• <ins id="pjuwb"></ins>
    <blockquote id="pjuwb"><pre id="pjuwb"></pre></blockquote>

    <noscript id="pjuwb"></noscript>
          <sup id="pjuwb"><pre id="pjuwb"></pre></sup>

            <dd id="pjuwb"></dd>
            <abbr id="pjuwb"></abbr>
            

    
            

            




            







												


        


            


            振動理論
            

            我的C++實現之路
            

            

            
	
					
	
            
	
		
            
			C++遺傳算法源程序
		
            
		
            // CMVSOGA.h : main header file for the CMVSOGA.cpp
            ////////////////////////////////////////////////////////////////////
            /////                                                          /////
            /////                沈陽航空工業學院 動力工程系               /////
            /////                       作者：李立新                       /////
            /////                   完成日期：2006.08.02                   /////
            /////                   修改日期：2007.04.10                                       /////
            ////////////////////////////////////////////////////////////////////

            #if !defined(AFX_CMVSOGA_H__45BECA_61EB_4A0E_9746_9A94D1CCF767__INCLUDED_)
            #define AFX_CMVSOGA_H__45BECA_61EB_4A0E_9746_9A94D1CCF767__INCLUDED_
            

            #if _MSC_VER > 1000
            #pragma once
            #endif // _MSC_VER > 1000
            #include "Afxtempl.h"
            #define variablenum 14
            class CMVSOGA
            {
            public:
             CMVSOGA();
             ~CMVSOGA();
             void selectionoperator();
             void crossoveroperator();
             void mutationoperator();
             void initialpopulation(int, int ,double ,double,double *,double *);           //種群初始化
             void generatenextpopulation();          //生成下一代種群
             void evaluatepopulation();           //評價個體，求最佳個體
             void calculateobjectvalue();          //計算目標函數值
             void calculatefitnessvalue();          //計算適應度函數值
             void findbestandworstindividual();         //尋找最佳個體和最差個體
             void performevolution();   
             void GetResult(double *);
             void GetPopData(CList <double,double>&);
             void SetFitnessData(CList <double,double>&,CList <double,double>&,CList <double,double>&);
            private:
             struct individual
             {
              double chromosome[variablenum];         //染色體編碼長度應該為變量的個數
              double value;         
              double fitness;             //適應度
             };
             double variabletop[variablenum];         //變量值
             double variablebottom[variablenum];         //變量值
             int popsize;              //種群大小
            // int generation;              //世代數
             int best_index;  
             int worst_index;
             double crossoverrate;            //交叉率
             double mutationrate;            //變異率
             int maxgeneration;             //最大世代數
             struct individual bestindividual;         //最佳個體
             struct individual worstindividual;         //最差個體
             struct individual current;              //當前個體
             struct individual current1;              //當前個體
             struct individual currentbest;          //當前最佳個體
             CList <struct individual,struct individual &> population;   //種群
             CList <struct individual,struct individual &> newpopulation;  //新種群
             CList <double,double> cfitness;          //存儲適應度值
             //怎樣使鏈表的數據是一個結構體????主要是想把種群作成鏈表。節省空間。
            };
            #endif
            

             
            

            執行文件：
            

            // CMVSOGA.cpp : implementation file
            //
            

            #include "stdafx.h"
            //#include "vld.h"
            #include "CMVSOGA.h"
            #include "math.h"
            #include "stdlib.h"
            


