YUAN

Matlab 工具箱，基于正则期望最大化方法(Regularied Expectation Maximization)的数据填充。(A Matlab toolbox based on the regularied expectation maximization (RegEM) based data imputation.)

光纤端面的辐射场,光纤与光纤的连接及其光功率损耗(Fiber end face of the radiation field, optical fiber and optical fiber connections and their optical power loss)

用matlab编写的模数转换和数模转换的仿真程序，写的比较浅显，可以辅助看一看。(Modulus using matlab convert digital to analog conversion of the simulation program, written in relatively plain, can assist a look.)

HERE IS A GOOD PSO TOOL BOX (HERE IS A GOOD PSO TOOL BOX)

speckle noise in image processing

特别好的matlab学习资料，适合初学者阅读学习，特别清晰(Particularly good matlab learning materials, suitable for beginners learning to read, particularly clear)

3dSIFT特征提取源码，有使用说明，主程序，非常容易使用(3dSIFT feature extraction source, with instructions, the main program, very easy to use)

说明：  processing and database for sar images

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.)

说明：  用牛顿下山法求解方程：下山因子在计算过程中可以变动，一般选择下山因子时从1开始，逐次将减半进行试算，直到能使下降条件成立为止。若当计算到某步时取不到满足要求的值（或值小到无法容忍），这时称“下山失败”，需要另取初值重新算起。(Descent method with Newton' s equation: down factor in the calculation process can change, usually selected from the 1 start down factor, will be halved for successive spreadsheet until the can down the conditions established. If when calculating the time to take a step not meet the requirements of the value (or values ??too small to tolerate), then the &quot down failed&quot , you need an alternative initial re-counting.)