曲线回归

The ultrasonic-rebound curve can reduce the accidental error, and thus increase the precision of concrete strength measurements.

提出一种新的模糊回归数据融合方法的超声回弹测强曲线，此测强曲线可以减小偶然误差，提高检测的精度。

For fitting ROC curves and getting the area under the ROC curve, we applied the parametric methods of binormal models and ordinal regression models, the semiparametric method of Cox proportional hazards model, the nonparametric methods of Hanley, Delong.

本文采用双正态模型、有序回归模型等参数法，Cox比例风险模型半参数法，Hanley、Delong非参数法拟合了ROC曲线；文中也考虑了样本量的估计、协变量的混杂效应、再抽样技术计算ROC曲线下面积的标准误与可信区间等问题；并研究了SROC分析方法。

In view of this, a one dimension polar distance sequence is obtained first from the closed planar curve and then the auto regressive model of this sequence is used to extract feature vector.

从空间旋转不变的要求出发，首先从平面闭合曲线得到一维极径序列，进而采用该序列的自回归模型来完成特征提取并用于平面曲线的形状分类。

Logarithmic curve fitting method was used...

使用对数曲线拟合方法推导出该概率曲线的回归方程。

Occurrence records from 1864 locations and 34 environmental variables from Daymet datasets were gathered, four modeling methods including Logistic Regression, Classification and Regression Trees, Genetic Algorithm for Rule-Set Prediction and maximum entropy method were used to generate potential geographic distributions for Dreissena polymorpha in the continental USA. Then three statistical criteria including area under the Receiver Operating Characteristic curve, correlation and Kappa were calculated to evaluate the performance of the models, followed by analyses of major variable contributions.

论文以1864个美国外来入侵物种斑马纹贻贝定点发生数据和开放式基础地理信息数据库Daymet的34个环境变量为主要信息源，采用逻辑斯蒂回归、分类与回归树模型、基于规则的遗传算法、最大熵法4种途径，建立美国大陆部分潜在生境预测模型，从接受者运行特征曲线下面积、Pearson相关系数、Kappa值3个方面来检验模型预测精度，在此基础上分析斑马纹贻贝的空间分布规律及其环境影响因素。

Measuring the magnetic field intensity in different areas and current:(1) The two stirrers have different magnetic field direction;(2) The two stirrers have different way of combination. Obtain the regression equation by using Origin 7.0 software.

本研究采用2台相同规格的行波磁场搅拌器，研究过程中测定了不同电流强度下：(1) 2台搅拌器采用不同磁场方向时；(2) 2台搅拌器采用不同组合方式时，搅拌区域内的磁感应强度；用Origin 7.0软件对所测数据进行了曲线拟合及回归分析，并得到回归方程。

A series of spot welding technology and joint tensile-shear tests for uncoated low carbon, electroplated and two kinds of hot dipped zinc-coated steels were made to improve the quality of spot welding joint for zinc-coated steels. The test results were analyzed with computer regressive method. The effects of welding current or time on nugget diameter or joint tensile-shear strength and critical curves in splash generation for spot welding were obtained.

摘 要：为提高镀锌钢板点焊接头的质量，对普通冷轧钢板、电镀锌钢板和两种镀锌层厚度不同的热镀锌钢板进行了一组点焊工艺及接点强度试验，并对试验结果进行了计算机回归分析，分别得出了这几种材料在不同的焊接电流、焊接时间下的点焊熔核直径或接头拉剪强度变化曲线以及点焊飞溅临界曲线。

The author explicates some developing aspects in the field of IC industry as suggested areas of future work. The original points of this dissertation are as following: 1. In this dissertation, we got the quality learning curve of China's IC manufacturers by regression. On the base of questionnaire, we later explained the reason of the reverse S type quality learning curve and the tendency of change in quality learning curve. 2. The evolution of technical unit of China's IC industry is calculated in this dissertation. We also explained the reason of technical unit splitting in the way of economic and technology. 3. In this dissertation, we described the environment difference in capital, technology transfer, human resource and market in USA, Japan, Korea, Taiwan and China, and gave some suggestions on the government's role in the development of China's IC industry.. 4. In this dissertation, we established an SD model of China's IC industry, and by using this model, we got some suggestions for future development in China's IC industry.

本文的主要创新之处在于：（1）用回归分析方法实证研究了我国集成电路企业的质量学习曲线，并在调查分析的基础上，对反S型质量学习曲线的历史成因和未来走势进行了研究；（2）对世界及我国集成电路产业技术单元的变化趋势进行了定量研究，从经济和技术角度解释了当前集成电路产业技术单元细化的原因；（3）从资金、技术、人才、市场角度系统总结研究了发达国家在集成电路产业发展环境建设中的成功经验，并结合我国集成电路产业发展的实际情况，对我国集成电路产业发展的政府行为提出了一些建议；（4）建立了狭义集成电路产业、材料业、设备业发展的系统动态模型，并利用该模型对不同投资结构下我国集成电路产业系统未来的演变进行了模拟研究，这一研究结果可以为我国集成电路产业今后发展提供一定的决策依据。

The author used to solve the linear matrix method to simulate the equations of quadratic regression equation work curve with only a few simple mathematical expressions for the second straight three coefficient regression equations, received the good effect.

作者用矩阵法求解线性方程组的方法来模拟工作曲线的二次回归方程，仅用几个简单的数学表达式就直接求得了二次回归方程的三系数，收到了很好的效果。

Based on the tomato and eggplant supply data of Shanghai in sequence of year, using meteorological data in SAMR(The data management system of Shanghai Agricultural Meteorology Report) and screening the meteorological factors related to the vagetable output, the authors carried out curve fitting and estimation of related parameters of distribution function.

Gompertz曲线和对数正态分布函数(Logarithmic normal distribution function)作为这二种蔬菜上市趋势的数学模型，进行曲线拟合，先调用上海市农业科学院测试中心的SAMR农业气象资料数据库所存贮的气象数据，筛选与该蔬菜产量有密切相关的气象因子，再用多元回归方法对初选因子作进一步的筛选，从而估计出分布函数的有关参数。

I will endeavour to find you some assistance.

我尽力帮你找人帮忙。

At first I only know bruck is the idol of American younglings, afterwards I returned back to Taiwan ,even in Beijing last year ,I saw her poster everywhere, I was so surprised at her charm.

起初我只晓得布鲁克雷德丝是美国少男少女崇拜的偶像，后来回台湾，甚至去年在北京，居然也四处看见她的海报，才惊讶她的魅力之大。