            #ifdef _DEBUG
            #define new DEBUG_NEW
            #undef THIS_FILE
            static char THIS_FILE[] = __FILE__;
            #endif
            /////////////////////////////////////////////////////////////////////////////
            // CMVSOGA.cpp
            CMVSOGA::CMVSOGA()
            {
             best_index=0;  
             worst_index=0;
             crossoverrate=0;            //交叉率
             mutationrate=0;            //變異率
             maxgeneration=0;
            }
            CMVSOGA::~CMVSOGA()
            {
             best_index=0;  
             worst_index=0;
             crossoverrate=0;            //交叉率
             mutationrate=0;            //變異率
             maxgeneration=0;
             population.RemoveAll();   //種群
             newpopulation.RemoveAll();  //新種群
             cfitness.RemoveAll(); 
            }
            void CMVSOGA::initialpopulation(int ps, int gen ,double cr ,double mr,double *xtop,double *xbottom)  //第一步，初始化。
            {
             //應該采用一定的策略來保證遺傳算法的初始化合理，采用產生正態分布隨機數初始化？選定中心點為多少？
             int i,j;
             popsize=ps;
             maxgeneration=gen;
             crossoverrate=cr;
             mutationrate =mr;
             for (i=0;i<variablenum;i++)
             {
              variabletop[i] =xtop[i];
              variablebottom[i] =xbottom[i];
             }
             //srand( (unsigned)time( NULL ) );  //尋找一個真正的隨機數生成函數。
             for(i=0;i<popsize;i++)
             { 
              for (j=0;j<variablenum ;j++)
              {
               current.chromosome[j]=double(rand()%10000)/10000*(variabletop[j]-variablebottom[j])+variablebottom[j];
              }
              current.fitness=0;
              current.value=0;
              population.InsertAfter(population.FindIndex(i),current);//除了初始化使用insertafter外,其他的用setat命令。
             }
            }
            void CMVSOGA::generatenextpopulation()//第三步，生成下一代。
            {
             //srand( (unsigned)time( NULL ) );
             selectionoperator();
             crossoveroperator();
             mutationoperator();
            }
            //void CMVSOGA::evaluatepopulation()   //第二步，評價個體，求最佳個體
            //{
            // calculateobjectvalue();
            // calculatefitnessvalue();   //在此步中因該按適應度值進行排序.鏈表的排序.
            // findbestandworstindividual();
            //}
            void CMVSOGA:: calculateobjectvalue()  //計算函數值，應該由外部函數實現。主要因為目標函數很復雜。
            {
             int i,j;
                double x[variablenum];
             for (i=0; i<popsize; i++)
             {
              current=population.GetAt(population.FindIndex(i));  
              current.value=0;
              //使用外部函數進行，在此只做結果的傳遞。
              for (j=0;j<variablenum;j++)
              {
               x[j]=current.chromosome[j];
               current.value=current.value+(j+1)*pow(x[j],4);
              }
              ////使用外部函數進行，在此只做結果的傳遞。
              population.SetAt(population.FindIndex(i),current);
             }
            }
            

            void CMVSOGA::mutationoperator()  //對于浮點數編碼，變異算子的選擇具有決定意義。
                      //需要guass正態分布函數，生成方差為sigma，均值為浮點數編碼值c。
            {
            // srand((unsigned int) time (NULL));
             int i,j;
             double r1,r2,p,sigma;//sigma高斯變異參數
             
             for (i=0;i<popsize;i++)
             {
              current=population.GetAt(population.FindIndex(i));
            

              //生成均值為current.chromosome，方差為sigma的高斯分布數
              for(j=0; j<variablenum; j++)
              {   
               r1 = double(rand()%10001)/10000;
               r2 = double(rand()%10001)/10000;
               p = double(rand()%10000)/10000;
               if(p<mutationrate)
               {
                double sign;
                sign=rand()%2;
                sigma=0.01*(variabletop[j]-variablebottom [j]);
                //高斯變異
                if(sign)
                {
                 current.chromosome[j] = (current.chromosome[j] 
                  + sigma*sqrt(-2*log(r1)/0.4323)*sin(2*3.1415926*r2));
                }
                else
                {
                 current.chromosome[j] = (current.chromosome[j] 
                  - sigma*sqrt(-2*log(r1)/0.4323)*sin(2*3.1415926*r2));
                }
                if (current.chromosome[j]>variabletop[j])
                {
                 current.chromosome[j]=double(rand()%10000)/10000*(variabletop[j]-variablebottom[j])+variablebottom[j];
                }
                if (current.chromosome[j]<variablebottom [j])
                {
                 current.chromosome[j]=double(rand()%10000)/10000*(variabletop[j]-variablebottom[j])+variablebottom[j];
                }
               }
              }
              population.SetAt(population.FindIndex(i),current);
             }
            }
            void CMVSOGA::selectionoperator()   //從當前個體中按概率選擇新種群,應該加一個復制選擇,提高種群的平均適應度
            {
             int i,j,pindex=0;
             double p,pc,sum;
             i=0;
             j=0;
             pindex=0;
             p=0;
             pc=0;
             sum=0.001;
             newpopulation.RemoveAll();
             cfitness.RemoveAll();
              //鏈表排序
            // population.SetAt (population.FindIndex(0),current); //多余代碼
             for (i=1;i<popsize;i++)
             { 
              current=population.GetAt(population.FindIndex(i));
              for(j=0;j<i;j++)   //從小到大用before排列。
              {
               current1=population.GetAt(population.FindIndex(j));//臨時借用變量
               if(current.fitness<=current1.fitness)  
               {
                population.InsertBefore(population.FindIndex(j),current);
                population.RemoveAt(population.FindIndex(i+1));
                break;
               }
              }
            //  m=population.GetCount();
             }
             //鏈表排序
             for(i=0;i<popsize;i++)//求適應度總值，以便歸一化,是已經排序好的鏈。
             {
              current=population.GetAt(population.FindIndex(i)); //取出來的值出現問題.
              sum+=current.fitness;
             }
             for(i=0;i<popsize; i++)//歸一化
             {
              current=population.GetAt(population.FindIndex(i)); //population 有值,為什么取出來的不正確呢??
              current.fitness=current.fitness/sum;
              cfitness.InsertAfter (cfitness .FindIndex(i),current.fitness);
             }
             
