Python数据分析

illustrates the improvement in BER performance when using log-likelihood instead of hard decision demodulation in a convolutionally coded communication link

说明：  用matlab实现的K2算法，需要用到贝叶斯网络工具箱(K2 algorithm implemented with matlab)

旅行商问题（Travelling Salesman Problem, 简记TSP):假设有一个旅行商人要拜访n个城市，他必须选择所要走的路径，路经的限制是每个城市只能拜访一次，而且最后要回到原来出发的城市。路径的选择目标是要求得的路径路程为所有路径之中的最小值。 此处使用蚁群算法求解TSP问题(Suppose a business trip to visit n cities, he must choose the path to go, pass through the restriction is to visit each city only once, and finally go back to the original departure city. Path selection objective is to get the path distance to the minimum value among all paths.Here,we use the procedure of ant colony algorithm to work out the TSP.)

基于cpso文章，给出的一个matlab代码，添加测试函数即可运行。(Based on cpso, given a matlab code, add test function can be run.)

数据输入形成节点导纳矩阵并用牛拉法解潮流计算(Solution of Power Flow by Niu-La Method)

用三种不同的Runge-kutta方法计算常微分方程(Runge-kutta for ODE)

拟合zernike多项式,这里给出了前35项的泽尼克像差。有需要的话可以继续添加像差。(Fitting zernike polynomial.The zernike aberrations of the first 35 terms are given here. Continue to add aberrations if necessary)

目标轮廓的椭圆拟合，matlab编写，精度很高，(Target contour ellipse fitting, matlab prepared, high precision,)

For training two-layer perceptrons using steepest descent.

说明：  一个ga的matlab源程序，读懂它可以方便地处理问题。(ga matlab procedure，read it you can deal with your problem easily)