iriscode

Fs = 100000 t = 0:1/Fs:.00296 x = 1-cos(4*pi*t) cos(2*pi*t*200) h = spectrum.welch Instantiate a welch object. psd(h,x, Fs ,Fs) Plot the one-sided PSD

本文件包含一个word文档，详细讲解互信息的计算，以及一个txt文档，包含MI的matlab源代码。(This document contains a word document, explain in detail the calculation of mutual information, as well as a txt file, including MI, Matlab source code.)

说明：  用于单变量的偏最小二乘回归，直接给出回归系数。 X0是自变量矩阵，Y0是因变量向量，PRESS是去除其中某一个样本而回归出的方程对 缺失样本的误差估计，SS则是使用全部样本回归出的方程对同一个样本的误差估计。 在h个成分时，计算PRESS_h与SS_h-1，若1-PRESS/SS大于0.0975时，应增加成份。 [row,col]=size(pz) (For single-variable partial least squares regression, regression coefficients are given directly. X0 is the independent variable matrix, Y0 is the dependent variable vector, PRESS is to remove one of them out of the sample and the regression equation for missing samples error estimates, SS is the use of all of the sample regression equation out of a sample of the same error estimates. In h constituent, the calculation PRESS_h and SS_h-1, if the 1-PRESS/SS greater than 0.0975, to increase the ingredients. [Row, col] = size (pz) )

lingo入门教程，附有很多基础命令以及简单问题的分析，求解。例如病人吃饭，场地选址，渡河问题，人员相容问题，顺序安排工作问题，最短路线等等。(lingo Getting Started tutorial, with a lot of basic commands and a simple analysis of the problem, solution. For example, patients eat, site selection, cross the river issues, staff compatibility issues, the issue of work order of the shortest route and so on.)

一个左手介质的FDTD的分析，采用ADE方法离散(A left-handed medium, the analysis of the FDTD method discrete ADE )

非常好用的LDPC代码，利用了比特交织编码技术。(Articles and code is very nice, I diligently study was done.)

有循环检测，周期性检测，针对EMD方法的不足,光纤陀螺输出误差的allan方差分析。( There are cycle detection, periodic testing, For lack of EMD, allan FOG output error variance analysis.)

NLMS是LMS的一种改进算法。对该自适应滤波的朋友有一定启发(NLMS is an improved algorithm of LMS. The adaptive filtering friends have a certain inspiration)

去噪后的性能指标计算，其中包含信噪比、均方误差以及平滑度指标。(After denoising performance index calculation, including signal-to-noise ratio, the mean square error (mse) and smoothness index. )

压缩感知现在比较热门其恢复方法也很多这里只是其中一种(Compressed sensing is now more popular methods of its recovery here is only one of many)