svm

包括图像分析的四部分代码：matlab扩散和高斯函数，线性扩散，线性复扩散，非线性扩散。(It contains four parts： [1]MATLAB function:diffusion.m gauss.m [2]Linear diffusion Applying linear diffusion to images creating linear scale-space. MATLAB code: demo_lin.m Image: haifa1.bmp [3]Linear complex diffusion Applying linear complex diffusion creating Gaussian and Laplacian scale-spaces. MATLAB code: demo_cmplin.m [4]Nonlinear diffusions: Perona-Malik ["Anisotropic diffusion"] Catte et al. regularization of P-M Complex ramp-preserving diffusion Nonlinear edge preserving diffusions.The classical Perona-Malik process: the value of the diffusion coefficient is reduced near edges estimated by the first derivative. Best applied to step edges. A regularized version by Catte et al- the gradient estimation for controlling the process is smoothed by a Gaussian. Proved to be mathematically well-posed. Ramp preserving complex diffusion- best for ramp-type edges. Results are smoother with almost no staircasing effects. MATLAB code: demo_nldif.m Image: ct_scan.bmp)

这是大名鼎鼎的薛定宇的《控制系统计算机辅助设计》（第一版）的代码。第一版与第二版区别还是挺大的。(It is famous on Compensation for " Computer Aided Control System Design" (first edition) code. First edition and second edition of the difference is big.)

灰色模型在城市中长期用水量预测中的应用，近年来, 随着我国经济的飞速发展, 城市规模 不断扩张, 现有供水系统已经不能满足未来几年 的供水需求, 必须依照未来城市发展与城市布局 进行科学合理的供水系统规划. 在(Gray model in the application of long-term water demand in recent years, as China' s rapid economic development, urban-scale expansion, the existing water supply system can not meet the water needs of the next few years must be in accordance with future urban development and urban scientific and rational layout of the water supply system planning. In)

controller with disrejection plus kalman(controller with disrejection plus Tracking)

判断一组数据服从何种分布：正态分布判，断泊松分布判断，γ分布判断，指数分布判断，rayleigh分布判断(Determine a set of data obey what distribution )

完整的遗传算法函数，这是它的matlab源程序(Integrity of the genetic algorithm function, that is its source code matlab)

Image Segmentation & Extraction

This folder contains several codes for energy detection and match filter.

说明：  （蒙特卡洛方法） 求出四分之一圆占正方形的比例。随机投点P(x,y)于正方形，π/4的近似值为落在四分之一圆内的点数与总投点数的比值。随机投点次数分别为10000次和50000次，计算π的近似值。 ((Monte Carlo method) are obtained accounting for a quarter of a round square ratio. Voted random point P (x, y) in the square, π/4 for the fall quarter of the approximation of the points won and the ratio of the total vote points. The number of random points, respectively, voted for the 10000 and 50000 times, the calculation of the approximation of π.)

说明：  VQ声纹识别算法和实验. 摘要：采用线性预测倒谱系数(1inear prediction cepstrum coefficient，LPCC)作为语音的特征参数，矢量量化(vector quantity，VQ)方法进行模式匹配，探讨声纹识别以实现身份认证，并对此识别方法进行了相关的实验．通过验证，这种方法可以区分不同的说话人，并且在做说话人辨认实验时可达到较高的识别率．(VQ pattern recognition algorithms and experimental sound. Abstract: The linear prediction cepstral coefficients (1inear prediction cepstrum coefficient, LPCC) as the voice of the characteristic parameters, vector quantization (vector quantity, VQ) method of pattern matching, pattern recognition of sound in order to achieve authentication and identification methods relevant to this experiment. Validated, this method can distinguish between different speaker, and speaker identification experiments to do to reach a higher recognition rate.)