A method based on vector type for sparse storage and quick access to projection matrix

For sparse storage and quick access to projection matrix based on vector type, this paper proposes a method to solve the problems of the repetitive computation of projection coefficient, the large space occupation and low retrieval efficiency of projection matrix in iterative reconstruction algorithms, which calculates only once the projection coefficient and stores the data sparsely in binary format based on the variable size of library vector type. In the iterative reconstruction process, these binary files are accessed iteratively and the vector type is used to quickly obtain projection coefficients of each ray. The results of the experiments show that the method reduces the memory space occupation of the projection matrix and the computation of projection coefficient in iterative process, and accelerates the reconstruction speed.

Minimum Cycle of Row Vector of a Generalized Circulant Fuzzy Matrix

In this paper,we intreduce the concept and discuss the properties of minimum cycle of row vector in a generalized circulant Fuzzy matrix. We present a new expression for circulant Fuzzy matrix,and discuss some properties of the idempotent elements of the semigroup of generalized circulant Fuzzy matrixes in connection with minimum cycle of row vector.

Performance Prediction Based on Statistics of Sparse Matrix-Vector Multiplication on GPUs

As one of the most essential and important operations in linear algebra, the performance prediction of sparse matrix-vector multiplication (SpMV) on GPUs has got more and more attention in recent years. In 2012, Guo and Wang put forward a new idea to predict the performance of SpMV on GPUs. However, they didn’t consider the matrix structure completely, so the execution time predicted by their model tends to be inaccurate for general sparse matrix. To address this problem, we proposed two new similar models, which take into account the structure of the matrices and make the performance prediction model more accurate. In addition, we predict the execution time of SpMV for CSR-V, CSR-S, ELL and JAD sparse matrix storage formats by the new models on the CUDA platform. Our experimental results show that the accuracy of prediction by our models is 1.69 times better than Guo and Wang’s model on average for most general matrices.

Empirical Likelihood Statistical Inference for Compound Poisson Vector Processes under Infinite Covariance Matrix

The paper discusses the statistical inference problem of the compound Poisson vector process(CPVP)in the domain of attraction of normal law but with infinite covariance matrix.The empirical likelihood(EL)method to construct confidence regions for the mean vector has been proposed.It is a generalization from the finite second-order moments to the infinite second-order moments in the domain of attraction of normal law.The log-empirical likelihood ratio statistic for the average number of the CPVP converges to F distribution in distribution when the population is in the domain of attraction of normal law but has infinite covariance matrix.Some simulation results are proposed to illustrate the method of the paper.

Solution of the Matrix Second Semi-Tensor Product Equation A ∘ l X ∘ l B=C

In this paper, the solution of the matrix second semi-tensor product equation A∘lX∘lB=Cis studied. Firstly, the solvability of the matrix-vector second semi-tensor product equation is investigated. At the same time, the compatibility conditions, the sufficient and necessary conditions and the specific solution methods for the matrix solution are given. Secondly, we further consider the solvability of the second semi-tensor product equation of the matrix. For each part, several examples are given to illustrate the validity of the results.

以编译为导向的Matrix-DSP程序分析与优化

数字信号处理器(DSP)在图像处理、自动化控制、信号处理等多个领域具有广泛应用。自主研发的Matrix DSP采用了典型的单指令多数据SIMD+超长指令字VLIW的向量化架构,因此面向该架构如何实现高效的向量化编程与优化是一项重要挑战。基于Matrix DSP的体系结构特点,以编译器性能为导向,对内核级代码常用的分析优化手段进行梳理和总结,并结合一个通用矩阵乘的例子进行展示,其执行性能可最高提升1个数量级。最后,从编译器优化和程序员高效编程的角度提出了一些后续的思考与讨论。

基于改进i-vector的说话人感知训练方法研究

基于辨识向量(i-vector)的说话人感知训练方法使用MFCC作为输入特征对i-vector进行提取,但MFCC较差的特征鲁棒性会影响该训练方法的识别性能。为此,提出一种基于改进i-vector的说话人感知训练方法。设计基于SVD的低维特征提取方法,用其提取的特征替代MFCC对表征能力更优的i-vector进行提取。实验结果表明,在捷克语语料库中,相对于DNN-HMM语音识别系统与原始基于i-vector的说话人感知训练方法,该方法的识别性能分别提升了1.62%与1.52%,在WSJ语料库中,该方法识别性能分别提升了3.9%和1.48%。

Classification using wavelet packet decomposition and support vector machine for digital modulations

To make the modulation classification system more suitable for signals in a wide range of signal to noise rate （SNR）, a feature extraction method based on signal wavelet packet transform modulus maxima matrix （WPTMMM） and a novel support vector machine fuzzy network （SVMFN） classifier is presented. The WPTMMM feature extraction method has less computational complexity, more stability, and has the preferable advantage of robust with the time parallel moving and white noise. Further, the SVMFN uses a new definition of fuzzy density that incorporates accuracy and uncertainty of the classifiers to improve recognition reliability to classify nine digital modulation types （i.e. 2ASK, 2FSK, 2PSK, 4ASK, 4FSK, 4PSK, 16QAM, MSK, and OQPSK）. Computer simulation shows that the proposed scheme has the advantages of high accuracy and reliability （success rates are over 98% when SNR is not lower than 0dB）, and it adapts to engineering applications.

