CODEProgram23_FDTD_2D_FreeBoundary_Unitless_Matri

功率谱估计的应用范围很广，在各学科和应用领域中受到了极大的重视。在《现代信号处理》课程中讲述了经典谱估计和现代谱估计这两大类谱估计方法；经典谱估计是基于傅立叶变换的，虽然具有运算效率高的优点，但是频谱分辨率低同时旁瓣泄漏严重，对长序列有着良好的估计。为了克服经典谱估计的缺点，人们开展了对现代谱估计方法的研究。现代谱估计是以随机过程的参数模型为基础的，有最大似然估计法、最大熵法、AR模型法、预测滤波器法。现代谱估计对短序列的估计精度高，同经典谱估计互为补充。在认真学习了现 代谱估计方法后，我选择了现代谱估计中的AR模型法的仿真作为题目。下面给出AR模型的相关理论和仿真实现。(Power Spectral Estimation of very extensive, in all disciplines and fields of application of a great deal of attention. The "modern signal processing" on the curriculum of classical and modern spectral estimation spectrum is estimated that the two types of spectrum estimation method; Classical spectrum estimation is based on Fourier transform, although high computing efficiency advantages, but also low-resolution spectrum Sidelobe serious leakage of long sequences have good estimates. In order to overcome the classic shortcomings of the spectrum estimation, there have been a pair of modern spectral estimation methods. Modern spectral estimation is the random process model parameters based on the maximum likelihood estimation, maximum entropy method, AR model, forecast filter. Spe)

生成shepp-logan 三维头模型，从官网下载(Generate Shepp-Logan 3D head model, download the official website )

说明：  高等土力学剑桥模型示例文件，土的本构模型(Cambridge model of advanced soil mechanics, constitutive model of soil)

状态脉冲分岔图程序State pulse bifurcation diagram program(State pulse bifurcation diagram program)

这是matlab中实现PID经典控制算法程序(This is the classic PID control algorithm program in matlab)

LT码的matlab代码,程序运行时最好预先预测长度开辟空间(LT code)

这是一个用MATLAB编写的接联惯性导航系统精对准阶段KALMAN滤波仿真程序的修正程序。解决了因系数矩阵条件数过大造成的滤波发散问题。(using MATLAB access Inertial Navigation System precision alignment stage Kalman filtering imitation really procedures amendment procedure. Solutions for the coefficient matrix several conditions caused by the excessive filtering divergence.)

薛定宇《高等应用数学问题MATLAB 求解》习题参考解答,一本学习matlab不错的书(Xue Dingyu " higher MATLAB to solve mathematical problems" exercises reference answers, a good book to learn matlab)

matlab source code for Multi-layer Perceptron

Finger print Wit Neural Network