             for(i=1;i<popsize; i++)//概率值從小到大;
             {
              current.fitness=cfitness.GetAt (cfitness.FindIndex(i-1))
               +cfitness.GetAt(cfitness.FindIndex(i));   //歸一化
              cfitness.SetAt (cfitness .FindIndex(i),current.fitness);
              population.SetAt(population.FindIndex(i),current);
             }
             for (i=0;i<popsize;)//輪盤賭概率選擇。本段還有問題。
             {
              p=double(rand()%999)/1000+0.0001;  //隨機生成概率
              pindex=0;  //遍歷索引
              pc=cfitness.GetAt(cfitness.FindIndex(1));  //為什么取不到數值???20060910
              while(p>=pc&&pindex<popsize) //問題所在。
              {
               pc=cfitness.GetAt(cfitness .FindIndex(pindex));
               pindex++;
              }
              //必須是從index~popsize，選擇高概率的數。即大于概率p的數應該被選擇，選擇不滿則進行下次選擇。
              for (j=popsize-1;j<pindex&&i<popsize;j--)
              {
               newpopulation.InsertAfter (newpopulation.FindIndex(0),
                population.GetAt (population.FindIndex(j)));
               i++;
              }
             }
             for(i=0;i<popsize; i++)
             {
              population.SetAt (population.FindIndex(i),
               newpopulation.GetAt (newpopulation.FindIndex(i)));
             }
            // j=newpopulation.GetCount();
            // j=population.GetCount();
             newpopulation.RemoveAll();
            }
            

