THE ASYMPTOTIC BEHAVIOR AND APPLICATIONS OF A CLASS OF PP R-STATISTICS

This paper uses R-statistics as projection indices to construct a class of projection pursuit(PP)R-statistics for multivariate two sample tests via PP techniques.Examples are presented asapplications to the location and dispersion problems.     

A FAST PROCEDURE OF VARIABLE SELECTION IN LINEAR REGRESSION MODEL

In many situations,we are interested in selection of important variables whichare adequate for prediction under a linear regression model.In this paper,a fast selectionprocedure is proposed and is proved to be strongly consistent.Also,the convergence rate ofmisjudgement probability is given.     

BOOTSTRAPPING PP L-STATISTICS FOR TESTS

Some bootstrap approximations of the asymptotic distributions of PP L-statistics whichwere proposed by the authors in[7]are discusse.Bootstrap statistics and their asymptotic propertiesare established.Two examples and the numerical results are given,by which one can actuallyimplement the proposed tests under the condition of normal population.     

基于模糊投影寻踪聚类的洪灾评估模型

针对洪水灾害样本集的复杂性、随机性以及差异性,本文将模糊聚类迭代理论与投影寻踪技术进行互补融合,构建了模糊投影寻踪聚类模型.该模型采用投影值标准差和投影值欧氏距离平方和来构造投影指标函数,避免了传统投影寻踪模型由于经验性选取密度窗宽导致过于主观的问题;将高维数据低维化后进行模糊聚类运算,再通过对最优投影方向的寻优进行投影寻踪聚类运算,降低了模糊聚类迭代的运算量,实现了两种模型的双重迭代聚类.误差分析及聚类有效性评价表明,互补融合后模糊聚类与投影寻踪聚类的双重迭代聚类使得聚类精度和效果也得到了较大提高;此外,除优化算法初始化参数外,模型无需预设其它参数,也不依赖于随机训练样本,可客观依据历史样本集内在规律来进行洪灾聚类评估.实例研究和方法比较表明,提出的模型计算简洁,且能有效处理洪灾评估中的随机、模糊等主客观不确定性,能够为洪灾风险管理提供科学的决策支撑.     

投影神经网络及其应用

本文提出了一种投影神经网络以实现模式矢量向某一空间的投影,文中详细讨论了网络的结构,并提出了一种调整联接权的格形学习算法。本文将投影神经网络应用于飞机目标冲激响应波形的识别问题,得到了良好的效果,研究结果表明这种投影神经网络具有投影精度高、实时性好的优点。     

线性离散动态变结构经济系统的相似结构聚类方法

本文探讨了经济系统的变结构性，提出了线性离散动态变结构经济系统的结构相似性概念，同时给出了按相似结构建立线性经济系统数学模型的聚类方法     

A CLUSTERING ALGORITHM FOR MIXED NUMERIC AND CATEGORICAL DATA

Most of the earlier work on clustering mainly focused on numeric data whose inherent geometric properties can be exploited to naturally define distance functions between data points. However, data mining applications frequently involve many datasets that also consists of mixed numeric and categorical attributes. In this paper we present a clustering algorithm which is based on the k-means algorithm. The algorithm clusters objects with numeric and categorical attributes in a way similar to k-means. The object similarity measure is derived from both numeric and categorical attributes. When applied to numeric data, the algorithm is identical to the k-means. The main result of this paper is to provide a method to update the “cluster centers“ of clustering objects described by mixed numeric and categorical attributes in the clustering process to minimise the clustering cost function. The clustering performance of the algorithm is demonstrated with the two well known data sets, namely credit approval and abalone databases.     

ON TESTS FOR LOCAL EXTREMUM POINTS IN PROJECTION PURSUIT

ＯＮＴＥＳＴＳＦＯＲＬＯＣＡＬＥＸＴＲＥＭＵＭＰＯＩＮＴＳＩＮＰＲＯＪＥＣＴＩＯＮＰＵＲＳＵＩＴＺＨＡＮＧＪｉａｎ；ＬＩＧｕｏｙｉｎｇ（ＩｎｓｔｉｔｕｔｅｏｆＳｙｓｔｅｍｓＳｃｉｅｎｃｅ，ＡｃａｄｅｍｉａＳｉｎｉｃａ，Ｂｅｉｊｉｎｇ１０００８０，Ｃｈ...     

Capturability of Pseudo Differential Games of Pursuit

This paper discusses the capturability with fixed time of a pseudo-linear differentialgame of pursuit.The pursuit set in which the pursuit will end once the initial state lies in this set isgiven by the method of integration of multi-valued function.The results obtained here solve an openproblem of Pontrjagin's on the linear differential game of pursuit.Meanwhile,the requirement of theconvexity of the control set and other related Pontrjagin's conditions are removed.     

矩阵对策上的计策问题及其实例

通过商战和军事对策的实例引进了矩阵对策上的计策等形式结构,研究了计策及将计就计等概念的性质.定量地研究了当某个局中人识破对手的计策时,应以什么尺度决定是否使用将计就计.最后,讨论了局中人如何制定最优计策的问题.     

