gold_spread

A source for TDOA for position location

用matlab编写的径向基函数神经网络程序，有需要的就下载吧，(Prepared using matlab radial basis function neural network program, there is need to download it,)

Rosenbrock函数优化属于无约束函数优化问题，其全局极小值位于一条平滑而狭长的抛物线形状的山谷底部，且为优化算法提供的信息很少，因此找到其全局极小值就显得很困难。根据Rosenbrock函数的这种特性，专门提出了一种改进的PSO算法，该算法引入三角函数因子，利用三角函数具有的周期振荡性，使每个粒子获得较强的振荡性，扩大每个粒子的搜索空间，引导粒子向全局极小值附近靠近，避免算法过早地收敛，陷入局部最优，从而找到Rosenbrock函数的全局极小值。大量实验结果表明，该算法具有很好的优化性能，为某些领域某些特定的类似于Rosenbrock函数的优化问题提供了一种新的思路。(Rosenbrock function optimization functions are unconstrained optimization problems, its global minimum value at a smooth parabolic shape and narrow mountain valley Department, and for the optimization algorithm provides little information, and therefore find its global minimum value becomes very difficult. According to this feature Rosenbrock function, specifically mentioning Out an improved PSO algorithm (PSO-R), the algorithm introduced trigonometric factor, using trigonometric has periodic oscillations, so that each particle to obtain more Strong oscillations of expanding the search space of each particle, the particle is close to nearby guide global minimum, avoiding premature convergence algorithm, into a local optimum, thus Finding the global minimum Rosenbrock function. Experimental results show that the algorithm has a good optimizing performance, similar to some certain areas Rosenbrock function in the optimization problem provides a new way of thinking.)

自己在硕士期间用到的各种模式识别，机器学习，数据挖掘算法的matlab程序。C4_5,NN，SVM，adaboost,KNN等(During their Master used a variety of pattern recognition, machine learning, data mining algorithm matlab program. C4_5, NN, SVM, adaboost, KNN, etc.)

％ PURPOSE : Demonstrate the differences between the following ％ filters on a simple DBN. ％ ％ 3) Particle Filter (PF) ％ 4) PF with Rao Blackwellisation (RBPF)( PURPOSE: Demonstrate the differences between the following filters on a simple DBN. 3) Particle Filter (PF) 4) PF with Rao Blackwellisation (RBPF))

说明：  主成分分析法主要算法程序, 里面有详细解释.(Principal component analysis procedure main algorithm, which has a detailed explanation.)

用于人脸识别的LDA和PCA特征提取方法的Matlab代码，结合两个程序可以实现PCA+LDA特征提取方法。(LDA and PCA is a common methods of feature selection,These are their source code using matlab. )

说明：  αβγ滤波器，αβ滤波器，卡尔曼滤波器仿真实例。(Simulation examples of alpha beta gamma filter, alpha beta filter and Kalman filter.)

the matlab code for block truncation code

EM 算法是求参数极大似然估计的一种方法，它可以从非完整数据集中对参数进行估计，是一种非常简单实用的学习算法。这种方法可以广泛地应用于处理缺损数据、截尾数据以及带有噪声等所谓的不完全数据，可以具体来说，我们可以利用EM算法来填充样本中的缺失数据、发现隐藏变量的值、估计HMM中的参数、估计有限混合分布中的参数以及可以进行无监督聚类等等。(Expectation Maximization image segmentation Input: ima: grey color image k: Number of classes Output: mask: clasification image mask mu: vector of class means v: vector of class variances p: vector of class proportions )