            //current   變化后，以上沒有問題了。
            


            void CMVSOGA:: crossoveroperator()   //非均勻算術線性交叉，浮點數適用,alpha ,beta是(0，1)之間的隨機數
                      //對種群中兩兩交叉的個體選擇也是隨機選擇的。也可取beta=1-alpha;
                      //current的變化會有一些改變。
            {
             int i,j;
             double alpha,beta;
             CList <int,int> index;
             int point,temp;
             double p;
            // srand( (unsigned)time( NULL ) );
             for (i=0;i<popsize;i++)//生成序號
             {
              index.InsertAfter (index.FindIndex(i),i);
             }
             for (i=0;i<popsize;i++)//打亂序號
             {
              point=rand()%(popsize-1);
              temp=index.GetAt(index.FindIndex(i));
              index.SetAt(index.FindIndex(i),
               index.GetAt(index.FindIndex(point)));  
              index.SetAt(index.FindIndex(point),temp);
             }
             for (i=0;i<popsize-1;i+=2)
             {//按順序序號,按序號選擇兩個母體進行交叉操作。
              p=double(rand()%10000)/10000.0;
              if (p<crossoverrate)
              {   
               alpha=double(rand()%10000)/10000.0;
               beta=double(rand()%10000)/10000.0;
               current=population.GetAt(population.FindIndex(index.GetAt(index.FindIndex(i))));
               current1=population.GetAt(population.FindIndex(index.GetAt(index.FindIndex(i+1))));//臨時使用current1代替
               for(j=0;j<variablenum;j++)
               { 
                //交叉
                double sign;
                sign=rand()%2;
                if(sign)
                {
                 current.chromosome[j]=(1-alpha)*current.chromosome[j]+
                  beta*current1.chromosome[j];
                }
                else
                {
                 current.chromosome[j]=(1-alpha)*current.chromosome[j]-
                  beta*current1.chromosome[j];
                }
                if (current.chromosome[j]>variabletop[j])  //判斷是否超界.
                {
                 current.chromosome[j]=double(rand()%10000)/10000*(variabletop[j]-variablebottom[j])+variablebottom[j];
                }
                if (current.chromosome[j]<variablebottom [j])
                {
                 current.chromosome[j]=double(rand()%10000)/10000*(variabletop[j]-variablebottom[j])+variablebottom[j];
                }
                if(sign)
                {
                 current1.chromosome[j]=alpha*current.chromosome[j]+
                  (1- beta)*current1.chromosome[j];
                }
                else
                {
                 current1.chromosome[j]=alpha*current.chromosome[j]-
                  (1- beta)*current1.chromosome[j];
                }
                if (current1.chromosome[j]>variabletop[j])
                {
                 current1.chromosome[j]=double(rand()%10000)/10000*(variabletop[j]-variablebottom[j])+variablebottom[j];
                }
                if (current1.chromosome[j]<variablebottom [j])
                {
                 current1.chromosome[j]=double(rand()%10000)/10000*(variabletop[j]-variablebottom[j])+variablebottom[j];
                }
               }
               //回代
              }
              newpopulation.InsertAfter  (newpopulation.FindIndex(i),current);
              newpopulation.InsertAfter  (newpopulation.FindIndex(i),current1);
             }
             ASSERT(newpopulation.GetCount()==popsize);
             for (i=0;i<popsize;i++)
             {
              population.SetAt (population.FindIndex(i),
               newpopulation.GetAt (newpopulation.FindIndex(i)));
             }
             newpopulation.RemoveAll();
             index.RemoveAll();
            }
            void CMVSOGA:: findbestandworstindividual( )  
            {
             int i;
             bestindividual=population.GetAt(population.FindIndex(best_index));
             worstindividual=population.GetAt(population.FindIndex(worst_index));
             for (i=1;i<popsize; i++)
             {
              current=population.GetAt(population.FindIndex(i));
              if (current.fitness>bestindividual.fitness)
              {
               bestindividual=current;
               best_index=i;
              }
              else if (current.fitness<worstindividual.fitness)
              {
               worstindividual=current;
               worst_index=i;
              }
             }
             population.SetAt(population.FindIndex(worst_index),
              population.GetAt(population.FindIndex(best_index)));
             //用最好的替代最差的。
             if (maxgeneration==0)
             {
              currentbest=bestindividual;
             }
             else
             {
              if(bestindividual.fitness>=currentbest.fitness)
              {
               currentbest=bestindividual;
              }
             }
            }
            void CMVSOGA:: calculatefitnessvalue() //適應度函數值計算，關鍵是適應度函數的設計
                      //current變化，這段程序變化較大，特別是排序。
            {
             int  i;
             double temp;//alpha,beta;//適應度函數的尺度變化系數
             double cmax=100;
             for(i=0;i<popsize;i++)
             {
              current=population.GetAt(population.FindIndex(i));
              if(current.value<cmax)
              {
               temp=cmax-current.value;
              }
              else
              {
               temp=0.0;
              }
              /*
              if((population[i].value+cmin)>0.0)
              {temp=cmin+population[i].value;}
             else
             {temp=0.0;
               }
              */
              current.fitness=temp;
              population.SetAt(population.FindIndex(i),current); 
             }
            }
            void CMVSOGA:: performevolution() //演示評價結果,有冗余代碼,current變化，程序應該改變較大
            {
             if (bestindividual.fitness>currentbest.fitness)
             {
              currentbest=population.GetAt(population.FindIndex(best_index));
             }
             else
             {
              population.SetAt(population.FindIndex(worst_index),currentbest);
             }
            }
            void CMVSOGA::GetResult(double *Result)
            {
             int i;
             for (i=0;i<variablenum;i++)
             {
              Result[i]=currentbest.chromosome[i];
             }
             Result[i]=currentbest.value;
            }
            

