fuzzpid

本资料为数字信号处理的一个课程设计源代码，内容关于数字带通滤波器设计。(this source code is about digital ban pass filter designing.)

计算圆波导的TE/TM传播问题的matlab源程序(matlab code for the simulation of circul waveguide)

用matlabf编程求解通常的图着色问题,经常使用这个原理的.(Matlabf programming is usually used to solve the graph coloring problem, frequent use of this principle.)

智能控制，智能优化，刘金坤，很多的应用程序，机器人控制的好好学学。(intellgent control and design,liujinkun many demos,especially in robotic control)

这是一个简单的FFT为无电位1 +1 +1 Ð 薛定谔方程的光束传播方法。如果该软件灵活，允许引入的术语（如果是极少数需要包括色散效应高阶导数）。例如，如果一个人渴望解决的一个方程的形式： （四/ dz的+ Ð ^ 2/dx ^ 2 - 0.25 * Ð ^ 3/dx ^ 3）== 0 Ÿ 它可以解决使用以下代码： Ž = linspace（0,1,512） x = linspace（-5,5,1024） psi0 =进出口（- x的。^ 2） Ð = D_lateral1D（十，2）-0.25 * D_lateral1D（十，3） 字段= LinearBPM（psi0，有D，Z） 凡D_lateral1D是一个函数，提供“取代”的微分算子。 这个函数是在一个非线性的BPM，我曾对（分步，谱方法等），将提交给我，当我完成他们的文件和组织功能更复杂的设置非常初期阶段。 (This is a simple FFT based beam propagation method for potential-free 1+1+1D Schrodinger equation. The software if flexible and allows to introduce high-order derivatives in the term (very handful if is needed to include dispersion effects). For example, if one desires to solve an equation in the form: (d/dz+ d^2/dx^2- 0.25*d^3/dx^3)Y == 0 It can be solved using the following code: z=linspace(0,1,512) x=linspace(-5,5,1024) psi0=exp(-x.^2) D=D_lateral1D(x,2)-0.25*D_lateral1D(x,3) field=LinearBPM(psi0,D,z) Where D_lateral1D is a provided function that "replaces" the derivative operator. This function is a very early stage in a more complex set of non-linear BPM functions that I have made (split-step, spectral methods, etc.) and I will submit them when I finish their documentation and organization. Sorry for my English, I m eager for your comments. )

自己编制的倒立摆matlab7的程序，采用神经网络控制方法(Prepared their own inverted pendulum matlab7 procedures, the use of neural network control method)

ALGORITHME DE CLASSIFFICATION

This code realize the root_music algorithm

matlab 改进蚁群算法，应用简单广泛。(ant optimization)

In this paper, we show how support vector machine (SVM) can be employed as a powerful tool for $k$-nearest neighbor (kNN) classifier. A novel multi-class dimensionality reduction approach, Discriminant Analysis via Support Vectors (SVDA), is introduced by using the SVM. The kernel mapping idea is used to derive the non-linear version, Kernel Discriminant via Support Vectors (SVKD). In SVDA, only support vectors are involved to obtain the transformation matrix. Thus, the computational complexity can be greatly reduced for kernel based feature extraction. Experiments carried out on several standard databases show a clear improvement on LDA-based recognition