ISODATA聚类matlab算法带详细中文注释

本资源是ISODATA聚类算法的matlab代码，其中包括isodata.m（ISODATA算法代码，其中包括了合并分裂等一系列子函数）、provaisodata.m（算法实例调用代码）和dades.mat（存放实例数据变量的文件）三个文件，并且每个函数都有详细的中文注释，而非原来的西班牙语注释。 ISODATA算法是在k-均值算法的基础上，增加对聚类结果的“合并”和“分裂”两个操作，并设定算法运行控制参数的一种聚类算法。全称：Iterative Selforganizing Data Analysis Techniques Algorithm 即：迭代自组织数据分析算法。 “合并”操作：当聚类结果某一类中样本数太少，或两个类间的距离太近时，进行合并。“分裂”操作： 当聚类结果某一类中样本某个特征类内方差太大，将该类进行分裂。

function [Z Xcluster Ycluster A cluster] = isodata（X Y k L I ON OC OS NO min）;
 
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%  函数参数信息  %
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
s=size（X）;
s=s（2）;
cluster=zeros（1s）; % 临时空间的内部检查
iter=0;
final=0;
vuelve3=0;
A=1;     % 初始化它的第一例
primeravez=1;   % 没有要求的参数修改

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%  1.初始化中心  %
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
Z= inicializa_centros（X Y A）;


%%%%%%%%%%%%%%%%%%%%%%%%
%  主要方案  %
%%%%%%%%%%%%%%%%%%%%%%%%

while final==0   %启动循环迭代。
	%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
	%  2.设置的参数值  %
	%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%   
    if primeravez==0
		if vuelve3==0
            [Ltemp Itemp ktemp ONtemp OCtemp OStemp]=parametros（L I k ON OC OS iter）;
        end;
    end;
	
	%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
	%  3.计算和分配每个坐标最近的（X，Y）  %
	%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
    primeravez=0;
	vuelve3=1;
	for i=1:s
        cluster（i）=cercano（X（i） Y（i） Z A）;
	end;
	
	%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
	%  4.删除群集  %
	%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
	% 函数可以减少我们（如果需要）的聚类中心数目和发现。
    [Z A cluster]=eliminar（A cluster Z X Y ON）;
    
    %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
	%  5.更新群集中心  %
	%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
	Z=recalcula（cluster X Y A Z）;
    
	%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
	%  6.最后，分裂或合并  %
	%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
    if （iter==I）
        final=1;
        next=0;
	else
        next=decide78（iter k A）;
    end;


	%%%%%%%%%%%%%%%
	%  7.分裂  %
	%%%%%%%%%%%%%%%
	if next==1
        next=2;
        hubo_division=0;
        A2=A;
  	    divide=0;
        % 分散的集群，全局分散
        % Y的顺序分别为最大分散组件变量y的分散。
        
        [Di D STM]= dispersion（X Y Z cluster A）;
	
        % 满足条件的各组进行分裂
		i=0;    % 按条件作出分裂和迭代。                         
		while （hubo_division==0） & （i < A）      % 如果由于某种...                                     
		    i=i+1;                                                                                      
		    index=find（cluster==i）; % index显示群集的值分区      
		    sindex=size（index）;                                                                         
		    sindex=sindex（2）;                                                                           
		    if  （STM（i）>OS） & （  （（Di（i1）>D（1）） & （Di（i2）>D（2）） & （sindex>（2*（ON+1）））） | （A<=（k/2）） ） 
		        hubo_division=1;                                                                        
		        next=1;                                                                                 
		        [Z cluster]=dividir（STM A cluster Z i （A+1） X Y）;    % 分裂.                 
		        A=A+1;  % 表示一个新的分组。                                      
		        iter=iter+1;                                                                      

 属性            大小     日期    时间   名称
----------- ---------  ---------- -----  ----

     文件        935  2010-04-18 22:45  provaisodata.m

     文件       4512  2004-06-15 16:22  dades.mat

     文件      16043  2010-04-19 11:11  isodata.m

----------- ---------  ---------- -----  ----

                21490                    3