1) non-orthogonal joint diagonalization
非正交联合对角化
1.
A novel cost function and a corresponding iterative algorithm for the non-orthogonal joint diagonalization of a set of eigen-matrices are proposed.
提出一种表征联合对角化近似程度的代价函数,给出优化该代价函数的非正交联合对角化算法。
2) orthogonal diagonalization
正交对角化
1.
A tensor matrix orthogonal diagonalization is utilized for image separation.
提出对照函数为二次特征函数的四阶导数,采用特征函数的高阶导数的矩阵张量方法,通过正交对角化实现图像的瞬时盲分离。
3) joint diagonalization
联合对角化
1.
Two efficient algorithms for joint diagonalization with exception of the singular solution
避免奇异解联合对角化的两种高效算法
2.
Improved joint diagonalization algorithm with low computational load
降低计算量的改进联合对角化算法
3.
A non-unitary joint diagonalization method was proposed to estimate the two-dimension(2D) direction of arrival(DOA) embedded in additive Gaussian noise.
针对高斯白噪声中的二维角度估计问题,提出一种非酉联合对角化方法。
4) orthogonal sub-diagonalization
正交次对角化
1.
The conditons and realization of sub-diagonalization and orthogonal sub-diagonalization of matrices;
矩阵的次对角化和正交次对角化的条件及实现
2.
The article gives a result of the orthogonal sub-diagonalization of skew-symmetric trabsformation,and proves this discussion.
我们将给出反对称变换都可以正交次对角化,并证明这一结论。
3.
We introduce a new kind of diagonalization for matrices-orthogonal sub-diagonalization, and find out a sufficient condition in which matrices can be orthogonally sub-diagonalized.
引进矩阵的一种新的“对角化”——正交次对角化的概念 ,并找出了矩阵可以正交次对角化的充分条件 。
5) joint block-diagonalization
联合块对角化
1.
The joint approximate diagonalization algorithm is generalized, making use of the non-stationarity and short-time stationarity of speech sources, and the joint difference correlation matrix and joint block-diagonalization cost function are defined.
首先对观测信号进行重新排列,将卷积混合盲分离问题转化为瞬时混合盲分离问题,然后对联合近似对角化算法进行了推广,利用语音的非平稳和短时平稳特征定义联合差分相关矩阵和联合块对角化代价函数,通过鲁棒的白化过程和求解最优化问题实现卷积语音的盲分离。
2.
A blind convolutive separation algorithm is proposed to sequently estimate the transform channels and separate the source signals based on joint block-diagonalization by virtue of the mutually independent property of the source signals.
针对卷积盲分离问题,利用源信号之间相互独立的性质,提出一种基于单分量提取的联合块对角化算法依次估计各源信号对应的传输信道,以实现源信号分离。
6) joint approximate diagonalization
联合近似对角化
1.
As a suitable solution,the joint approximate diagonalization algorithm of auto correlation matrices of the whitening signals is presented for separating each vibration signal from mixed signals.
该方法利用白化信号自相关矩阵的联合近似对角化算法,从观测信号中分离故障特征源信号,并根据分离信号的频谱成功地提取了混合故障的特征信息,有效地诊断出齿轮箱所处的故障状态。
补充资料：非应非化
【非应非化】
谓佛法、报二身，非属应、化，是名非应非化。
谓佛法、报二身，非属应、化，是名非应非化。
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