CS-SVM_惩罚参数c_核函数_gamma.zip

function [bestsol,fval]=cuckoo_ori_with_chinese_note(time) % 由CS算法源码添加中文注释，Genlovy Hoo，2016.09.05 clear clc close all format long if nargin<1, % Number of iteraions 迭代次数 time=2000; end disp('Computing ... it may take a few minutes.'); % Number of nests (or different solutions) n=25; % n为巢穴数量 % Discovery rate of alien eggs/solutions pa=0.25; % 被宿主发现的概率 % Simple bounds of the search domain % Lower bounds and upper bounds dim = 3; % 需要寻优的参数个数 Lb=[0.05,0.25,2.0]; % 设置参数下界 Ub=[2.0,1.3,15.0]; % 设置参数上界 % Random initial solutions nest=zeros(n,dim); for i=1:n % 遍历每个巢穴 nest(i,:)=Lb+(Ub-Lb).*rand(size(Lb)); % 对每个巢穴，随机初始化参数 end % Get the current best fitness=10^10*ones(n,1); % 目标函数值初始化 [fmin,bestnest,nest,fitness]=get_best_nest(nest,nest,fitness); % 找出当前最佳巢穴和参数 N_iter=0; % 迭代计数器 %% Starting iterations for t=1:time % Generate new solutions (but keep the current best) new_nest=get_cuckoos(nest,bestnest,Lb,Ub); % 保留当前最优解，寻找新巢穴 [fnew,best,nest,fitness]=get_best_nest(nest,new_nest,fitness); % 找出当前最佳巢穴和参数 % Update the counter N_iter=N_iter+n; % 更新计数器 % Discovery and randomization new_nest=empty_nests(nest,Lb,Ub,pa); % 发现并更新劣质巢穴 % Evaluate this solution [fnew,best,nest,fitness]=get_best_nest(nest,new_nest,fitness); % 找出当前最佳巢穴和参数 % Update the counter again N_iter=N_iter+n; % 更新计数器 % Find the best objective so far if fnew<fmin, fmin=fnew; bestnest=best ; end end %% End of iterations %% Post-optimization processing %% Display all the nests disp(strcat('Total number of iterations=',num2str(N_iter))); fmin bestnest %% --------------- All subfunctions are list below ------------------ %% Get cuckoos by ramdom walk 通过随机游走搜寻鸟巢 function nest=get_cuckoos(nest,best,Lb,Ub) % Levy flights n=size(nest,1); % 鸟巢个数 % Levy exponent and coefficient % For details, see equation (2.21), Page 16 (chapter 2) of the book % X. S. Yang, Nature-Inspired Metaheuristic Algorithms, 2nd Edition, Luniver Press, (2010). % Levy flights参数准备 beta=3/2; sigma=(gamma(1+beta)*sin(pi*beta/2)/(gamma((1+beta)/2)*beta*2^((beta-1)/2)))^(1/beta); % gamma(x)求gamma函数值 for j=1:n % 遍历每个巢穴 s=nest(j,:); % 提取当前巢穴的参数 % This is a simple way of implementing Levy flights % For standard random walks, use step=1; %% Levy flights by Mantegna's algorithm u=randn(size(s))*sigma; % 生成服从 N(0,sigma^2) 的随机数u，u为长度为参数个数的向量 v=randn(size(s)); % 生成服从 N(0,1) 的随机数v向量 step=u./abs(v).^(1/beta); % 计算步长 % In the next equation, the difference factor (s-best) means that % when the solution is the best solution, it remains unchanged. stepsize=0.01*step.*(s-best); % 巢穴位置变化量，如当前巢穴为最优解，则变化量将为0 % Here the factor 0.01 comes from the fact that L/100 should the typical % step size of walks/flights where L is the typical lenghtscale; % otherwise, Levy flights may become too aggresive/efficient, % which makes new solutions (even) jump out side of the design domain % (and thus wasting evaluations). % Now the actual random walks or flights s=s+stepsize.*randn(size(s)); % 步长调整 % Apply simple bounds/limits nest(j,:)=simplebounds(s,Lb,Ub); % 更新巢穴 end %% Find the current best nest function [fmin,best,nest,fitness]=get_best_nest(nest,newnest,fitness) % 该函数用于寻找当前最优巢穴和最优目标函数值 % Evaluating all new solutions for j=1:size(nest,1) % 遍历每个旧巢穴 fnew=fobj(newnest(j,:)); % 对每个新巢穴，计算目标函数值 if fnew<=fitness(j) % 如果新目标函数值优于对应旧目标函数值 fitness(j)=fnew; % 更新当前巢穴目标函数值 nest(j,:)=newnest(j,:); % 更新对应巢穴 end end % Find the current best [fmin,K]=min(fitness) ; % 找出当前最优目标函数值 best=nest(K,:); % 当前最优巢穴（即当前最优参数值） %% Replace some nests by constructing new solutions/nests 替代某些巢穴 function new_nest=empty_nests(nest,Lb,Ub,pa) % A fraction of worse nests are discovered with a probability pa % 部分劣质巢穴以一定概率被发现 n=size(nest,1); % 鸟巢个数 % Discovered or not -- a status vector K=rand(size(nest))>pa; % 判断巢穴是否会被发现 % In real world, if a cuckoo's egg is very similar to a host's eggs, then % this cuckoo's egg is less likely to be discovered, thus the fitness should % be related to the difference in solutions. Therefore, it is a good idea % to do a random walk in a biased way with some random step sizes. nestn1=nest(randperm(n),:); % 重新随机排列巢穴 nestn2=nest(randperm(n),:); % 重新随机排序巢穴 %% New solution by biased/selective random walks stepsize=rand*(nestn1-nestn2); % 计算调整步长 new_nest=nest+stepsize.*K; % 新巢穴 for j=1:size(new_nest,1) % 遍历每个新巢穴 s=new_nest(j,:); % 提取当前巢穴的参数 new_nest(j,:)=simplebounds(s,Lb,Ub); % end % Application of simple constraints function s=simplebounds(s,Lb,Ub) % Apply the lower bound ns_tmp=s; % 复制临时变量（参数） I=ns_tmp<Lb; % 判断参数是否小于下临界值 ns_tmp(I)=Lb(I); % Apply the upper bounds J=ns_tmp>Ub; % 判断参数是否大于上临界值 ns_tmp(J)=Ub(J); % 将超出下临界值的参数拉回下边界 % Update this new move s=ns_tmp; % 更新参数 %% Spring desgn optimization -- objective function function z=fobj(u) % The well-known spring design problem z=(2+u(3))*u(1)^2*u(2); z=z+getnonlinear(u); function Z=getnonlinear(u) Z=0; % Penalty constant lam=10^15; % Inequality constraints g(1)=1-u(2)^3*u(3)/(71785*u(1)^4); gtmp=(4*u(2)^2-u(1)*u(2))/(12566*(u(2)*u(1)^3-u(1)^4)); g(2)=gtmp+1/(5108*u(1)^2)-1; g(3)=1-140.45*u(1)/(u(2)^2*u(3)); g(4)=(u(1)+u(2))/1.5-1; % No equality constraint in this problem, so empty; geq=[]; % Apply inequality constraints for k=1:length(g), Z=Z+ lam*g(k)^2*getH(g(k)); end % Apply equality constraints for k=1:length(geq), Z=Z+lam*geq(k)^2*getHeq(geq(k)); end % Test if inequalities hold % Index function H(g) for inequalities function H=getH(g) if g<=0, H=0; else H=1; end % Index function for equalities function H=getHeq(geq) if geq==0, H=0; else H=1; end % ----------------- end ------------------------------