            void CMVSOGA::GetPopData(CList <double,double>&PopData)  
            {
             PopData.RemoveAll();
             int i,j;
             for (i=0;i<popsize;i++)
             {
              current=population.GetAt(population.FindIndex(i));
              for (j=0;j<variablenum;j++)
              {
               PopData.AddTail(current.chromosome[j]);
              }
             }
            }
            void CMVSOGA::SetFitnessData(CList <double,double>&PopData,CList <double,double>&FitnessData,CList <double,double>&ValueData)
            {
             int i,j;
             for (i=0;i<popsize;i++)
             {  
              current=population.GetAt(population.FindIndex(i)); //就因為這一句，出現了很大的問題。 
              for (j=0;j<variablenum;j++)
              {
               current.chromosome[j]=PopData.GetAt(PopData.FindIndex(i*variablenum+j));
              }
              current.fitness=FitnessData.GetAt(FitnessData.FindIndex(i));
              current.value=ValueData.GetAt(ValueData.FindIndex(i));
              population.SetAt(population.FindIndex(i),current);
             }
             FitnessData.RemoveAll();
             PopData.RemoveAll();
             ValueData.RemoveAll();
            }
            

            
		
            
			posted on 2007-05-26 08:14 唯月釋懷 閱讀(15054) 評論(7)  編輯 收藏 引用  
		
            
	
            
	
	





            
	    
    


            

            Feedback
            
	
	
			
            
				# re: C++遺傳算法源程序
					
						2007-05-26 17:38
					
				pass86
			
            
			
            
				我也寫過一點，從書上改編的。
            /********************************************************************
            	Filename: 	aiWorld.h
                Purpose:	遺傳算法，花朵演化。
            	Author:		pass86
                E-mail:     pass86@gmail.com
                Created:	2007/03/29
                Id:
                Copyright:
                Licence:
            *********************************************************************/
            #ifndef AIWORLD_H_
            #define AIWORLD_H_

            #include <iostream>
            #include <ctime>
            #include <cstdlib>
            #include <cmath>

            #define kMaxFlowers                         10

            using std::cout;
            using std::endl;

            class ai_World
            {
            public:
            	ai_World()
            	{
            	    srand(time(0));
                }
            	~ai_World() {}

            	int temperature[kMaxFlowers];           //溫度
            	int water[kMaxFlowers];                 //水質
            	int sunlight[kMaxFlowers];              //陽光
            	int nutrient[kMaxFlowers];              //養分
            	int beneficialInsect[kMaxFlowers];      //益蟲
            	int harmfulInsect[kMaxFlowers];         //害蟲

                int currentTemperature;
                int currentWater;
                int currentSunlight;
                int currentNutrient;
                int currentBeneficialInsect;
                int currentHarmfulInsect;

                /**
                第一代花朵
                */
            	void Encode();

            	/**
            	花朵適合函數
            	*/
            	int Fitness(int flower);

            	/**
            	花朵演化
            	*/
            	void Evolve();

            	/**
            	返回區間[start, end]的隨機數
            	*/
            	inline int tb_Rnd(int start, int end)
            	{
            	    if (start > end)
                        return 0;
                    else
                    {
                        //srand(time(0));
                        return (rand() % (end + 1) + start);
                    }
            	}

            	/**
            	顯示數值
            	*/
            	void show();
            };
            // ----------------------------------------------------------------- //
            void ai_World::Encode()
            // ----------------------------------------------------------------- //

            {
            	int					i;

            	for (i=0;i<kMaxFlowers;i++)
            		{
            			temperature[i]=tb_Rnd(1,75);
            			water[i]=tb_Rnd(1,75);
            			sunlight[i]=tb_Rnd(1,75);
            			nutrient[i]=tb_Rnd(1,75);
            			beneficialInsect[i]=tb_Rnd(1,75);
            			harmfulInsect[i]=tb_Rnd(1,75);
            		}

            	currentTemperature=tb_Rnd(1,75);
            	currentWater=tb_Rnd(1,75);
            	currentSunlight=tb_Rnd(1,75);
            	currentNutrient=tb_Rnd(1,75);
            	currentBeneficialInsect=tb_Rnd(1,75);
            	currentHarmfulInsect=tb_Rnd(1,75);

            	currentTemperature=tb_Rnd(1,75);
            	currentWater=tb_Rnd(1,75);
            	currentSunlight=tb_Rnd(1,75);
            	currentNutrient=tb_Rnd(1,75);
            	currentBeneficialInsect=tb_Rnd(1,75);
            	currentHarmfulInsect=tb_Rnd(1,75);

            }
            // ----------------------------------------------------------------- //
            int ai_World::Fitness(int flower)
            // ----------------------------------------------------------------- //

