样本函数

We give several sufficient conditions of NA and NSD properties of random variables, compare the closeness of distribution functions of order statistics between NA and independent rv's, investigate properties of NSD defined by supermodular functions, study the dependence structure of stationary Markov process and order statistics and their spacings from two samples, establish stochastic comparisons of order statistics of heterogeneous rv's in the hazard rate and the reversed hazard rate orders, and give the first analytic proof of the closure property of the up shifted likelihood ratio order under convolution.

给出判定一组随机变量NA性质的几个充分条件，并给出NA和独立随机变量的次序统计量之间"贴近性"的比较，系统地研究基于特殊函数类所定义的NSD负相依概念，给出一些判别NSD性质的结构定理和一些有用概率不等式。系统研究平稳马氏过程的相依结构。研究两样本次序统计量及其问题隔的相依结构。在失效率、反向失效率序和似然序意义下给出非齐次随机变量次序统计量的比较。给出上漂移似然序卷积封闭性的第一个解析证明。

Choosing reliability simulation data as a sample, the parameter confidence interval as coding space and the reciprocal of errors between empirical distribution function and acquired distribution function as a fitness function, the point estimation model of age distribution is established based on the genetic algorithm, and the reliability function of complex systems is acquired.

以可靠性仿真数据为寿命样本，待估计参数的置信区间为编码空间，以经验分布与所求分布误差倒数为适应度函数，建立了基于遗传算法的寿命分布参数点估计模型，求得了复杂系统可靠度函数。

By using the kernel-type density estimation in the case of identically distributed and negatively associated samples, the empirical Bayes test rules for the scale exponential family are constructed, and the asymptotically optimal property is obtained.

本文利用同分布负相协样本情形概率密度函数的核估计构造了刻度指数族参数的经验Bayes检验函数，并获得了它的渐近最优

Therefore, to subsample"s observation of continuous random sample parent population, if we can"t get its material function easily, or we dont know its density function, we can use this way to approximate its distribution function. And these methods can achieve good approximation effect.

对连续型随机样本母体中的简单随机子样的观察值，在不易得到其具体分布或不知道其密度函数的情况下，可用此方法来近似求出其分布函数并可达到很好的逼近效果。

Finally, Bayesian methods for sample size calculation under 0~1 loss function and quadratic loss function were considered.

最后考虑了0-1损失函数和平方损失函数下计算样本容量的Bayes方法。

Experiment shows it is perfect to classify study sample itself by the kernel function in this thesis, and the generalization ability of it is more predominant than SVM of traditional one.

实验表明了本文的核函数对学习样本本身的分类良好，而且泛化能力优于传统的核函数的SVM。

The multi-index comprehensive evaluation model was established by artificial neural network BP algorithm. The evaluation index was described by adopting subordinative function of fuzzy mathematics. Sample-study pattern consists of the values of subordinative function on ends and on middle point.

利用人工神经网络BP算法建立了多指标综合评价模型，采用模糊数学的隶属函数对评价指标进行描述，由隶属函数的端点值和中间值组成学习样本模式，举例讨论了神经网络在多指标综合评价中的应用方法及应注意的一些问题。

In addition, The proposed approach is compared with the recognition approach based on he vector power spectrum and radial basis function network. The experiment result shows that the proposed approach is very effective, especially in the small samples.

同时，该方法还与基于矢功率谱的径向基函数网络识别结果进行了比较，实验结果表明，该方法是有效的，尤其在小样本情况下，SVM识别效果明显优于径向基函数网络。

A radial basis function neural network, as well as a back propagation neural network for comparison, is trained and tested using 23 series of centrifuge model test data, 2 fullscale test data, and prototype date of a practical project.

收集23组挡墙离心模型试验数据，2组足尺试验数据，1组实际工程的破坏数据，共26组样本作为训练及检验样本，建立了可用于加筋挡墙设计高度预测的径向基函数网络及误差反传网络模型。

Owing to the fact that uniform evaluation criterion of the neckline performance of woolen sweaters is not available presently,the performance of neckline s of woolen sweaters is classified objectively by comfortableness and durability through testing the stretchability of the neckline.

由于目前没有一个评价羊毛衫领口性能的统一标准，应用领口拉伸测试仪对领口性能从耐用性和舒适性两个方面进行客观的分类，构建了样本隶属函数，用迭代的方法得到最优模糊划分系数，以最大隶属度原则对样本进行分类，最后应用FE和最大类间模糊划分熵检验分类的合理性和聚类的有效性。

I can not make it blossom and suits me

我不能让树为我开花

When temperatures are above approximately 80 °C discolouration of the raceways or rolling elements is a frequent feature.

当温度高于 80 °C 左右时，滚道或滚动元件褪色是很常见的特征。