投影法带通信号的中频数字相干检波研究

本文提出一种应用投影法复值估计［１］在低中频直接采样中处理带通信号的方法。这种方法可以利用较少的采样数据,得到高精度的复值估计,从而实现对带通信号的相干检测。这种算法的计算量小,因而可以构成实时系统。计算机模拟的结果证明了这种高精度的信号处理方法是完全可行的。     

Incremental clustering algorithm via crossentropy

1.INTRODUCTION Fuzzyclusteringisanunsupervisedwayofdatagrouping andusefulinpatternrecognition,informationretrieval,imageprocessing,faultdetection[1,2].Itgroupsdatainto finiteclustersbyusingsomekindsofmeasuressuchasthe linearandnon lineardistance,theentropymeasure,or inclusiondegreeinfuzzyenvironments.Intermsofthe modelsandmeasuresbetweenobjects,differentalgo rithmspartitiondifferentdatasetsandproduceclusters withdifferentshapesandhavedistinctdifferenceintime andspaceefficiency.Currentclus…     

Kernel method-based fuzzy clustering algorithm

1.INTRODUCTION Clusteranalysisdividesdataintoclustersinorderto facilitateunderstandingortofindstructurehiddenin dataset.Clusteringalgorithmspartitionasetofdata objectsintoclustersorclasses,wheresimilardataob jectsareassignedtothesameclusterwhereasdissimi lardataobjectsshouldbelongtodifferentclusters. SinceZadeh(1965)presentedthefuzzysettheory, thefuzzymethodisfirstlyintroducedinclustering problems,whichiscalledthefuzzyclusteringanaly sis.Fuzzyclusteringisawidelyappliedmethodfor acquiri…     

基于投影寻踪和遗传算法的一种非线性系统建模方法

基于投影寻踪和遗传算法,提出了一种建立非线性系统模型的新方法及其算法实现,并给出了两个仿真算例.仿真结果表明,用本文提出的方法建立非线性系统模型,具有预测精度高、工程实用性好等优点.     

基于用户访问兴趣的Web日志挖掘

Web日志挖掘可以发现访问者兴趣和需求, 提出了一种改进的以访问时间、点击次数以及访问路径共同刻画用户的访问兴趣的Web日志挖掘算法. 首先以Web日志为基础构建相关矩阵, 使用平均访问时间相似度和访问路径相似度共同度量用户访问兴趣的相似程度, 最后采用直接聚类去除相交项的聚类算法将相似用户和相关URL聚类. 实证分析结果表明该算法能较好地解释用户的实际访问兴趣, 从而为网站提供相应的运营建议.     

Higher-order principal component pursuit via tensor approximation and convex optimization

Recovering the low-rank structure of data matrix from sparse errors arises in the principal component pursuit （PCP）. This paper exploits the higher-order generalization of matrix recovery, named higher-order principal component pursuit （HOPCP）, since it is critical in multi-way data analysis. Unlike the convexification （nuclear norm） for matrix rank function, the tensorial nuclear norm is stil an open problem. While existing preliminary works on the tensor completion field provide a viable way to indicate the low complexity estimate of tensor, therefore, the paper focuses on the low multi-linear rank tensor and adopt its convex relaxation to formulate the convex optimization model of HOPCP. The paper further propose two algorithms for HOPCP based on alternative minimization scheme： the augmented Lagrangian alternating direction method （ALADM） and its truncated higher-order singular value decomposition （ALADM-THOSVD） version. The former can obtain a high accuracy solution while the latter is more efficient to handle the computationally intractable problems. Experimental results on both synthetic data and real magnetic resonance imaging data show the applicability of our algorithms in high-dimensional tensor data processing.     

基于轮廓波变换和改进模糊c均值聚类的红外图像分割

针对红外图像分辨率低、对比度弱、易受噪声污染等特点,给出了轮廓波变换与模糊c均值聚类相结合的红外图像分割方法。该方法首先在假定图像轮廓波变换系数的先验为高斯分布的基础上,将基于最大后验概率准则的比例萎缩法应用于红外图像降噪,以完成分割前的预处理过程,然后利用改进的模糊c均值算法对降噪后的红外图像进行分割。针对标准模糊c均值分割存在的问题,本文提出的方法从基于样本直方图的最小最大距离法的初始聚类中心确定、考虑邻域像素相关性的样本点聚类权值和邻域隶属度修正三个方面加以改进,在保证分割精度的基础上,进一步滤除降噪阶段遗留下的图像噪声。对一系列红外图像进行实验的结果表明,相对于标准模糊c均值算法,本文提出的改进算法划分熵平均降低约10%,区域对比度提高约27%,能够实现对受到噪声污染红外图像的有效分割。     

CMA:an efficient index algorithmof clustering supporting fast retrieval oflarge image databases

1 .INTRODUCTIONWith the rapid development of computer and commu-nicationtechnologies ,thereis a tendency of sharpin-creasing of multi media information. Due to theircharacters of large quantity and difficulty in descrip-tion,it’s very difficult tofind users’neededinforma-tion accurately and quickly in the sea of multi mediainformation. Thus ,howto organize and index largemulti media information to support efficient retrievalbecomes the most urgent issue . I mage , which is asi mple medi…     

一种基于H.264的细粒度多适应性视频编码算法

提出了一种基于H．264的细粒度多适应性编码算法并对其进行了仿真实验。该算法综合运用了MP(Matching Pursuit)变换和位面编码等细粒度编码技术，灵活地将MP变换结果分为两个层次的码流，帧间预测也采用了两级预测模式，生成了多层次细粒度的视频压缩码流。该算法输出码流具有精细可调性，能自适应网络带宽变化，对于解决视频应用在现有尽力而为网络上所面，临的带宽波动和异构等问题有着重要意义。仿真实验证明了该算法的恢复质量和可伸缩性。     

ERBF network with immune clustering

Based on immune clustering and evolutionary programming(EP), a hybrid algorithm to train the RBF network is proposed. An immune fuzzy C-means clustering algorithm (IFCM) is used to adaptively specify the amount and initial positions of the RBF centers according to input data set; then the RBF network is trained with EP that tends to global optima. The application of the hybrid algorithm in multiuser detection problem demonstrates that the RBF network trained with the algorithm has simple network structure with good generalization ability.