| 1. | Asymptotic minimax efficiency ; interative logarithm law ; mean error
渐近minimax有效重对数律均方误差 |
| 2. | Exponential bounds of mean error for the kernel regreeion estimates with directional data
方向数据回归函数核估计平均偏差的指数界 |
| 3. | In the process of accuracy synthesis , monte carlo method is used for calculating the moving platform ' s mean error . the results show that this method is simply and easy to program
在精度综合工作中，本文提出一种基于蒙特卡洛方法的精度综合方法，利用该方法能较好地选择铰链的配合精度。 |
| 4. | Firstly the fringe is subdivided properly , then we get the estimated phase in subdivided regions based on the wavelet method and minimum mean errors estimates method
首先对干涉图象进行适当的分块，然后通过线性相位模型对每个子块的相位进行拟合；拟合系数通过干涉图象分块的小波变换与最小均方误差估计方法获得。 |
| 5. | By testing the corrected image map , the mean error of point position was 1 meter , the maximal error was 2 meters , length distortions on x and y axis orientation were not more than 1 % and angle distortion was almost not existing
经检验，单点定位平均偏差为1m左右，最大偏差为2m左右，在x 、 y方向上的长度变形均不大于1 ，基本没有角度变形。 |
| 6. | The mean error of ssp inversion by this algorithm is less than that by mfi when the sediment parameters is known a priori . the ssp inversion by this algorithm shows a better match to the measured ssp in the step layer
Mbi反演ssp对沉积层参数失配具有较高的稳定性，当根据先验信息确定沉积层参数后， mbi反演ssp均方根误差小于匹配场反演方法反演得到的结果，并且mbi反演ssp的温跃层部分更接近实际测量ssp 。 |
| 7. | At the same timejt is proposed that the mean error , maximum error and minimum error of the last 8 numbers between the measured results and predicting results are used as criteria in order that we can select the optimum model judge the accuracy and dispersion of measured results
在模型比选时，提出用实测值与预测值的后八项的平均误差，最大和最小误差来选择最优模型并判断其准确性以及实测数据选取的离散性。 |
| 8. | Abstract : starting from the definition of weight , the paper derives the relaton detween the change of the a priori unit weight weight mean error with the result of adjustment . lt is found that the change has influence only on the exploring effect of the posteriori unit weight mean error and gross error and the coordinated factor matrix , and no influence on all other adjustment results
文摘:该文从权的定义出发，导出了先验单位权中误差的变化与平差成果的关系，发现其变化仅对验后单位权中误差、粗差探测效果和协因数阵有影响，对其它平差成果均无影响。 |
| 9. | The calibration of flow model is acceptable with average rms of 0 . 7m , residual mean of - 0 . 045 m , average absolute mean error of 0 . 1 m and normalized rms value of 2 . 3 % . the contour map of the simulated heads , elaborated acceptable model calibration compared to observed heads map
模型结果中，均方差为0 . 7m ，平均误差为- 0 . 045m ，平均绝对误差为0 . 1m ，标准均方差为2 . 3 ，模拟地下水流场与实际观测地下水流场基本一致，说明所建立的数值模型符合该地区的实际水文地质条件。 |
| 10. | Considering the one - sidedness and inaccuracy of knowledge discovery only from single - color database , an approach is proposed to discover knowledge from 1331 groups of mix - color database with partial least - square regression , based on measuring and learning 400 groups of single - color database . by this method , the mean error decreases when converting from rgb to cmyk , the precision of color matching is improved , and the automatic and general problem in color matching is further solved
本文基于统计学习理论构造了一种快速自适应随机搜索算法,证明了算法的收敛性.给出了一种简易实用的宽带天线匹配设计新方法.应用该自适应算法进行天线匹配设计,不仅算法简单,易于编程实现;而且能够快速设计出具有较好性能的匹配网络,非常适用于各种短波、超短波天线的匹配设计问题 |
