1. 技术文章
  2. 数据挖掘之神经网络SOM算法

数据挖掘之神经网络SOM算法

由 不打扰是莪最后的温柔 提交于 2019-12-27 05:40:04 
/*神经网络SOM算法思想：分为输入层和竞争层，输入层就是样本的输入，假如我现在有5个样本A,B,C,D,E,他们是5维向量，竞争层是10*10的二维平面，相当于100个神经元，这些神经元也是5维向量，这些神经元对输入向量进行竞争，最后只有一个神经元获胜，越是与输入向量相似，竞争力越强，假如现在位于(7,8)的神经元最相似，它有权力去修改以它为中心的神经元的值，越靠近它的神经元影响越大，越是接近获胜神经元。假如样本A对应的获胜神经元是（7,8），B对应的获胜神经元是(6,8),因为这两个神经元靠得很近，所以样本A和B很相似。如果C对应的获胜神经元是(1,1)，与另外两个距离比较远，所以C与A,B相似度较低。
*/#include<fstream.h>
#include<iomanip.h>
#include<stdio.h>
#include<cstdlib.h>
#include<math.h>
using namespace std;
#define InputLayerNum 35
#define OutputLayerRow 8
#define OutputLayerColumn 12
#define total_iteration_Num 80
#define error_limit 0.0001
#define efficiency 0.9

int i,j,k,l,m,n;
int inputMode[26][7][5];
double weight[OutputLayerRow*OutputLayerColumn][InputLayerNum];
int current_iteration_num=0;
double study_efficiency=efficiency;
double distance[OutputLayerRow*OutputLayerColumn];
int neighbor_width=OutputLayerColumn;
int neighbor_height=OutputLayerRow;
int row[OutputLayerRow],column[OutputLayerColumn];
int flag[OutputLayerRow][OutputLayerColumn];
int temp_row,temp_column;
int winner_row,winner_column;
double min_distance=1000.0;

/****************************************************/
//该函数初始化距离变量为0，初始化保存生胜出节点的位置的变量
/****************************************************/
void init_distance(){
    for(i=0;i<OutputLayerRow;i++)
        for(j=0;j<OutputLayerColumn;j++)
        distance[i*OutputLayerColumn+j]=0.0;
}
/****************************************************/
//该函数用于计算欧氏距离，并找到获胜神经元
/****************************************************/
void eula_distance(){
    int ttLow,ttUp,ppLow,ppUp;
    ttLow=winner_column-neighbor_width/2;
    ttUp=winner_column+neighbor_width/2;
    ppLow=winner_row-neighbor_height/2;
    ppUp=winner_row+neighbor_height/2;
    if(ttLow<0) ttLow=0;
    if(ttUp>=OutputLayerColumn) ttUp=OutputLayerColumn-1;
    if(ppLow<0) ppLow=0;
    if(ppUp>=OutputLayerRow) ppUp=OutputLayerRow-1;
    for(i=ppLow;i<=ppUp;i++)
    for(j=ttLow;j<=ttUp;j++){
        if(!(flag[i][i]==100)){
            for(m=0;m<7;m++)
                for(n=0;n<5;n++)
                distance[i*OutputLayerColumn+j]+=pow((inputMode[l][m][n]-
                                                     weight[i*OutputLayerColumn+j][m*5+n]),2);
            if(distance[i*OutputLayerColumn+j]<min_distance){
                min_distance=distance[i*OutputLayerColumn+j];
                temp_row=i;
                temp_column=j;
            }
        }
    }
    if(current_iteration_num>0){
        if(min_distance<=error_limit){
            row[temp_row]=temp_row;
            row[temp_column]=temp_column;
            flag[temp_row][temp_column]=100;
        }
    }
}
/****************************************************/
//调整权值
/****************************************************/
void weight_change(){
    int ttLow,ttUp,ppLow,ppUp;
    winner_row=temp_row;
    winner_column=temp_column;
    ttLow=winner_column-neighbor_width/2;
    ttUp=winner_column+neighbor_width/2;
    ppLow=winner_row-neighbor_height/2;
    ppUp=winner_row+neighbor_height/2;
    if(ttLow<0) ttLow=0;
    if(ttUp>=OutputLayerColumn) ttUp=OutputLayerColumn-1;
    if(ppLow<0) ppLow=0;
    if(ppUp>=OutputLayerRow) ppUp=OutputLayerRow-1;
    for(i=ppLow;i<=ppUp;i++)
    for(j=ttLow;j<=ttUp;j++){
        if(!(flag[i][j]==100)){
            for(m=0;m<7;m++)
                for(n=0;n<5;n++)
                weight[i*OutputLayerColumn+j][m*5+n]+=
                study_efficiency*(inputMode[l][m][n]-weight[i*OutputLayerColumn+j][m*5+n]);
        }
    }
}

