基于遗传算法-支持向量机的兔肝VX2肿瘤光谱鉴别

兔肝VX２肿瘤是一种快速生长的肿瘤模型,可以在多种器官如肝、肺、直肠等快速生长,常用于肿瘤研究。采用可见-近红外高光谱技术对四只兔子的兔肝VX２肿瘤和正常组织进行活体和离体的反射光谱检测,然后采用支持向量机分别实现了二分类(正常肝组织和肝VX2肿瘤组织)和四分类(未出血活体正常肝组织、未出血活体VX2肿瘤组织、出血离体正常肝组织和出血离体肝VX2肿瘤组织)。根据其光谱反射曲线的特征,选择了400～1 800 nm区间的数据为特征变量。为进一步提高分类准确率,分别采用5折交叉验证和遗传算法对支持向量机的核函数参数g和惩罚因子c进行了优化。其中5折交叉验证优化参数和分类结果为：二分类优化的惩罚参数c为4,核函数参数g为0.125 0,其校正集和预测集的准确率都达到了100%;四分类中优化出的参数c为8,g为0.121 1,其校正集和预测集的准确率分别达到了99.242 4%和93.333%。遗传算法优化参数和结果为：二分类中优化的参数c为0.845 6,g为0.062 5,其校正集和预测集的准确率同样都达到了100%;四分类中优化的参数c为5.5307,g为0.068 5,其校正集和预测集的准确率分别达到了99.242 4%和100%。结果显示两种优化方法都取得了很好的效果,遗传算法优化参数对四分类的分类更为精确。为进一步提升算法速度,采用间隔选取变量的方法来不断减少特征变量,最终每隔100 nm谱段选择一个变量,共选择14个谱段作为特征变量。采用遗传算法优化支持向量机参数并对其分类进行了研究,结果表明：二分类和四分类的校正集和预测集结果准确率均为99.242 4%,而且运行时间分别为11.4和20.0 s, 与选择全波段的运行时间：340.3和491.0 s相比, 说明多光谱技术可以进行肝VX2肿瘤组织和正常肝组织的鉴别,且分类准确率可达99%以上,而且运行时间缩短了很多。为未来多光谱技术在未来临床肿瘤诊断中实现肿瘤组织的快速实时在线检测和分类奠定了基础,显示出巨大的应用潜力。     

Curvelet based image compression via core vector machine

In this paper, a novel curvelet based digital image compression scheme is proposed. Aiming at achieving high compression ratio, the proposed scheme embeds a representative machine learning method, core vector machine (CVM), in the encoding process of the image compression technique. The core vector machine (CVM) has been introduced as an extremely fast classifier which is demonstrably superior to standard support vector machine (SVM) on very large datasets. In this scheme, we appropriately utilize the characteristic of CVM to reduce huge numbers of curvelet coefficients. Compared with image compression algorithms do not use CVM and methods based on wavelet transform, experimental results show that the compression performance of our method gains much improvement in peak-signal-to-noise-ratio (PSNR) and CPU time. Moreover, the algorithm works fairly well for declining block effect at higher compression ratios.     

A flexible framework for Group Decision Support: WINGDSS version 3.0

A flexible framework for Group Decision Support on PCs in Microsoft Windows environment is presented. WINGDSS does not replace human judgment but highly supports the entire process of decision making, from problem structuring to post-decision analysis. The latest version of WINGDSS is a modular, open system with a dynamical connection to relational databases, an interpreter for defining problem specific evaluation procedures, a lot of interactive features from setting up the tree of criteria until the sensitivity analysis on individual/group ranking. By providing tools for recursively redefining the decision problem, WINGDSS helps the decision makers in achieving a result satisfactory to the whole group.Research supported in part by the Hungarian Foundation for Scientific Research, Grant No. 2568 and by the Hungarian National Committee for Technical Research and Development, Grant No. 93-97-67-0553.     