            {
            	int				theFitness;


            	theFitness=abs(temperature[flower]-currentTemperature);
            	theFitness=theFitness+abs(water[flower]-currentWater);
            	theFitness=theFitness+abs(sunlight[flower]-currentSunlight);
            	theFitness=theFitness+abs(nutrient[flower]-currentNutrient);
            	theFitness=theFitness+abs(beneficialInsect[flower]-currentBeneficialInsect);
            	theFitness=theFitness+abs(harmfulInsect[flower]-currentHarmfulInsect);

            	return (theFitness);

            }
            // ----------------------------------------------------------------- //
            void ai_World::Evolve()
            // ----------------------------------------------------------------- //

            {
            	int						fitTemperature[kMaxFlowers];
            	int						fitWater[kMaxFlowers];
            	int						fitSunlight[kMaxFlowers];
            	int						fitNutrient[kMaxFlowers];
            	int						fitBeneficialInsect[kMaxFlowers];
            	int						fitHarmfulInsect[kMaxFlowers];
            	int						fitness[kMaxFlowers];
            	int						i;
            	int						leastFit=0;
            	int						leastFitIndex;

            	for (i=0;i<kMaxFlowers;i++)
            		if (Fitness(i)>leastFit)
            			{
            				leastFit=Fitness(i);
            				leastFitIndex=i;
            			}

            	temperature[leastFitIndex]=temperature[tb_Rnd(0,kMaxFlowers - 1)];
            	water[leastFitIndex]=water[tb_Rnd(0,kMaxFlowers - 1)];
            	sunlight[leastFitIndex]=sunlight[tb_Rnd(0,kMaxFlowers - 1)];
            	nutrient[leastFitIndex]=nutrient[tb_Rnd(0,kMaxFlowers - 1)];
            	beneficialInsect[leastFitIndex]=beneficialInsect[tb_Rnd(0,kMaxFlowers - 1)];
            	harmfulInsect[leastFitIndex]=harmfulInsect[tb_Rnd(0,kMaxFlowers - 1)];

            	for (i=0;i<kMaxFlowers;i++)
            		{
            			fitTemperature[i]=temperature[tb_Rnd(0,kMaxFlowers - 1)];
            			fitWater[i]=water[tb_Rnd(0,kMaxFlowers - 1)];
            			fitSunlight[i]=sunlight[tb_Rnd(0,kMaxFlowers - 1)];
            			fitNutrient[i]=nutrient[tb_Rnd(0,kMaxFlowers - 1)];
            			fitBeneficialInsect[i]=beneficialInsect[tb_Rnd(0,kMaxFlowers - 1)];
            			fitHarmfulInsect[i]=harmfulInsect[tb_Rnd(0,kMaxFlowers - 1)];
            		}

            	for (i=0;i<kMaxFlowers;i++)
            		{
            				temperature[i]=fitTemperature[i];
            				water[i]=fitWater[i];
            				sunlight[i]=fitSunlight[i];
            				nutrient[i]=fitNutrient[i];
            				beneficialInsect[i]=fitBeneficialInsect[i];
            				harmfulInsect[i]=fitHarmfulInsect[i];
            		}

            	for (i=0;i<kMaxFlowers;i++)
            		{
            			if (tb_Rnd(1,100)==1)
            				temperature[i]=tb_Rnd(1,75);
            			if (tb_Rnd(1,100)==1)
            				water[i]=tb_Rnd(1,75);
            			if (tb_Rnd(1,100)==1)
            				sunlight[i]=tb_Rnd(1,75);
            			if (tb_Rnd(1,100)==1)
            				nutrient[i]=tb_Rnd(1,75);
            			if (tb_Rnd(1,100)==1)
            				beneficialInsect[i]=tb_Rnd(1,75);
            			if (tb_Rnd(1,100)==1)
            				harmfulInsect[i]=tb_Rnd(1,75);
            		}

            }
            void ai_World::show()
            {
            //    cout << "\t temperature water sunlight nutrient beneficialInsect harmfulInsect\n";
                cout << "current\t  " << currentTemperature << "\t " << currentWater << "\t ";
                cout << currentSunlight << "\t " << currentNutrient << "\t ";
                cout << currentBeneficialInsect << "\t " << currentHarmfulInsect << "\n";
                for (int i=0;i<kMaxFlowers;i++)
                {
                    cout << "Flower " << i << ": ";
                    cout << temperature[i] << "\t ";
            		cout << water[i] << "\t ";
                    cout << sunlight[i] << "\t ";
            		cout << nutrient[i] << "\t ";
            		cout << beneficialInsect[i] << "\t ";
            		cout << harmfulInsect[i] << "\t ";
            		cout << endl;
                }
            }
            #endif // AIWORLD_H_

