Machine-learning

Communication walsh code generator for modeling.

说明：  在MATLAB环境下设计的计算卷积的软件平台(Design in the MATLAB computing environment software platform convolution)

实现BP神经网络的matlab运算，运算效率高，方便，快捷(BP neural network matlab realize operation, high operational efficiency, convenient and fast)

基于平行等距均匀线阵的信号频率，方位角，俯仰角联合估计，采用MUSIC算法 (Based on uniform linear array of parallel equidistant signal frequency, azimuth, pitch angle joint estimation using MUSIC algorithm)

matlab实现的小球运动的源程序，不错的matlab GUI 例程(Matlab achieve a small ball of the source, a good GUI Matlab routines)

基于小波变换和OMP算法的稀疏表示,不仅包括适用于黑白图片的程序，也包括适用于彩色图片的程序。(the sparse representation basing on wavelet and omp,not only for the gray image,but also color image )

3GPP演进协议LTE 实现检测CLSM OLSM SISO SIxO(The 3GPP Evolution agreement LTE detection CLSM OLSM SISO SIxO)

马氏距离是一种有效地计算两个样本集之间相似度的算法（数据之间协方差距离），与欧式距离相比，它考虑了各种特征之间的联系。本实验旨在通过给出的样本数据，设计一个最小马氏距离分类器并对测试点进行分类，然后将其与最小欧式距离分类器进行比较，实验得出当协方差矩阵为单位阵时，最小马氏距离分类器将与最小欧式距离分类器等价。本实验还根据实验样本设计贝叶斯分类器进行分类，并与最小马氏距离分类器进行比较，比较两种分类器的分类效果。(Markov distance is an effective method to compute the similarity between the two samples (data covariance distance), compared with the Euclidean distance, which takes into account the link between different characteristics. This experiment aimed at through the given sample data, design a minimum Mahalanobis distance classifier and classify the test points, and then compare it with the minimum Euclidean distance classifier. Experimental results showed that when the covariance matrix is a unit matrix, minimum Mahalanobis distance classifier with the minimum Euclidean distance classifier equivalent.In this experiment, according to the experimental design of the Bias classifier, and compared with the minimum distance classifier, the classification results of the two classifiers are compared.)

说明：  基于MP的信号稀疏分解参考程序的matlab仿真代码(Matlab simulation code of the reference procedure based on the MP signal sparse decomposition)

仿真实现了MUSIC、Beamformer、Capon功率谱，并未实现线性预测功率谱估计（未找到方法）。由实验结果我们可以得出结论MUSIC的估计效果最好，它可以区分800、850处来波，其他角度也可区分。(Simulation of MUSIC, Beamformer, Capon power spectrum, did not realize the power spectrum estimation linear prediction (not way to find). From the experimental results, we can draw the conclusion MUSIC best estimate of the effect, it can be distinguished to wave at 800, 850, other angles can also be distinguished.)