/****************************************************/
//调整学习效率以及获胜节点的邻域大小
/****************************************************/
void paraChange(){
    study_efficiency=study_efficiency*(1.0-((double)current_iteration_num)/total_iteration_Num);
    neighbor_width=(int)(neighbor_width*(1.0-((double)current_iteration_num)/total_iteration_Num));
    neighbor_height=(int)(neighbor_height*(1.0-((double)current_iteration_num)/total_iteration_Num));
}

/****************************************************/
//该函数用于将所有输入模式从文件中读入，并存放在数组inputMode中
//同时进行权值的初始化，采用随机赋值的方法
/****************************************************/
void initialize(){
    for(i=0;i<OutputLayerRow;i++) row[i]=100;
    for(j=0;j<OutputLayerColumn;j++) column[j]=100;
    for(i=0;i<OutputLayerRow;i++)
        for(j=0;j<OutputLayerColumn;j++) flag[i][j]=0;

    FILE *pf=fopen("输入数据.txt","a+");
    if(pf==NULL){
        cout<<"Can not input file!\n";
        exit(0);
    }
    for(i=0;i<26;i++)
        for(j=0;j<7;j++)
        for(k=0;k<5;k++) fscanf(pf,"%d",&inputMode[i][j][k]);
    //用于测试是否能够正确读入输入模式
    char character[26];
    for(i=0;i<26;i++) character[i]=(65+i);
    ofstream mode("输出数据.txt",ios::out);
    for(i=0;i<26;i++){
        mode<<character[i]<<'\n'<<endl;
        for(j=0;j<7;j++){
            for(k=0;k<5;k++) mode<<inputMode[i][j][k]<<" ";
            mode<<"\n";
        }
        mode<<"\n\n\n";
    }
    //权值随机初始化，采用随机赋值的方法
    for(i=0;i<OutputLayerRow;i++)
        for(j=0;j<OutputLayerColumn;j++)
        for(k=0;k<InputLayerNum;k++)
        weight[i*OutputLayerColumn+j][k]=(double)(rand()%101)/100.0;
    //用于测试是否能够正确初始化权值
    ofstream quan("初始权值.txt",ios::out);
    for(i=0;i<OutputLayerRow;i++)
    for(j=0;j<OutputLayerColumn;j++){
        quan<<"\n\n\n"<<"Node["<<i+1<<"]["<<j+1<<"]"<<"\n";
        for(k=0;k<InputLayerNum;k++){
            if(k%5==0) quan<<"\n";
            quan<<setprecision(6)<<setiosflags(ios::fixed)<<weight[i*OutputLayerColumn+j][k]<<"    ";
        }
        quan<<"\n\n\n";
    }
}

int main(){
    int iteration_numbers[26];
    int total_num=0;
    char character[26];
    void test_netWork_1();
    void test_netWork_2();
    for(l=0;l<26;l++){
        iteration_numbers[l]=0;
        character[l]=(65+l);
    }
    initialize();
    for(l=0;l<26;l++){
        winner_row=OutputLayerRow/2;
        winner_column=OutputLayerColumn/2;
        while(current_iteration_num<total_iteration_Num){//迭代次数控制
            init_distance();
            eula_distance();
            weight_change();
            if(min_distance<=error_limit) break;
            ++current_iteration_num;
            paraChange();
        }
        iteration_numbers[l]=current_iteration_num+1;
        neighbor_width=OutputLayerColumn; //修改邻域的宽度
        neighbor_height=OutputLayerRow;  //修改邻域的高度
        study_efficiency=efficiency;  //学习率重置
        current_iteration_num=0;     //重置迭代次数
        min_distance=1000.0;         //重置最小距离
    }
    /***********************************/
    //输出部分
    /***********************************/
    for(l=0;l<26;l++) total_num+=iteration_numbers[l];
    ofstream iteration_num("迭代次数.txt",ios::out);
    for(l=0;l<26;l++){
        iteration_num<<character[l]<<"迭代"<<iteration_numbers[l]<<"次!\n"<<endl;
        if(l==25) iteration_num<<"整个训练过程共迭代"<<total_num<<"次!\n"<<endl;
    }
    ofstream all_weight("训练后所有权值.txt",ios::out);
    ofstream winner_weight("训练后胜出权值.txt",ios::out);
    for(i=0;i<OutputLayerRow;i++)
    for(j=0;j<OutputLayerColumn;j++){
        printf("\n\n\n");
        all_weight<<"\n\n\n"<<"Node["<<i+1<<"]["<<j+1<<"]"<<"\n";
        for(k=0;k<InputLayerNum;k++){
            if(k%5==0){
                printf("\n");
                all_weight<<"\n";
            }
            if(weight[i*OutputLayerColumn+j][k]>0.9999999) weight[i*OutputLayerColumn+j][k]=1.0;
            if(weight[i*OutputLayerColumn+j][k]<0.0000001) weight[i*OutputLayerColumn+j][k]=0.0;
            printf("%f    ",weight[i*OutputLayerColumn+j][k]);
            all_weight<<setprecision(8)<<setiosflags(ios::fixed)<<weight[i*OutputLayerColumn+j][k]<<"   ";

