1) scatter estimator
散布阵估计
2) scatter matrix
散布矩阵
1.
Firstly, all the samples are projected to the nonzero space of the total scatter matrix.
首先将样本投影到总体散布矩阵的非零空间中进行分析;进而将类内散布矩阵分成零空间和非零空间进行鉴别向量确定和鉴别特征提取,最后将得到的两种鉴别特征融合,从而使用最近邻法进行分类。
2.
Then,an image scatter matrix is constructed using the reshaped image matrixes and its eigenvectors are derived for image feature extraction.
该方法先将图像矩阵进行重组,根据重组的图像矩阵构造出总体散布矩阵,然后求出最佳投影向量进行特征提取。
3.
The generation matrix of the GPCA is analyzed, and the between-class scatter matrix is redefined by introducing a radical basis function, so classification features are obtained by adjusting the coefficient of the function.
通过对广义主分量分析中的产生矩阵进行分析,并重新定义,在类间散布矩阵定义的基础上引入了径向基函数,通过调整径向基函数的系数得到更有利于分类的特征信息,获得较高的识别率。
3) Array shape estimation
阵形估计
1.
Towed array shape estimation using adaptive Kalman filters;
拖曳阵阵形估计的自适应Kalman滤波算法
2.
The principle of array shape estimation based on time delay estimation is analyzed, which is a robust method of high precision, compared to direct measurement based on sensors and match-field inversion approaches.
阵形估计是水听器阵列应用中的关键问题,基于时延估计的阵形估计方法比基于传感器测量和基于匹配场处理的方法具有更强的适应性和更高的精度。
4) matrix estimation
矩阵估计
1.
Based on generalized least square (GLS) model, a dynamic origindestination (OD) matrix estimation algorithm with sliding window is established.
基于广义最小二乘模型建立了一种带滑动窗的动态起点 迄点(OD)矩阵估计算法,可通过对路段交通量和行程时间的检测来估计时变的OD数据。
5) Matrix of estimator
估计矩阵
6) Decentralized estimation
分散估计
补充资料：布阵
1.布列阵势。
说明：补充资料仅用于学习参考，请勿用于其它任何用途。
参考词条