dsp

说明：  该程序主要也是针对滤波器设计的，实现了对一个语音信号的滤波处理(The program is largely designed for the filter, the realization of a voice signal filtering)

MATLAB图像标记，可以对图像中的你感兴趣的区域进行提取和标记，为后续分析提供帮助，程序可运行(MATLAB image tag, the image of the region of interest you can be extracted and tag, provide help for subsequent analysis, program can be run)

出一种实现不同维间估计结果自动配对的二维频率估计算法。首先把二维频率估计问题转化成两个矩阵束的特征值问题。根据矩阵束的特征求出两个矩阵束的公共特征向量，并以此为基础同时求出两个矩阵束的特征值。算法估计误差与现有算法相近，但解决了现有算法普遍存在的配对难题。 (Matrix pencils play an important role in numerical linear algebra. The problem of finding the eigenvalues of a pencil is called the generalized eigenvalue problem. The most popular algorithm for this task is the QZ algorithm, which is an implicit version of the QR algorithm to solve the associated eigenvalue problem B − 1Ax = λx without forming explicitly the matrix B − 1A (which could be impossible or ill-conditioned if B is singular or near-singular) )

说明：  //1、动态改变学习速率 //2、加入动量项 //3、运用了Matcom4.5的矩阵运算库（可免费下载,头文件matlib.h)， // 方便矩阵运算,当然，也可自己写矩阵类 //4、可暂停运算 //5、可将网络以文件的形式保存、恢复(//1, dynamically changing learning rate// 2, adding momentum item// 3, the use of matrix operations Matcom4.5 library (available for free download, headers matlib.h),// ​ ​ to facilitate matrix operations, but may also write your own matrix class// 4, may suspend the operation// 5, the network can be saved as a file and restore)

设计一个可以输入若干评委分数的表单，可以通过两个for循环分别找出分数的最大值和最小值，存入到两个变量，把评委的分数存入到一个数组中，计算时去掉找出的最大值和最小值即可得出最后得分。 (You can enter a number of judges to design a fractional form, you can find the maximum and minimum scores for each through two loops, credited to two variables, the judges scores deposited into an array, remove the calculation to find out the maximum and minimum values ​ ​ to arrive at a final score.)

基于rssi的室内定位算法，NN,KNN,WKNN及贝叶斯算法的对比。(The indoor location algorithm based on RSSI is compared with NN, KNN, WKNN and Bayes algorithm.)

说明：  利用龙格库塔法解布洛赫方程 有较为详细的注释 简单易懂(Solving Bloch Equation by Runge-Kutta Method)

compressive sensing theory

在matlab平台上实现了迭代最近点算法（ICP），功能齐全(a full-featured iterative closest point algorithm (ICP) achieved On matlab platform successfully)

径向基神经网络,使用的算法梯度下降法,比较清晰,适合于初学神经网络的用户(RBF neural network, using gradient descent algorithm, more clarity, suitable for novice users of neural network)