的定量模型的线性相关性R大于0.99,显著性检验p值小于0.05。研究结果表明,三维荧光光谱的数字图像特征可以被本文所述方法有效提取并用于对油类样本的定性定量分析。该研究为海面溢油检测提供了一种简单、可靠的识别方法。     

Hadronic quark distribution amplitudes from QCD sum-rule moments

We discuss the reliability of hadronic wave functions (quark distribution amplitudes) determined by a finite number of QCD sum-rule moments. Although the expansion coefficients for polynomial models of the wave function are uniquely determined by the moments, the inherent uncertainty in such moments leads to a considerable indeterminacy in the wave functions because minimal changes of the moments can lead to large oscillations of the model function. In particular, the freedom in the moments left by QCD sum rules leads to a nonconverging polynomial expansion. This remains true even if additional constraints on the wave functions are used. As a consequence of this, the widely used procedure of constructing polynomial models of hadronic wave function from QCD sum rule moments does not guarantee even a reasonable approximation to the true wave function. The differences among the model wave functions persist also in the calculations of physical observables like hadronic form factors. This implies that physical observables calculated by means of such model wave functions are in general very unreliable. As specific examples, we examine the pion and nucleon wave functions and show that Gegenbauer as well as Appell polynomial expansions constructed from QCD sum rule moments are ruled out. The implications for the wave functions which are generally used in the literature are discussed.     

基于先验组分的多谱CT序列DCM融合算法研究

多谱CT成像是通过不同谱段的CT图像表征检测对象中的不同组分。为了便于在同一视图中显示所有组分的信息,需要研究多谱CT序列的融合方法;但是常用融合方法如加权平均法、小波变换融合法等都是针对图像细节信息的优化,不能表达组分的物理特性,从而导致融合图像的灰度不具有物理表征性,影响CT的定量检测。为此,结合具有物理表征特征的数据约束模型(DCM),开展了基于先验组分的多谱CT序列DCM融合算法研究。首先通过能谱滤波分离的成像方法获得多个能谱范围内的多能投影数据,采用TV-OSEM算法重建不同能谱段的CT序列;其次,利用传统DCM模型和改进DCM模型分别对多谱CT序列进行融合,传统DCM模型是严格单能的,由于滤波后能谱的非严格单能特性,其融合结果不能表征出对象序列中的全部组分。针对此问题提出了改进DCM模型。改进DCM模型选择了新的体元定义,并且在多谱CT序列融合中引入先验组分作为参照,通过先验物质对融合结果中其他物质进行校准,实现检测对象中各组分位置的准确分布。仿真实验表明,该方法可从物理表征正确性的角度,实现多谱CT序列融合,在满足CT序列中不同组分区分的同时,其融合图像的灰度具有物理可参照性,有利于后续的CT定量检测。     

基于亚像素区域加权能量特征的多尺度图像融合算法

对矩形和圆形区域中各像素进行亚像素划分,确定各亚像素的权值,得到基于哑像素的综合加权区域能量.融合箅法首先对源图像进行金字塔分解,然后对金字塔的高频细节分量使用基于哑像素加权区域能量特征的融合规则取大,对低频粗糙分量取平均.得到融合图像的塔形分解,最后重构融合图像.仿真结果表明,新算法融合效果较常规的区域能量特征作为融合规则的多分辨率图像融合算法效果更好,从清晰度和熵的评价来看,提高了融合图像的品质.     

Restrictions on exact current correlation functions and reliability of sum-rule results

Criteria of reliability are studied for results obtained within the sum-rule approach in QCD and in some toy models. The criterion of validity of the approximation for current correlation functions based on operator-product expansion within Borel sum rules, suggested previously in the literature, is critically reexamined. A new criterion of validity of a perturbative approximation that makes use of the Källen-Lehmann representation and finite-energy sum rules is proposed. The stability of criteria against small variations in expansion coefficients is investigated in an exactly solvable model and in QCD.     

考虑帧间信息的语音带宽扩展

语音带宽扩展是为了提高语音质量,利用语音低频和高频之间的相关性重构语音高频的一种技术。高斯混合模型法是语音带宽技术中被广泛应用的一种方法,但是,该方法的映射函数是分段线性函数,且没有考虑语音前后帧的相关信息。因此,提出了一种基于条件受限玻尔兹曼机的方法。该方法利用条件受限玻尔兹曼机提取了语音信号的帧间信息,同时将语音低频、高频特征参数映射为高阶统计特性,深层发掘和模拟了语音低频和高频之间的非线性关系。客观和主观对比测试结果都表明,该方法性能优于传统的高斯混合模型方法。      

Transition probability functions for applications of inelastic electron scattering

In this work, the transition matrix elements for inelastic electron scattering are investigated which are the central quantity for interpreting experiments. The angular part is given by spherical harmonics. For the weighted radial wave function overlap, analytic expressions are derived in the Slater-type and the hydrogen-like orbital models. These expressions are shown to be composed of a finite sum of polynomials and elementary trigonometric functions. Hence, they are easy to use, require little computation time, and are significantly more accurate than commonly used approximations.