par_roll

wonderfull sourcne code for weka tools mential

2d Genetic Algorithm

FFTW 32位FFTW调用算法库,MATLAB可以调用(FFTW 32BIT LIBRARY)

matlab标准遗传算法 优化函数为f=-(x-1)^2+4，其中，0<=x<=3(matlab)

With PRP conjugate gradient method for solving unconstrained problem

说明：  使用FCM对数据进行分类，数据使用随机数据。(FCM was used to classify the data and random data was used.)

it is fcm kidney segmentation

经典的香农采样定理认为,为了不失真地恢复模拟信号,采样频率应该不小于奈奎斯特频率(即模拟信号 频谱中的最高频率)的两倍.但是其中除了利用到信号是有限带宽的假设外,没利用任何的其它先验信息.采集到 的数据存在很大程度的冗余.Donoho等人提出的压缩感知方法(Compressed Sensing或Compressive Sampling, CS)充分运用了大部分信号在预知的一组基上可以稀疏表示这一先验信息,利用随机投影实现了在远低于奈奎斯 特频率的采样频率下对压缩数据的直接采集.该方法不仅为降低采样频率提供了一种新思路,也为其它科学领域 的研究提供了新的契机.该文综述性地阐述了压缩感知方法的基本原理,给出了其中的一些约束问题和估计方法, 并介绍压缩感知理论的相关问题———矩阵填充,最后讨论了其未来可能的应用前景. (According to the conventional Shannon s sampling theorem,in order to represent the analog signal,the sampling rate should not be less than twice the Nyquist sampling rate.Howev- er,this theorem only makes use of the bandwidth information.As a result,the collected data contain many redundant information.The recently proposed sampling method,compressed sens- ing or compressive sampling(CS),can collect compressed data at the sampling rate much lower than that needed in Shannon s sampling theorem by exploring the compressibility of the signal. This paper presents a review on the basic theory of CS.Some of the restrictions and recovery methods in CS are also discussed.Finally,some potential applications based on CS are presented. )

光伏微网逆变器并网matlab/simulink仿真，仿真效果很好，mppt环节采用扰动跟踪法，锁相环部分使用s-function编译(Solar Micro Inverter Grid matlab/simulink simulation, the simulation results very well, mppt link tracking using perturbation method, phase lock loop section compiled using s-function)

深度学习中自动编码器，对象为手写体识别应用，希望可以一同研究学习(Deep Learning AutoEncoder)