            //test.cpp
            #include <iostream>
            #include "ai_World.h"

            using namespace std;

            int main()
            {
                ai_World a;
                a.Encode();
            //    a.show();
                for (int i = 0; i < 10; i++)
                {
                    cout << "Generation " << i << endl;
                    a.Evolve();
                    a.show();
                }

                system("PAUSE");
                return 0;
            }
              回復  更多評論
				  			
			
            
		
			
            
				# re: C++遺傳算法源程序
					
						2007-05-27 19:04
					
				江水獸
			
            
			
            
				啊哈 當初我也寫過 只是沒有像這樣如此具有遺傳算法的特點 當時只是為了選修課寫的一個具有基本功能的GA Program  回復  更多評論
				  			
			
            
		
			
            
				# re: C++遺傳算法源程序
					
						2007-06-25 17:33
					
				7777
			
            
			
            
				垃圾  什么你都往上傳  回復  更多評論
				  			
			
            
		
			
            
				# re: C++遺傳算法源程序
					
						2007-10-21 08:15
					
				starlet
			
            
			
            
				作者不知道有沒有聯系方式，有問題請教  回復  更多評論
				  			
			
            
		
			
            
				# re: C++遺傳算法源程序
					
						2008-04-20 02:33
					
				阿毛
			
            
			
            
				你好，我在做遺傳算法解決vrp問題的畢業論文，有問題想指教，有償求助，急，望回復，我的q是267497220  回復  更多評論
				  			
			
            
		
			
            
				# re: C++遺傳算法源程序
					
						2008-10-19 21:57
					
				禇
			
            
			
            
				謝謝，我如果有新的代碼，也給大家傳上來共享！  回復  更多評論
				  			
			
            
		
			
            
				# re: C++遺傳算法源程序
					
						2011-04-20 16:28
					
				sjiao888
			
            
			
            
				你好，我在做遺傳算法的畢業論文，有問題想指教，我的QQ是709375489  回復  更多評論
				  			
			
            
		

            

            




            






            

				

            

            

	

            My Links
            

	

            Blog Stats
            
	
	
	

            常用鏈接
            


            留言簿(5)
            


		
            隨筆檔案
            
		
				
			
	
		
            文章檔案
            
		
				
			
	
		
            My sohu blog
            
		
				
			
	


            搜索
            



            最新評論
	
            

            
	
			
		

            


            閱讀排行榜
            



            評論排行榜
            




            


    
    







            
	   
	



国产亚洲成人久久|
久久精品亚洲男人的天堂|
亚洲精品无码专区久久久
|
久久久久久极精品久久久
|
日本五月天婷久久网站|
亚洲国产欧美国产综合久久|
久久亚洲AV成人无码电影|
国产精品九九久久精品女同亚洲欧美日韩综合区|
久久综合九色综合97_久久久|
久久久精品久久久久久
|
狠狠精品久久久无码中文字幕|
久久久国产精品亚洲一区
|
久久夜色精品国产噜噜麻豆|
久久久久中文字幕|
精品人妻伦九区久久AAA片69|
91亚洲国产成人久久精品|
无码国产69精品久久久久网站|
久久AAAA片一区二区|
国产精品免费看久久久|
偷窥少妇久久久久久久久|
久久996热精品xxxx|
国内精品久久人妻互换
|
国产激情久久久久影院|
精品久久8x国产免费观看|
97精品依人久久久大香线蕉97|
久久久久一本毛久久久|
国产激情久久久久影院|
97超级碰碰碰碰久久久久|
久久91精品国产91久久小草|
婷婷久久香蕉五月综合加勒比|
一本久久综合亚洲鲁鲁五月天|
欧美激情精品久久久久|
国产亚洲婷婷香蕉久久精品|
97精品国产97久久久久久免费|
久久久久久精品无码人妻|
亚洲欧美日韩精品久久亚洲区|
久久精品国产99久久丝袜|
国产精品成人久久久久三级午夜电影
|
亚洲欧美日韩久久精品|
亚洲国产成人久久综合一区77|
天天做夜夜做久久做狠狠|