duojing

贝叶斯分类器，首先生成3000个高斯分布的点，1000个点做训练集，2000个点做测试集。先运行data_generator.m自动生成两个集盒，再运行bayes_classifier.m进行分类(Bayesian classifier, the first generation 3000 Gaussian distribution of points, 1000 points to do the training set, 2000 points to do the test set. Automatically generated the first two sets running data_generator.m box, and then run bayes_classifier.m classification)

用于解反问题的代数重建法，对于Ax=b，输入矩阵A，列向量b，以及迭代步数k，可求的列向量x(Algebraic solution of the inverse problem for the reconstruction of France, for Ax = b, the input matrix A, the column vector b, as well as the number of iterations k, rectifiable column vector x)

Senoidal,Square and sawtooth functions with amplitud, time and frecuencia variables

一种新的快速esprit_DOA算法估计来波方向(a new fast algorithm esprit_DOA estimated to wave direction)

可以实现车牌定位 分割 识别 效果很好 通过验证 放心使用(Segmentation can identify the license plate location works well validated ease of use)

说明：  以直驱式永磁同步风力发电机为研究对象，在Matlab/simulink平台建立了风力机模型、传动系统模型，采用变桨距控制。(Taking the direct drive permanent magnet synchronous wind turbine as the research object, the wind turbine model and the transmission system model are established on the MATLAB / Simulink platform, and the variable pitch control is adopted.)

详细的介绍了matlab/simulink的实现方法，对从事该工作的同志们有很大帮助(Detailed description of the matlab/simulink implementation method of comrades engaged in the work of great help)

develop controler for wind turbine

对信号进行Wigner-Ville分布分析的matlab函数(The matlab function of Wigner-Ville distribution analysis.)

不错的GM_EM代码。用于聚类分析等方面。( GM_EM- fit a Gaussian mixture model to N points located in n-dimensional space. Note: This function requires the Statistical Toolbox and, if you wish to plot (for k = 2), the function error_ellipse Elementary usage: GM_EM(X,k)- fit a GMM to X, where X is N x n and k is the number of clusters. Algorithm follows steps outlined in Bishop (2009) Pattern Recognition and Machine Learning , Chapter 9. Additional inputs: bn_noise- allow for uniform background noise term ( T or F , default T ). If T , relevant classification uses the (k+1)th cluster reps- number of repetitions with different initial conditions (default = 10). Note: only the best fit (in a likelihood sense) is returned. max_iters- maximum iteration number for EM algorithm (default = 100) tol- tolerance value (default = 0.01) Outputs idx- classification/labelling of data in X mu- GM centres)