genetic algorithm for feature selection

3 次查看（过去 30 天）

显示更早的评论

HASAN AL-KAF 2017-3-23

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/331446-genetic-algorithm-for-feature-selection

编辑： Walter Roberson 2018-5-20

data.mat

在 MATLAB Online 中打开

I used the code in MathWorks and I edited but I couldn't get the result I find these error after i run the code

    Not enough input arguments.
Error in lastga>fitnessfunction (line 47)
fitnessRMSE = sqrt(sum(bsxfun(@minus,X,Y').^2,2)/20);
Error in createAnonymousFcn>@(x)fcn(x,FcnArgs{:}) (line 11)
fcn_handle = @(x) fcn(x,FcnArgs{:});
Error in makeState (line 47)
            firstMemberScore = FitnessFcn(state.Population(initScoreProvided+1,:));
Error in gaunc (line 40)
state = makeState(GenomeLength,FitnessFcn,Iterate,output.problemtype,options);
Error in ga (line 356)
            [x,fval,exitFlag,output,population,scores] = gaunc(FitnessFcn,nvars, ...
Error in lastga (line 23)
[chromosome,~,~,~,~,~] = ga(FitnessFcn,nVars,options);
Caused by:
    Failure in initial user-supplied fitness function evaluation. GA cannot continue.
>>

I Use 2015b version . I used the code for genetic algorithm for feature selection for near infrared data

    Clear all
    Data  = load('data.mat')
    % This is available in Mathworks
    GenomeLength =401; % This is the number of features in the dataset
    options = gaoptimset('CreationFcn', {@PopFunction},...
                         'PopulationSize',50,...
                         'Generations',100,...
                         'PopulationType', 'bitstring',... 
                         'SelectionFcn',{@selectionroulette},...
                         'MutationFcn',{@mutationuniform, 0.1},...
                         'CrossoverFcn', {@crossoverarithmetic,0.8},...
                         'EliteCount',2,...
                         'StallGenLimit',100,...
                         'PlotFcns',{@gaplotbestf},...  
                         'Display', 'iter'); 
    rand('seed',1)
    nVars = 20; % 
    FitnessFcn = @fitnessfunction ; 
    [chromosome,~,~,~,~,~] = ga(FitnessFcn,nVars,options);
    Best_chromosome = chromosome; % Best Chromosome
    Feat_Index = find(Best_chromosome==1); % Index of Chromosome
    end
    %%%POPULATION FUNCTION
    function [pop] = PopFunction(GenomeLength,~,options)
    RD = rand;  
    pop = (rand(options.PopulationSize, GenomeLength)> RD); % Initial Population
    end
    %%%FITNESS FUNCTION   You may design your own fitness function here
    function [fitnessRMSE] = fitnessfunction(X ,Y)
    X= data.x ;
    Y=data.y ;
    fitnessRMSE = sqrt(sum(bsxfun(@minus,X,Y').^2,2)/nvar);
    end