MPC_bookMaciejowski

基于EM算法的图像融合算法，对图像不用进行多尺度分解。(EM algorithm based on image fusion algorithm for multi-scale image without decomposing.)

说明：  利用FFT快速算法来实现二维图像基于匹配追踪算法的稀疏分解。(Fast Algorithm for the use of FFT to achieve two-dimensional image matching tracking algorithm based on sparse decomposition.)

说明：  经典的有限元入门程序之beam，希望对你有用。(Introduction to classical finite element procedures beam, hope useful for you.)

用matlab做的多元线形回归预测的小程序，抱愧数据，可以运行。(using Matlab do multiple linear regression forecast a small procedure, feel ashamed of data, can run.)

说明：  在MATLAB中编写实现图像的不同级别小波分解算法；2选择合适的小波基；3对经典的几幅黑白和彩色图像进行DWT变换；4实现零树、基于塔式网格矢量量化、基于LBG算法、基于标量量化等小波变换编码；5得到分析比较结果。达到的目的：1综合训练学生编程的能力；2对高数、计算方法、程序设计、数据结构、算法、数字图像处理等课程的复习和运用；3可培养学生的算法设计和分析能力。(in MATLAB prepared to achieve different levels of image wavelet decomposition algorithm; Choice of two small Porgy; Three pairs of classic pieces of black-and-white and color images DWT; Four zero tree, grid-based Tower vector quantization, LBG-based algorithm, based on the scalar quantization Wavelet Transform Coding ; 5 analyzed the results of the comparison. The purpose : a comprehensive training program students; Two pairs of the high number and the method of computation, programming, data structures, algorithms, digital image processing and review of the curriculum used; Three students can develop the algorithm design and analysis.)

详细介绍了3G网络的发展前景和应用程度，是一本很全的知识宝典，(Details of the 3G network development prospects and application level, is a very wide knowledge of canon,)

matlab simulink仿真实例分析（源代码模型)(matlab simulink simulation analysis (source model))

用于已知栅格环境下机器人路径规划的Astar算法源码，像知道的可以来看看一看 ，对于像用matlab来仿真算法的有所帮助(Known for grid environment of the path planning algorithm Astar source, like know can come to see a see, for as by matlab simulation algorithm to the help)

This InstructionVisitor executes the instructions that it visits on a given local variable frame and stack.

k means techniques de classification non supervisée (clustering) les plus utilisées. Etant donné un entier K, K-means partitionne les données en K groupes, ou "clusters", ou "classes" ne se chevauchant pas. Ce résultat est obtenu en positionnant K "prototypes", ou "centroï des" dans les régions de l espace les plus peuplées. Chaque observation est alors affectée au prototype le plus proche (règle dite "de la Distance Minimale"). Chaque classe contient donc les observations qui sont plus proches d un certain prototype que de tout autre prototype