PCM_model_OK

matlab code for adaptive equalizer..

说明：  ① 样本数据从MATLAB命令窗口或新建一M文件作为数据输入文件，样本输入变量名为samin,样本输出变量名samout 样本个数和每个样本的维数可任意，样本输出的个数与样本个数应一致，即保证每个样本都对应一个期望输出，但每个输出的维数不要求与输入的维数相同，可任意； ② 聚类中心的个数（即基函数的个数）可根据实际情况调整；同样可调整参数的还有重叠系数、聚类中心最大更新次数、聚类中心更新终止误差； ③ 训练结束后进行测试时，要求输入的测试数据与样本具有相同的维数，测试数据的个数可任意； ④ 如果训练样本是二维的，则数据中心聚类的结果可用一平面图显示出来；同样测试数据的输出是一维的话也可显示出来； (RBF artifical neual networks)

matlab实现样条插值法，方便快捷实现各种拟合(matlab implementation spline interpolation method, to achieve a variety of quick and easy fitting)

alpha稳定分布的函数。该分布是一种连续概率分布，其概率密度比高斯分布概率密度有更厚的拖尾，是一类适用范围很宽的随机信号模型，比高斯分布有更广泛的适用性。(Alpha stable distribution function. This distribution is a continuous probability distribution, the probability density are thicker than gaussian probability density trailing, random signal model is a kind of very wide application scope, has wider applicability than gaussian distribution. )

给定观测序列 O=O1O2O3…Ot和模型参数λ=(A,B,π)，怎样有效计算某一观测序列的概率，进而可对该HMM做出相关评估。例如，已有一些模型参数各异的HMM，给定观测序列O=O1O2O3…Ot，我们想知道哪个HMM模型最可能生成该观测序列。通常我们利用forward算法分别计算每个HMM产生给定观测序列O的概率，然后从中选出最优的HMM模型。(Given the observation sequence O = O1O2O3 ... Ot and model parameters λ = (A, B, π), how to effectively calculate the probability that a single observation sequence, and thus can make the relevant assessment of the HMM. For example, there are a number of different model parameters HMM, given the observation sequence O = O1O2O3 ... Ot, we want to know which model is most likely to generate the HMM observation sequence. Usually we use forward algorithm calculates the probability of a given observation sequence O generated for each HMM, HMM and then to choose the best model.)

basic implementation of graphs in matlab

说明：  计算电动汽车充电功率和符合预测，分时段计算，精度高(Calculation of electric vehicle charging power and coincidence prediction, time-sharing calculation, high precision)

说明：  this module gives a basic image compression example

SVM EEG signal classification

In a multiple transmit antenna, single antenna per receiver downlink channel with limited channel state feedback, we consider the following question: given a constraint on the total system-wide feedback load, is it referable to get low-rate/coarse channel feedback from a large number of receivers or high-rate/high-quality feedback from a smaller number of receivers? Acquiring feedback from many receivers allows multi-user diversity to be exploited, while high-rate feedback allows for very precise selection of beamforming directions. We show that there is a strong preference for obtaining high-quality feedback, and that obtaining near-perfect channel information from as many receivers as possible provides a significantly larger sum rate than collecting a few feedback bits from a large number of users.