zhixian3

This thesis describes methods for solving certain optimization problems commonly arising in computer vision by PETTER STRANDMARK

HEED的分簇算法的matlab代码，注释详细，对初学WSN协议的同学很大帮助。(HEED clustering algorithm matlab code, detailed notes for the students of great help beginners WSN protocol)

说明：  多目标遗传算法是NSGA-II[1]（改进的非支配排序算法）,该遗传算法相比于其它的多目标遗传算法有如下优点：传统的非支配排序算法的复杂度为 ，而NSGA-II的复杂度为 ，其中M为目标函数的个数，N为种群中的个体数。引进精英策略，保证某些优良的种群个体在进化过程中不会被丢弃，从而提高了优化结果的精度。采用拥挤度和拥挤度比较算子，不但克服了NSGA中需要人为指定共享参数的缺陷，而且将其作为种群中个体间的比较标准，使得准Pareto域中的个体能均匀地扩展到整个Pareto域，保证了种群的多样性。（消除了共享参数）。(Multi-objective genetic algorithm is nsga-ii [1] (improved non-dominant sorting algorithm), which has the following advantages compared with other multi-objective genetic algorithms: the complexity of the traditional non-dominant sorting algorithm is, while the complexity of nsga-ii is, where M is the number of objective functions and N is the number of individuals in the population.The introduction of elite strategy to ensure that some good individuals in the evolutionary process will not be discarded, thus improving the accuracy of the optimization results.The comparison operator of crowding degree and crowding degree not only overcomes the defect that NSGA needs to specify the Shared parameter artificially, but also takes it as the comparison standard between individuals in the population, so that individuals in the quasi-pareto domain can uniformly expand to the whole Pareto domain, ensuring the diversity of the population.(eliminating Shared parameters).)

基于matlab/simulink的直流无刷电机的仿真。(Based on matlab/simulink simulation of DC brushless motors.)

说明：  小波变换在多尺度下检测分解重构图像，以及融合边缘算法。(Under the multi-scale wavelet decomposition of the reconstructed image detection, and edge fusion algorithm.)

K-Means Algorithm with x.mat to arrange items.

说明：  射线追踪Matlab演示程序，完美可运行(Ray tracing matlab demonstration program, perfect for operation)

用matlab实现的对一阶系统实现的预测函数控制，能有效的处理小扰动，效果非常理想。(Achieved with the matlab implementation of the first-order predictive functional control system can effectively deal with small perturbations, the effect was very good.)

简化的ANN程序，程序代码很少，但是预测效果相当(a simplified Ann algorithm with good performance)

用于一维信号的小波包去噪，选取特定的阈值，采用最优小波基(For one-dimensional signal denoising using wavelet packet , select a specific threshold, the optimal wavelet)