random_process

matlab 关于股票单项指标滚动预测神经网络源代码。大家可以根据自己的回归预测问题，进行改写，。只用于研究ELMAN神经网络的一般使用，不适合用于投资分析，误差较大，切忌。切忌。(a code of Elman netural network about predicating the stocks price.. it is free and easy..)

用欧拉方法和龙格－库塔方法求微分方程数值解，画出解的图形，对结果进行比较分析。(using Euler method and RK method to solve the differential equations ,ploting the graph of the solution, compare and analyze the solutions)

经验模式分解，用于局域波分解，使用于多分量信号分析(empirical mode decomposition, for the local wave decomposition, in the use of multi-component signal analysis)

matlab实现的基于模糊逻辑的一个简单小例子，仿真已通过，可供初学者实践。(matlab fuzzy logic-based implementation of a simple small example, simulation has been adopted practice for beginners.)

自己做的： （一）用双线性变换法设计并用实验系统实现一个三阶的契比雪夫Ⅰ型低通数字滤波器，其采样频率Fs =8KHz，1DB通带边界频率为fp=2KHz。 （二）用双线性变换法设计并用实验系统实现一个三阶的契比雪夫Ⅱ型高通数字滤波器，其采样频率Fs =16KHz，阻带边界频率为fst =4KHz，As=20dB。 ((A) design using the bilinear transformation method and the experimental system of a third-order Chebyshev low-pass type Ⅰ digital filter, the sampling frequency Fs = 8KHz, 1DB passband boundary frequency is fp = 2KHz. (B) Bilinear transformation method used to design and use of the experimental system of a third-order Chebyshev type Ⅱ high-pass digital filter, the sampling frequency Fs = 16KHz, stopband boundary frequency fst = 4KHz, As = 20dB.)

机器人的psd路径规划策略，非常好的例子，是基于vc++平台的(robot psd )

粒子群算法以及优化后粒子群算法，可直接运行(Particle swarm optimization algorithm and particle swarm after, run)

粒子群算法，也称粒子群优化算法（Particle Swarm Optimization），缩写为 PSO， 是近年来发展起来的一种新的进化算法(Evolutionary Algorithm - EA)。PSO 算法属于进化算法的一种，和模拟退火算法相似，它也是从随机解出发，通过迭代寻找最优解，它也是通过适应度来评价解的品质，但它比遗传算法规则更为简单，它没有遗传算法的“交叉”(Crossover) 和“变异”(Mutation) 操作，它通过追随当前搜索到的最优值来寻找全局最优。这种算法以其实现容易、精度高、收敛快等优点引起了学术界的重视，并且在解决实际问题中展示了其优越性。粒子群算法是一种并行算法。(Particle swarm optimization, also known as particle swarm optimization (Particle Swarm Optimization), abbreviated as PSO, is a new evolutionary algorithm developed in recent years (Evolutionary Algorithm- EA). Kind, and simulated annealing algorithm PSO algorithm is similar evolutionary algorithms, it is also starting a random solution, through an iterative search for the optimal solution, which is also used to uate the quality through fitness solution, but it is simpler than genetic algorithm rules It has no genetic algorithm " crossover" (Crossover) and " variant" (Mutation) operation, which by following the current search to find the optimal value to the global optimum. This algorithm is its easy implementation, high accuracy, fast convergence, etc. attracted academic attention and show its superiority in solving practical problems. PSO algorithm is a parallel algorithm.)

遗传算法的matlab程序，可以解决函数的极值最小值问题。(GA can solve the unlinear problems.)

模型是结构体类型的线性投影Y = linproj(X, model) 其中W.model为线性投影矩阵， Y = model.W *X + model.b b为偏差值( Description: Y = linproj(X, model) linearly projects data in X such that Y = model.W *X+ model.b out_data = linproj(in_data, model) projects in_data.X out_data.X = model.W *in_data.X+ model.b out_data.y = in_data.y Input: model [struct] linear projection: .W [dim x ncomp] Projection matrix. .b [ncomp x 1] Bias.)