Direction and polarization estimation for coherent sources using vector sensors

A two-dimensional direction-of-arrival （DOA） and polarization estimation algorithm for coherent sources using a linear vector-sensor array is presented. Two matrices are first constructed by the receiving data. The ranks of the two matrices are only related to the DOAs of the sources and independent of their coherency. Then the source’s elevation is resolved via the matrix pencil （MP） method, and the singular value decomposition （SVD） is used to reduce the noise effect. Finally, the source’s steering vector is estimated, and the analytics solutions of the source’s azimuth and polarization parameter can be directly computed by using a vector cross-product estimator. Moreover, the proposed algorithm can achieve the unambiguous direction estimates, even if the space between adjacent sensors is larger than a half-wavelength. Theoretical and numerical simulations show the effectiveness of the proposed algorithm.

畸变Data Matrix码图像的倾斜校正算法研究

针对Data Matrix码倾斜校正中需要多次旋转的问题,本文提出了一种畸变二维码倾斜校正方法。首先使用LoG算子对二值化后的图像进行边缘检测,再基于Data Matrix码的结构特征,通过Hough变换有效快速地确定定位符"L"所在的位置,并将"L"型交点用两条向量表示。然后通过向量叉乘计算出Data Matrix码的旋转角度、确定旋转方向,只需一次旋转即可实现倾斜校正。本文算法节省了Data Matrix码在图像恢复过程中所需的时间和工作量。

Kernel matrix learning with a general regularized risk functional criterion

Kernel-based methods work by embedding the data into a feature space and then searching linear hypothesis among the embedding data points. The performance is mostly affected by which kernel is used. A promising way is to learn the kernel from the data automatically. A general regularized risk functional （RRF） criterion for kernel matrix learning is proposed. Compared with the RRF criterion, general RRF criterion takes into account the geometric distributions of the embedding data points. It is proven that the distance between different geometric distdbutions can be estimated by their centroid distance in the reproducing kernel Hilbert space. Using this criterion for kernel matrix learning leads to a convex quadratically constrained quadratic programming （QCQP） problem. For several commonly used loss functions, their mathematical formulations are given. Experiment results on a collection of benchmark data sets demonstrate the effectiveness of the proposed method.

Reverse-time migration and amplitude correction in the angle-domain based on Poynting vector

We propose a method based on the Poynting vector that combines angle-domain imaging and image amplitude correction to overcome the shortcomings of reverse-time migration that cannot handle different angles during wave propagation. First, the local image matrix （LIM） and local illumination matrix are constructed, and the wavefield propagation directions are decomposed. The angle-domain imaging conditions are established in the local imaging matrix to remove low-wavenumber artifacts. Next, the angle-domain common image gathers are extracted and the dip angle is calculated, and the amplitude-corrected factors in the dip angle domain are calculated. The partial images are corrected by factors corresponding to the different angles and then are superimposed to perform the amplitude correction of the final image. Angle-domain imaging based on the Poynting vector improves the computation efficiency compared with local plane-wave decomposition. Finally, numerical simulations based on the SEG/EAGE velocity model are used to validate the proposed method.

On the completeness of eigen and root vector systems for fourth-order operator matrices and their applications

In this paper, we consider the eigenvalue problem of a class of fourth-order operator matrices appearing in mechan- ics, including the geometric multiplicity, algebraic index, and algebraic multiplicity of the eigenvalue, the symplectic orthogonality, and completeness of eigen and root vector systems. The obtained results are applied to the plate bending problem.

Stability of GM(1,1) power model on vector transformation

The morbidity problem of the GM（1,1） power model in parameter identification is discussed by using multiple and rotation transformation of vectors. Firstly we consider the morbidity problem of the special matrix and prove that the condition number of the coefficient matrix is determined by the ratio of lengths and the included angle of the column vector, which could be adjusted by multiple and rotation transformation to turn the matrix to a well-conditioned one. Then partition the corresponding matrix of the GM（1,1） power model in accordance with the column vector and regulate the matrix to a well-conditioned one by multiple and rotation transformation of vectors, which completely solve the instability problem of the GM（1,1） power model. Numerical results show that vector transformation is a new method in studying the stability problem of the GM（1,1） power model.

