analyze

最小二乘ESPRIT (LS-ESPRIT)的Matlab实现与相关性能分析，直接由特征值确定DOA，大大减少了计算量；不需要精确知道阵列流型向量，对阵列校准要求不严格。(analysis and performance to LS-ESPRIT achieved by the Matlab, DOA value is determined directly by the characteristics, greatly reducing the amount of calculation do not need to know the exact array manifold vectors, not strictly on array calibration requirements.)

autocorrelation matlab file

Source separation problems in digital signal processing are those which are used to separate useful signal a mix of signals of interest, other signals and noise. The typical example of a source separation problem is the cocktail party problem, where many number of peoples are talking simultaneously in a room and a listener is trying to follow one of the discussions. The human brain can separate the voices of different people (source separation) using neurons in the auditory region. But source separation using digital signals is difficult task with the available techniques. Several approaches have been proposed for solving this issue but most of the techniques are still in development stages. Some of the successfully tested approaches are principal components analysis (PCA) and Independent components analysis (ICA). Both the approaches work well when there are no delays or echoes present

The optimization behavior of the self-adaptation (SA) evolution strategy (ES) with intermediate multirecombination (the (=I )-SA-ES) using isotropic mutations is investigated on the general elliptic objective function. An asymptotically exact quadratic progress rate formula is derived. This is used to model the dynamical ES system by a set of difference equations. The solutions of this system are used to analytically calculate the optimal learning parameter  . The theoretical results are compared and validated by comparison with real (=I )-SA-ES runs on typical elliptic test model cases. The theoretical results clearly indicate that using a model-independent learning parameter  leads to suboptimal performance of the (=I )-SA-ES on objective functions with changing local condition numbers as often encountered in practical problems with complex fitness landscapes.

这里面有5个程序，一是sarima预测的，2是HHT变换计算的主程序，3是计算平均周期的，4是人工神经网络的主程序，5是计算lyapunuv数字的主程序，计算域与eemd分解有关的股市预测方面的主程序(farcast mainprogram)

Digital signal processing is the important aspect of modern communication system. here is the matlab code given which helps for the beginers for understanding the basics of DSP.

研究用于自适应均衡器的LMS算法的性能，数据源产生有零平均和单位方差的由符号+1和-1组成的Bernoulli的序列{I(n)}.数据源之后的信道可以用升余弦脉冲响应来模拟。 (study for the adaptive equalizer LMS algorithm performance, Data Sources have zero mean and unit variance from the-1 and a symbol of the Bernoulli sequence (I ( n)). Data Source after the channel can be raised-cosine pulse response simulation.)

数字图像处理 同学做的，程序是文本，可在matlab运行(Students to do the digital image processing, the program text can run in matlab)

Matlab functions implementing non-parametric local linear smoothing (LLS) for one-dimensional curve fitting: yi = f(xi) + ei for i = 1, 2, ..., n. The toolbox contains: (i) the usual LLS estimator, see e.g. [1] (ii) a jump-preserving (two-sided) LLS estimator proposed in [2] (iii) a modified version of the two-sided LLS proposed in [3].(Matlab functions implementing non-parametric local linear smoothing (LLS) for one-dimensional curve fitting: yi = f(xi)+ ei for i = 1, 2, ..., n. The toolbox contains: (i) the usual LLS estimator, see e.g. [1] (ii) a jump-preserving (two-sided) LLS estimator proposed in [2] (iii) a modified version of the two-sided LLS proposed in [3].)

the basic space time block code techniqes