matlab中svm testacc参数,利用GA优化SVM参数的一点小探索

function [bestCVaccuarcy,bestc,bestg,ga_option] = gaSVMcgForClass(train_label,train,ga_option)

% gaSVMcgForClass

% by faruto

% 2009.10.07

%% 参数初始化

if nargin == 2

ga_option = struct('maxgen',100,'sizepop',20,'pCrossover',0.4,'pMutation',0.01, ...

'cbound',[0.1,100],'gbound',[0.01,1000],'v',3);

end

% maxgen:最大的进化代数,默认为100,一般取值范围为[100,500]

% sizepop:种群最大数量,默认为20,一般取值范围为[20,100]

% pCrossover:交叉概率,默认为0.4,一般取值范围为[0.4,0.99]

% pMutation:变异概率,默认为0.01,一般取值范围为[0.0001,0.1]

% cbound = [cmin,cmax],参数c的变化范围,默认为[0.1,100]

% gbound = [gmin,gmax],参数g的变化范围,默认为[0.01,1000]

% v:SVM Cross Validation参数,默认为3

c_len_chromosome = ceil(log2((ga_option.cbound(2)-ga_option.cbound(1))*100));

g_len_chromosome = ceil(log2((ga_option.gbound(2)-ga_option.gbound(1))*100));

len_chromosome = c_len_chromosome+g_len_chromosome;

% 将种群信息定义为一个结构体

individuals=struct('fitness',zeros(1,ga_option.sizepop), ...

'chromosome',zeros(ga_option.sizepop,len_chromosome));

% 每一代种群的平均适应度

avgfitness_gen = zeros(1,ga_option.maxgen);

% 每一代种群的最佳适应度

bestfitness_gen = zeros(1,ga_option.maxgen);

% 最佳适应度

bestfitness = 0;

% 适应度最好的染色体

bestchromosome = zeros(1,len_chromosome);

%% 初始化种群

for i = 1:ga_option.sizepop

% 编码

individuals.chromosome(i,:) = unidrnd(2,1,len_chromosome)-1;

% 解码

[c,g] = ga_decode(individuals.chromosome(i,:),ga_option.cbound,ga_option.gbound);

% 计算初始适应度(CV准确率)

cmd = ['-v ',num2str(ga_option.v),' -c ',num2str( c ),' -g ',num2str( g )];

individuals.fitness(i) = svmtrain(train_label, train, cmd);

end

% 找最佳的适应度和最好的染色体的位置

[bestfitness,bestindex]=max(individuals.fitness);

% 最好的染色体

bestchromosome = individuals.chromosome(bestindex,:);

% 初始染色体的平均适应度

avgfitness_gen(1) = sum(individuals.fitness)/ga_option.sizepop;

%% 迭代寻优

for i=1:ga_option.maxgen

% Selection Operator

individuals = Selection(individuals,ga_option);

% Crossover Operator

individuals = Crossover(individuals,ga_option);

% Mutation Operator

individuals = Mutation(individuals,ga_option);

% 计算适应度

for j = 1:ga_option.sizepop

% 解码

[c,g] = ga_decode(individuals.chromosome(j,:),ga_option.cbound,ga_option.gbound);

% 计算初始适应度(CV准确率)

cmd = ['-v ',num2str(ga_option.v),' -c ',num2str( c ),' -g ',num2str( g )];

individuals.fitness(j) = svmtrain(train_label, train, cmd);

end

% 找最佳的适应度和最好的染色体的位置

[new_bestfitness,bestindex]=max(individuals.fitness);

% 最好的染色体

new_bestchromosome = individuals.chromosome(bestindex,:);

[new_c,g] = ga_decode(new_bestchromosome,ga_option.cbound,ga_option.gbound);

[c,g] = ga_decode(bestchromosome,ga_option.cbound,ga_option.gbound);

if new_bestfitness == bestfitness && new_c < c

bestfitness = new_bestfitness;

bestchromosome = new_bestchromosome;

end

if new_bestfitness > bestfitness

bestfitness = new_bestfitness;

bestchromosome = new_bestchromosome;

end

% 这一代染色体的最佳适应度

bestfitness_gen(i) = bestfitness;

% 这一代染色体的平均适应度

avgfitness_gen(i) = sum(individuals.fitness)/ga_option.sizepop;

end

%% 结果分析

figure;

hold on;

plot(bestfitness_gen,'r');

plot(avgfitness_gen);

legend('最佳适应度','平均适应度');

title(['适应度曲线','(终止代数=',num2str(ga_option.maxgen),',种群数量pop=',num2str(ga_option.sizepop),')']);

xlabel('进化代数');ylabel('适应度');

axis([0 ga_option.maxgen 0 100]);

grid on;

[bestc,bestg] = ga_decode(bestchromosome,ga_option.cbound,ga_option.gbound);

bestCVaccuarcy = bestfitness_gen(ga_option.maxgen);