44graph

Multi-shift CGLS solves the systems of linear equations (A *A+TAU(I)*EYE(N))*X(:,I)=A *B (I=1:L) for X with the multishift CGLS algorithm. The right hand side (column) vector B must have length M, where the coefficient matrix A is M-by-N. TAU is a vector of reals (the shifts) of length L. For a short demo run main.m

说明：  使用icosaedron细分方法建立球面三角模型。(Returns the triangulated model of a sphere using the icosaedron subdivision method. )

bartle自功率谱密度分析，对于直接法的功率谱估计，当数据长度N太大时，谱曲线起伏加剧，若N太小，谱的分辨率又不好，因此需要改进。(Bartle since the power spectral density analysis, for the direct method of power spectrum estimation, when the data length N is too large, the spectrum curve of the ups and downs, if N is too small, the resolution of the spectrum and is not good, so need to improve.)

说明：  EM 算法是Dempster，Laind，Rubin于1977年提出的求参数极大似然估计的一种方法，它可以从非完整数据集中对参数进行 MLE估计，是一种非常简单实用的学习算法。这种方法可以广泛地应用于处理缺损数据、截尾数据以及带有噪声等所谓的不完全数据，可以具体来说，我们可以利用EM算法来填充样本中的缺失数据、发现隐藏变量的值、估计HMM中的参数、估计有限混合分布中的参数以及可以进行无监督聚类等等。(EM algorithm is a method for maximum likelihood estimation of parameters proposed by Dempster, Laind and Rubin in 1977. It can estimate parameters from incomplete data sets by MLE. It is a very simple and practical learning algorithm. This method can be widely used in dealing with the so-called incomplete data such as defective data, censored data and noisy data. Specifically, we can use EM algorithm to fill missing data in samples, find hidden variable values, estimate parameters in HMM, estimate parameters in finite mixed distribution, and so on. Unsupervised clustering and so on.)

多输入多输出（MIMO）雷达 波束优化处理研究 (STUDY ON THE BEAMPATTERN OPTIMIZATION FOR MULTIPLE-INPUT MULTIPLE-OUTPUT RADAR )

模拟砂堆的元胞自动机源代码。对于认识和学习元胞自动机（CA）很有帮助(sand pile simulation of cellular automata source code. Learning to recognize and cellular automata (CA) helpful)

用ICA方法进行BSS分离的源程序，有Matlab运行结果和详细实验过程，非常实用(ICA method with source separation BSS, Matlab operating results and detailed experimental procedure, very practical)

进行逐步线性回归，采用的是脉冲对消法，使用起来非常方便，分析了该信号的时域、频域、倒谱，循环谱等,正确率可以达到98％，有小波分析的盲信号处理，包含特征值与特征向量的提取、训练样本以及最后的识别。( Stepwise linear regression, It uses a pulse of consumer law, Very convenient to use, Analysis of the signal time domain, frequency domain, cepstrum, cyclic spectrum, etc. Accuracy can reach 98 , There Wavelet Analysis Blind Signal Processing, Contains the eigenvalue and eigenvector extraction, the training sample, and the final recognition.)

This Program enables you to embed a visible watermark to any image

使用matlab来对图像进行边缘检测的方法之一，便于在此基础上进行其他的功能的实现(Using matlab to the image edge detection methods, to facilitate this function based on the realization of other)