FREQUENCY DOMAIN TESTS OF MULTIVARIATE GAUSSIANITY AND LINEARITY

A stationary multivariate time series { X _t } is defined as linear if it can be written in the form X _t = ∑^∞ _{j =−∞} A _j e _{t − j} where A _j are square matrices and e _t are independent and identically distributed random vectors. If the e _t } are normally distributed, then { X _t is a multivariate Gaussian linear process. This paper is concerned with the testing of departures of a vector stationary process from multivariate Gaussianity and linearity using the bispectral approach. First the definition and properties of cumulants of random matrices are used to obtain the expressions for the higher-order cumulant and spectral vectors of a linear vector process as defined above. Then it is shown that linearity of a vector process implies constancy of the modulus square of its normalized higher-order spectra whereas the component of such a vector process does not necessarily have a linear representation. Finally, statistics for the testing of multivariate Gaussianity and linearity are proposed.     

基于改进卡方统计的微博特征提取方法

通过对微博文本特征信息的分析与研究,提出一种基于改进卡方统计的微博特征提取方法。扩充微博信息分类特征,在传统的卡方统计量的基础上,引入了频度等因素,改进特征选择方法;在传统的特征项权值计算的基础上,提出了新的改进卡方统计量的方法,改进权重计算效果。对上述方法利用经典KNN和SVM算法进行了测试,实验结果表明该方法提高了微博信息分类的准确率。     

A multivariate study of the correlation between tocopherol content and fatty acid composition in vegetable oils

The main biochemical function of the tocopherols is believed to be the protection of polyunsaturated fatty acids (PUFA) against peroxidation. A critical question that must be asked in reference to this is whether there is a biochemical link between the tocopherol levels and the degree of unsaturation in vegetable oils, the main source of dietary PUFA and vitamin E. We used a mathematical approach in an effort to highlight some facts that might help address this question. Literature data on the relative composition of fatty acids (16:0, 16:1, 18:0, 18:1, 18:2, and 18:3) and the contents of tocopherols (α-, β-, δ-, and γ-tocopherol) in 101 oil samples, including 14 different botanical species, were analyzed by principal-component analysis and linear regression. There was a negative correlation between α- and γ-tocopherols (r=0.633, P<0.05). Results also showed a positive correlation between linoleic acid (18:2) and α-tocopherol (r=0.549, P<0.05) and suggested a positive correlation between linolenic acid (18:3) and γ-tocopherol.     

A review of the current status of small-scale seawater reverse osmosis desalination

The current status of small-scale desalination (produced water capacity 100 m³/day or less) is reviewed to provide an overview of the market segment. The use of energy-recovery devices in this market segment is also reviewed. We find that the Middle East accounts for the largest market share worldwide at present, and reverse osmosis is overwhelmingly dominant among the desalination technologies adopted. Implementation of energy-recovery devices at small scale is rare, which leads to relatively high energy consumption for small-scale seawater reverse osmosis desalination systems.     

全参考图像质量评价综述

图像质量评价是图像处理领域内一项很有意义的研究课题。客观图像质量评价方法可分为全参考评价方法、半参考评价方法和无参考评价方法, 目前全参考评价方法较为成熟, 而半参考和无参考评价方法则处于初级阶段, 远远达不到参考评价方法所能达到的效果。对全参考评价方法进行综述。首先简要地介绍了各种类型的评价方法, 其次详细地介绍了PSNR、SSIM、MSSIM、IFC、VIF、FSIM等几种典型的全参考图像质量评价方法, 然后在LIVE和TID2008数据库上进行实验, 对这几种全参考方法进行对比、分析, 最后探讨图像质量评价研究的发展趋势。     

基于Blowfish和MD5的混合加密方案*

针对Blowfish算法在实际应用中存在的等价密钥、重复初始化等问题,提出Blowfish与MD5算法相结合,将MD5算法的生成值作为密钥的一部分对Blowfish算法进行初始化,使用概率统计方法证明该方案弥补了Blowfish算法的实际应用缺陷。计算结果表明,混合加密方案具有更高的安全性、更快的速度。     

基于图像噪声分析的计算机生成图像检测算法

计算机生成图像与自然图像在物理生成机理上的差异性导致其在噪声分布上具有明显的区别,据此提出一种基于图像噪声分析的计算机生成图像检测新方法。首先,用小波隐马尔可夫(MMT)模型对图像噪声进行预处理;接着,基于最大似然估计方法估测图像参考模式噪声;最后,在提取图像模式噪声统计距及其与参考模式噪声相关差值基础上,利用支持向量机(SVM)分类器进行鉴别。实验结果显示,较已有的典型算法,该算法具有更好的检测率。     

Speech-stream detection in short-wave channel based on empirical mode decomposition and higher-order statistics

To capture the presence of speech embedded in nonspeech events and background noise in short-wave non-cooperative communication,an algorithm for speech-stream detection in noisy environments is presented based on Empirical Mode Decomposition (EMD) and statistical properties of higher-order cumulants of speech signals.With the EMD,the noise signals can be decomposed into different numbers of IMFs.Then,the fourth-order cumulant (FOC) can be used to extract the desired feature of statistical properties for IMF components.Since the higher-order cumulants are blind for Gaussian signals,the proposed method is especially effective regarding the problem of speech-stream detection,where the speech signal is distorted by Gaussian noise.With the self-adaptive decomposition by EMD,the proposed method can also work well for non-Gaussian noise.The experiments show that the proposed algorithm can suppress different noise types with different SNRs,and the algorithm is robust in real signal tests.     

商务智能、归纳逻辑与统计学的关联研究

商务智能是提高企业竞争能力的一种建设方案,其主要技术包括数据仓库、数据挖掘和联机分析等。举例说明了商务智能技术在客户关系管理中的应用。对案例的分析表明,商务智能技术的基础是统计学和归纳逻辑。作为传统哲学分支的归纳逻辑学,以现代统计学作为中介,在经济学领域的商务智能中找到了应用。深入探讨这三个截然不同的学科之间的密切关系,不仅将有助于商务智能及其应用开发的研究,从而推动我国经济和社会的发展,而且也会给统计学和归纳逻辑学理论的研究带来深远的影响。