Flatness intelligent control via improved least squares support vector regression algorithm

To overcome the disadvantage that the standard least squares support vector regression(LS-SVR) algorithm is not suitable to multiple-input multiple-output(MIMO) system modelling directly,an improved LS-SVR algorithm which was defined as multi-output least squares support vector regression(MLSSVR) was put forward by adding samples' absolute errors in objective function and applied to flatness intelligent control.To solve the poor-precision problem of the control scheme based on effective matrix in flatness control,the predictive control was introduced into the control system and the effective matrix-predictive flatness control method was proposed by combining the merits of the two methods.Simulation experiment was conducted on 900HC reversible cold roll.The performance of effective matrix method and the effective matrix-predictive control method were compared,and the results demonstrate the validity of the effective matrix-predictive control method.

Using position specific scoring matrix and auto covariance to predict protein subnuclear localization

The knowledge of subnuclear localization in eukaryotic cells is indispensable for under-standing the biological function of nucleus, genome regulation and drug discovery. In this study, a new feature representation was pro-posed by combining position specific scoring matrix (PSSM) and auto covariance (AC). The AC variables describe the neighboring effect between two amino acids, so that they incorpo-rate the sequence-order information;PSSM de-scribes the information of biological evolution of proteins. Based on this new descriptor, a support vector machine (SVM) classifier was built to predict subnuclear localization. To evaluate the power of our predictor, the benchmark dataset that contains 714 proteins localized in nine subnuclear compartments was utilized. The total jackknife cross validation ac-curacy of our method is 76.5%, that is higher than those of the Nuc-PLoc (67.4%), the OET- KNN (55.6%), AAC based SVM (48.9%) and ProtLoc (36.6%). The prediction software used in this article and the details of the SVM parameters are freely available at http://chemlab.scu.edu.cn/ predict_SubNL/index.htm and the dataset used in our study is from Shen and Chou’s work by downloading at http://chou.med.harvard.edu/ bioinf/Nuc-PLoc/Data.htm.

Forced Axial and Torsional Vibrations of a Shaft Line Using the Transfer Matrix Method Related to Solution Coefficients

This present paper deals with a mathematical description of linear axial and torsional vibrations. The normal and tangential stress tensor components produced by axial-torsional deformations and vibrations in the propeller and intermediate shafts, under the influence of propeller-induced static and variable hydrodynamic excitations are also studied. The transfer matrix method related to the constant coefficients of differential equation solutions is used. The advantage of the latter as compared with a well-known method of transfer matrix associated with state vector is the possibility of reducing the number of multiplied matrices when adjacent shaft segments have the same material properties and diameters. The results show that there is no risk of buckling and confirm that the strength of the shaft line depends on the value of the static tangential stresses which is the most important component of the stress tensor.

Binary Image Steganalysis Based on Distortion Level Co-Occurrence Matrix

In recent years,binary image steganography has developed so rapidly that the research of binary image steganalysis becomes more important for information security.In most state-of-the-art binary image steganographic schemes,they always find out the flippable pixels to minimize the embedding distortions.For this reason,the stego images generated by the previous schemes maintain visual quality and it is hard for steganalyzer to capture the embedding trace in spacial domain.However,the distortion maps can be calculated for cover and stego images and the difference between them is significant.In this paper,a novel binary image steganalytic scheme is proposed,which is based on distortion level co-occurrence matrix.The proposed scheme first generates the corresponding distortion maps for cover and stego images.Then the co-occurrence matrix is constructed on the distortion level maps to represent the features of cover and stego images.Finally,support vector machine,based on the gaussian kernel,is used to classify the features.Compared with the prior steganalytic methods,experimental results demonstrate that the proposed scheme can effectively detect stego images.

QoS Routing Algorithm with Multi-Dimensions for Overlay Networks

Overlay networks have emerged as a useful approach to providing a general framework for new applications and services that are to be implemented without significantly changing the IP-layer network infrastructure.Overlay routing has been used as an alternative to the default best effort Internet routing for the absence of end-to-end Quality of Service(QoS). While the former has recently been investigated, the conflict of QoS restraints and resource optimization remains unsolved. Recent studies have shown that overlay paths can give better latency, loss rate and TCP throughput. In this paper, a multi-dimensional QoS objective model based on the analysis of multiple QoS constraints has been presented, and a routing algorithm to optimise the overlay resource of its nodes and links is then proposed.In fact, the algorithm obtained multiple QoS values using probability theory to achieve the routing according to the multi-dimensional QoS objective vector of the QoS objective model. Simulation results reveals that the algorithm works better than other existing algorithms in balancing the network resources, and applications with stringent QoS requirements could be run.

用说话人相似度i-vector的非负值矩阵分解说话人聚类

基于贝叶斯或者全贝叶斯准则的说话人自动聚类或者识别方法,主要采取重复换算全发话语音段的相似量度,再组合相似性较大的语音片段实现说话人的聚类。这种方法中如果发话语音片段数越多,组合计算时间就越长,系统实时性变差,而且各说话人模型用GMM方法建立,发话语音时间短暂时GMM的信赖性降低,最终影响说话人聚类精度。针对上述问题,提出引用i-vector说话人相似度的非负值矩阵分解的高精度快速说话人聚类方法。