A new type SVM-projected SVM

Support vector machine (SVM), developed by Vapnik et al., is a new and promising technique for classification and regression and has been proved to be competitive with the best available learning machines in many applications. However, the classification speed of SVM is substantially slower than that of other techniques with similar generalization ability. A new type SVM named projected SVM (PSVM), which is a combination of feature vector selection (FVS) method and linear SVM (LSVM), is proposed in present paper. In PSVM, the FVS method is first used to select a relevant subset (feature vectors, FVs) from the training data, and then both the training data and the test data are projected into the subspace constructed by FVs, and finally linear SVM(LSVM) is applied to classify the projected data. The time required by PSVM to calculate the class of new samples is proportional to the count of FVs. In most cases, the count of FVs is smaller than that of support vectors (SVs), and therefore PSVM is faster than SVM in running. Compared with other speeding-up techniques of SVM, PSVM is proved to possess not only speeding-up ability but also de-noising ability for high-noised data, and is found to be of potential use in mechanical fault pattern recognition.     

用地面阵列寻找TeV能区γ点源的方法探讨

文中探讨搜寻TeV能区γ点源的方法.讨论利用student变量t判断来自源区及背景区宇宙线事例的统计差别,并由Bayes定理与MonteCarlo模拟相结合计算源区各能段的信号数,推算蟹状星云在TeV能区的γ射线微分能谱     

Au等离子体M带5f-3d跃迁的电子离子碰撞激发速率系数

电子离子碰撞激发速率系数在超组态碰撞辐射模型中真实模拟非局域热动力学平衡Au激光等离子体M带谱 5f 3d跃迁中各种复杂电荷态离子的电离态特性 (譬如离子的平均电离度 ,相对丰度和能级布居数 )是必不可少的。基于准相对论多组态Hartree Fock方法和扭曲波玻恩交换近似 ,采用自编的扭曲波程序ACDW (9)和Fit(9) ,从头计算了Au等离子体M带 5f 3d电子离子碰撞激发速率系数。结果表明 :在“神光II”实验装置诊断的电子温度约 2keV ,电子密度约 6× 10 2 1cm-3 范围内 ,这些电子离子碰撞激发参数有利于采用超组态碰撞辐射模型模拟Au的激光等离子体M带 5f～ 3d细致谱的平均电离度和电荷态分布。     

Evolution of Weighted Networks by Duplication-Divergence Mechanism

The duplication and divergence process is ubiquitous in nature and man-made networks. Motivated by the duplication-divergence mechanism which depicts the growth of protein networks, we propose a weighted network model in which topological evolution is coupled with weight dynamics. Large scale numerical results indicate that our model can naturally generate networks with power-law-like distributions of degree, strength and weight. The degree-strength correlation is illustrated as well. These properties are in agreement well with empirical data observed in real-world systems. Furthermore, by altering the retention probability δ, weighted, structured exponential networks are realized.     

对称正则长波方程的一个守恒差分格式

本文考虑了具有齐次边界条件的对称正则长波方程的有限差分法．构造了一个两层守恒的有限差分格式,利用离散泛函分析方法分析了格式的收敛性和稳定性,从理论上得到了收敛阶为O(h~2 τ)．数值试验表明,我们的方法是可信的．     

造纸污泥与废水污泥流化床焚烧时NO_x和SO_2的排放特性研究

1前言流化床焚烧污犯是近年来发达国家广泛采用的方法，它能很好地实现污泥的稳定化、无害化、减容化和资源化处理。燃煤流化床锅炉污染物排放方面已做了大量的研究工作，由于污泥与煤在结构和性质方面的差异较大，因此有必要对流化床焚烧污泥时污染物排放特性进行研究。本文详细研究了造纸、废水污泥在流化床中焚烧时污泥水份、运行床温及过量空气对NO。和SO。的排放特性及污泥N－＋NO。、S－SO。的转化率的影响，并对这两种性质差异较大的污泥焚烧时的NO。和502的生成特性进行了对比分析，取得了许多有价值的结果，为污泥流化床焚烧…     

工业CT图像均匀性校正

在工业CT图像重建过程中,射束硬化使得图像出现“杯状”伪影,阵列探测器响应不一致使得图像出现环状伪影、带状伪影和点伪影,影响图像均匀性.本文分析了射束硬化的原理和探测器响应不一致的数学模型,并通过实验,对探测器响应进行多挡板定标得到校正系数表.利用查表插值的方法对投影数据进行均匀性校正,消除上述伪影.     

Ferromagnetic Properties of Bond-Dilution and Random Positive or Negative Uniaxial Anisotropy Blume-Capel Model

We study the ferromagnetic properties of spin-1 system, which is considered in the frame of the bond dilution and random positive or negative anisotropy Blume-Capel model in the effective field theory and a cutting approximation. The investigation of phase diagrams displays some rich properties of the trajectory of tricritical point, reentrant henomena at low temperatures. Under certain both bond concentrations and random negative anisotropy, there are new transition lines of double tricritical points. So special emphasis is placed on the influence of the bond dilution and random anisotropy on phase diagrams. The magnetizations of the system are also discussed. Some results have not been evealed in previous reports.     

基于专家动态权重的群组AHP交互式决策方法

为了能在群组决策中得到更为客观和准确的决策结果,在把专家权重划分为静态权重和动态权重的基础上,研究了在交互式决策中专家动态权重的确定方法,给出了共识度的一个定义.在此基础上,研究了群组AHP交互式决策方法中的一致性和相容性检验,给出了基于专家动态权重的群组AHP交互式决策方法流程,最后用一个示例说明了该方法的应用步骤.     

马尔可夫域变模型在我国季度GDP增长率序列建模中的应用

本文建立了我国季度GDP同比增长率序列的马尔可夫域变模型,通过与线性AR(X)、LSTAR和ARCH等模型的比较,结果表明它更好地刻画了研究对象的均值、波动性和动态结构存在域变行为的非线性特征.