基于适应度距离平衡的全局优化问题导向机制的改进粘液-霉菌算法（Matlab代码实现）

欢迎来到本博客❤️❤️

博主优势：博客内容尽量做到思维缜密，逻辑清晰，为了方便读者。

⛳️座右铭：行百里者，半于九十。

本文目录如下：

目录

1 概述

2 运行结果

3 Matlab代码实现

4 参考文献

---

1 概述

在本文中，Slime-Mould-Algorithm（SMA）的性能得到了提高，这是一种当前的元启发式搜索算法。为了在SMA算法中更有效地对搜索过程生命周期过程进行建模，使用适应度-距离平衡（FDB）方法确定了指导搜索过程的候选解决方案。虽然SMA算法的性能被接受，但可以看出，由于应用FDB方法而开发的FDB-SMA算法的性能要好得多。CEC 2020 当前存在基准问题，用于测试开发的 FDB-SMA 算法的性能。从CEC 2020中选取的10个不同的无约束比较问题，将它们按30-50-100个维度排列，进行了设计。使用设计的比较问题进行实验研究，并用Friedman和Wilcoxon统计测试方法进行分析。根据分析结果，已经看到FDB-SMA变体在所有实验研究中都优于基本算法（SMA）。

2 运行结果

部分代码：

% Max_iter: maximum iterations, N: populatoin size, Convergence_curve: Convergence curve
% To run SMA: [Destination_fitness,bestPositions,Convergence_curve]=SMA(N,Max_iter,lb,ub,dim,fobj)
%function [Destination_fitness,bestPositions,Convergence_curve]=sma(N,Max_iter,lb,ub,dim,fobj)

function[] = FDB_sma_case_1()
disp('SMA is now tackling your problem')
[N,dim,Max_iter ,lb,ub]=problem_terminate();

%fhd=cec20so;

% initialize position
bestPositions=zeros(1,dim);
Destination_fitness=inf;%change this to -inf for maximization problems
AllFitness = inf*ones(N,1);%record the fitness of all slime mold
weight = ones(N,dim);%fitness weight of each slime mold
%Initialize the set of random solutions
X=initialization(N,dim,ub,lb);
Convergence_curve=zeros(1,Max_iter);
it=1;  %Number of iterations
lb=ones(1,dim).*lb; % lower boundary 
ub=ones(1,dim).*ub; % upper boundary
z=0.03; % parameter

% Main loop
while  it <= Max_iter
    disp(it)
    fdbindex = fitnessDistanceBalance( X, Destination_fitness );
    
    %sort the fitness
    for i=1:N
        % Check if solutions go outside the search space and bring them back
        Flag4ub=X(i,:)>ub;
        Flag4lb=X(i,:)         
        X(i,:)=(X(i,:).*(~(Flag4ub+Flag4lb)))+ub.*Flag4ub+lb.*Flag4lb;
        %AllFitness(i) = fobj(X(i,:));
        AllFitness(i)=problem( X(i,:)' );
            it=it+1;
    end
    
    [SmellOrder,SmellIndex] = sort(AllFitness);  %Eq.(2.6)
    worstFitness = SmellOrder(N);
    bestFitness = SmellOrder(1);

    S=bestFitness-worstFitness+eps;  % plus eps to avoid denominator zero

    %calculate the fitness weight of each slime mold
    for i=1:N
        for j=1:dim
            if i<=(N/2)  %Eq.(2.5)
                weight(SmellIndex(i),j) = 1+rand()*log10((bestFitness-SmellOrder(i))/(S)+1);%fdb
            else
                weight(SmellIndex(i),j) = 1-rand()*log10((bestFitness-SmellOrder(i))/(S)+1);%fdb
            end
        end
    end
    
    %update the best fitness value and best position
    if bestFitness < Destination_fitness
        bestPositions=X(SmellIndex(1),:);
        Destination_fitness = bestFitness;
    end
    
    a = atanh(-(it/Max_iter)+1);   %Eq.(2.4)
    b = 1-it/Max_iter;
    % Update the Position of search agents
    for i=1:N
        if rand             X(i,:) = (ub-lb)*rand+lb;
        else
           if(rand<0.5)
            p =tanh(abs(AllFitness(fdbindex)-Destination_fitness));  %Eq.(2.2)%fdb
           else
            p =tanh(abs(AllFitness(i)-Destination_fitness));  %Eq.(2.2)%fdb   
           end
            vb = unifrnd(-a,a,1,dim);  %Eq.(2.3)
            vc = unifrnd(-b,b,1,dim);
            for j=1:dim
                r = rand();
                A = randi([1,N]);  % two positions randomly selected from population
                B = randi([1,N]);
                if r

                   if(rand<0.5)
                    X(i,j) = bestPositions(j)+ vb(j)*(weight( fdbindex,j)*X(fdbindex,j)-X(fdbindex,j));%fdb
                   else
                    X(i,j) = bestPositions(j)+ vb(j)*(weight( i,j)*X(A,j)-X(B,j));%fdb
                   end
                else
                    
                    X(i,j) = vc(j)*X(fdbindex,j);%fdb
                   
                end
            end
        end
    end
    Convergence_curve(it)=Destination_fitness;
    %it=it+1;
end

bestSolution=bestPositions;
bestFitness= Destination_fitness;
iteration=it;
disp(it)
end

function Positions=initialization(SearchAgents_no,dim,ub,lb)

Boundary_no= size(ub,2); % numnber of boundaries

% If the boundaries of all variables are equal and user enter a signle
% number for both ub and lb
if Boundary_no==1
    Positions=rand(SearchAgents_no,dim).*(ub-lb)+lb;
end

% If each variable has a different lb and ub
if Boundary_no>1
    for i=1:dim
        ub_i=ub(i);
        lb_i=lb(i);
        Positions(:,i)=rand(SearchAgents_no,1).*(ub_i-lb_i)+lb_i;
    end
end
end
 

3 Matlab代码实现

4 参考文献

部分理论来源于网络，如有侵权请联系删除。

[1]SUİÇMEZ, Ç., KAHRAMAN, H., YILMAZ, C., IŞIK, M. F., & CENGİZ, E. Improved Slime-Mould-Algorithm with Fitness Distance Balance-based Guiding Mechanism for Global Optimization Problems. Duzce University Journal of Science and Technology, 9(6), 40-54.