Support properties and Holmgren's uniqueness theorem for differential operators with hyperplane singularities

Let W be a finite Coxeter group acting linearly on Rn. In this article we study the support properties of a W-invariant partial differential operator D on Rn with real analytic coefficients. Our assumption is that the principal symbol of D has a special form, related to the root system corresponding to W. In particular the zeros of the principal symbol are supposed to be located on hyperplanes fixed by reflections in W. We show that conv(suppDf)=conv(suppf) holds for all compactly supported smooth functions f so that conv(suppf) is W-invariant. The main tools in the proof are Holmgren's uniqueness theorem and some elementary convex geometry. Several examples and applications linked to the theory of special functions associated with root systems are presented.     

Rainfall forecasting by technological machine learning models

Accurate forecasting of rainfall has been one of the most important issues in hydrological research. Due to rainfall forecasting involves a rather complex nonlinear data pattern; there are lots of novel forecasting approaches to improve the forecasting accuracy. Recurrent artificial neural networks (RNNS) have played a crucial role in forecasting rainfall data. Meanwhile, support vector machines (SVMs) have been successfully employed to solve nonlinear regression and time series problems. This investigation elucidates the feasibility of hybrid model of RNNs and SVMs, namely RSVR, to forecast rainfall depth values. Moreover, chaotic particle swarm optimization algorithm (CPSO) is employed to choose the parameters of a SVR model. Subsequently, example of rainfall values during typhoon periods from Northern Taiwan is used to illustrate the proposed RSVRCPSO model. The empirical results reveal that the proposed model yields well forecasting performance, RSVRCPSO model provides a promising alternative for forecasting rainfall values.     

基于支持向量机测定水质中硝酸盐含量

针对水质中被测物硝酸盐与干扰物铁离子、铬离子紫外吸收谱线严重重叠的问题,将支持向量机应用于混合重叠光谱分析中,利用核函数将重叠的光谱数据进行高维空间变换后求得SVM回归模型,实现硝酸盐含量的光谱检测。实验结果表明:硝酸盐浓度在0.5—10mg/L范围内,所测得含量的最大相对误差为3.2%;平均回收率为100.9%,本法与传统的方法相比,要求条件较低,不需要物理或化学的分离,分析速度快,有望应用于在线监测污水中硝酸盐的含量。     

广义α-stable过程自相交局部时增量的Holder律及重点

文研究了 N 指标 d 维广义α-stable过程自相交局部时增量的Holder律. 并利用所得自相交局部时的性质, 证明了该过程重点的存在性, 得到了该过程多重时的Hausdorff维数及测度的下界.所得结论包含并推广了广义布朗单及stable单相应的结果.     

On convergence of closed convex sets

In this paper we introduce a convergence concept for closed convex subsets of a finite-dimensional normed vector space. This convergence is called C-convergence. It is defined by appropriate notions of upper and lower limits. We compare this convergence with the well-known Painlevé-Kuratowski convergence and with scalar convergence. In fact, we show that a sequence (An)_n∈NC-converges to A if and only if the corresponding support functions converge pointwise, except at relative boundary points of the domain of the support function of A, to the support function of A.     

Predicting O-glycosylation sites in mammalian proteins by using SVMs

O-glycosylation is one of the most important, frequent and complex post-translational modifications. This modification can activate and affect protein functions. Here, we present three support vector machines models based on physical properties, 0/1 system, and the system combining the above two features. The prediction accuracies of the three models have reached 0.82, 0.85 and 0.85, respectively. The accuracies of the three SVMs methods were evaluated by 'leave-one-out' cross validation. This approach provides a useful tool to help identify the O-glycosylation sites in mammalian proteins. An online prediction web server is available at http://www.biosino.org/Oglyc.     

Ultradistributional boundary values of harmonic functions on the sphere

We present a theory of ultradistributional boundary values for harmonic functions defined on the Euclidean unit ball. We also give a characterization of ultradifferentiable functions and ultradistributions on the sphere in terms of their spherical harmonic expansions. To this end, we obtain explicit estimates for partial derivatives of spherical harmonics, which are of independent interest and refine earlier estimates by Calderón and Zygmund. We apply our results to characterize the support of ultradistributions on the sphere via Abel summability of their spherical harmonic expansions.