        }
    }
    ofstream winner_node("获胜节点.txt",ios::out);
    for(i=0;i<OutputLayerRow;i++)
    for(j=0;j<OutputLayerColumn;j++){
        if(flag[i][j]==100){ //获胜节点
            printf("\n\n\n");
            winner_weight<<"\n\n\n"<<"Node["<<i+1<<"]["<<j+1<<"]"<<"\n";
            for(k=0;k<InputLayerNum;k++){
                if(k%5==0){
                    printf("\n");
                    winner_weight<<"\n";
                }
                if(weight[i*OutputLayerColumn+j][k]>0.9999999) weight[i*OutputLayerColumn+j][k]=1.0;
                if(weight[i*OutputLayerColumn+j][k]<0.0000001) weight[i*OutputLayerColumn+j][k]=0.0;

                printf("%f    ",weight[i*OutputLayerColumn+j][k]);
                winner_weight<<setprecision(8)<<setiosflags(ios::fixed)<<weight[i*OutputLayerColumn+j][k]<<"    ";

            }
            winner_node<<"Node["<<i+1<<"]["<<j+1<<"]"<<endl;
        }
    }
    printf("\n");
    test_netWork_1();
    test_netWork_2();
    return 0;
}

void test_netWork_1(){
    ofstream test1("标准测试.txt",ios::out);
    char character[26];
    for(i=0;i<26;i++) character[i]=(65+i);
    for(l=0;l<26;l++){
        for(i=0;i<OutputLayerRow;i++)
           for(j=0;j<OutputLayerColumn;j++) distance[i*OutputLayerColumn+j]=0.0;
           min_distance=1000;
           for(i=0;i<OutputLayerRow;i++)
           for(j=0;j<OutputLayerColumn;j++){
               for(m=0;m<7;m++)
                for(n=0;n<5;n++)
                  distance[i*OutputLayerColumn+j]+=pow(inputMode[l][m][n]-weight[i*OutputLayerColumn+j][m*5+n],2);
               if(distance[i*OutputLayerColumn+j]<min_distance){
                  min_distance=distance[i*OutputLayerColumn+j];
                  temp_row=i;
                  temp_column=j;
               }
           }
           test1<<character[l]<<"'s winner is Node["<<temp_row+1<<"]["<<temp_column+1<<"]"<<endl<<endl;
    }
}
/****************************************************/
//利用非标准数据测试训练后的网络
/****************************************************/
void test_netWork_2(){
    ofstream test2("非标准测试.txt",ios::out);
    char character[26];
    FILe *pf=fopen("非标准数据测试.txt","a+");
    if(pf==NULL){
        cout<<"Can not open input file!\n";
        exit(0);
    }
    for(i=0;i<26;i++)
        for(j=0;j<7;j++)
        for(k=0;k<5;k++) fscanf(pf,"%d",&inputMode[i][j][k]);
    for(i=0;i<26;i++) character[i]=(65+i);
    for(l=0;l<26;l++){
        for(i=0;i<OutputLayerRow;i++)
            for(j=0;j<OutputLayerColumn;j++) distance[i*OutputLayerColumn+j]=0.0;
        min_distance=1000;
        for(i=0;i<OutputLayerRow;i++)
        for(j=0;j<OutputLayerColumn;j++){
            for(m=0;m<7;m++)
                for(n=0;n<5;n++)
                distance[i*OutputLayerColumn+j]+=pow(inputMode[l][m][n]-weight[i*OutputLayerColumn+j][m*5+n],2);
            if(distance[i*OutputLayerColumn+j]<min_distance){
                min_distance=distance[i*OutputLayerColumn+j];
                temp_row=i;
                temp_column=j;
            }
        }
        test2<<character[l]<<"'s winner is Node["<<temp_row+1<<"]["<<temp_column+1<<"]"<<endl<<endl;
    }
}

 

标签
神经网络算法
num
som
易学教程内所有资源均来自网络或用户发布的内容，如有违反法律规定的内容欢迎反馈！
该文章没有解决你所遇到的问题?点击提问,说说你的问题,让更多的人一起探讨吧!