error it cant find my zdt1, can you fix it: clc; clear; close all; % Multi-objective…
- User
error it cant find my zdt1, can you fix it: clc; clear; close all;
% Multi-objective function selector MultiObjFnc = 'ZDT1'; % Change this to use different functions MultiObj = struct(); % Initialize MultiObj structure
switch MultiObjFnc case 'Schaffer' MultiObj.fun = @(x) [x(:).^2, (x(:)-2).^2]; MultiObj.nVar = 1; MultiObj.var_min = -5; MultiObj.var_max = 5; load('Schaffer.mat'); MultiObj.truePF = PF; case 'Kursawe' MultiObj.fun = @(x) [-10.(exp(-0.2.sqrt(x(:,1).^2+x(:,2).^2)) + exp(-0.2.sqrt(x(:,2).^2+x(:,3).^2))), ... sum(abs(x).^0.8 + 5.sin(x.^3),2)]; MultiObj.nVar = 3; MultiObj.var_min = -5.ones(1,MultiObj.nVar); MultiObj.var_max = 5.ones(1,MultiObj.nVar); load('Kursawe.mat'); MultiObj.truePF = PF; case 'Poloni' A1 = 0.5sin(1)-2cos(1)+sin(2)-1.5cos(2); A2 = 1.5sin(1)-cos(1)+2sin(2)-0.5cos(2); B1 = @(x,y) 0.5.*sin(x)-2.*cos(x)+sin(y)-1.5.cos(y); B2 = @(x,y) 1.5.sin(x)-cos(x)+2.sin(y)-0.5.cos(y); f1 = @(x,y) 1+(A1-B1(x,y)).^2+(A2-B2(x,y)).^2; f2 = @(x,y) (x+3).^2+(y+1).^2; MultiObj.fun = @(x) [f1(x(:,1),x(:,2)), f2(x(:,1),x(:,2))]; MultiObj.nVar = 2; MultiObj.var_min = -pi.ones(1,MultiObj.nVar); MultiObj.var_max = pi.ones(1,MultiObj.nVar); case 'Viennet2' f1 = @(x,y) 0.5.(x-2).^2+(1/13).(y+1).^2+3; f2 = @(x,y) (1/36).(x+y-3).^2+(1/8).(-x+y+2).^2-17; f3 = @(x,y) (1/175).(x+2.y-1).^2+(1/17).(2.y-x).^2-13; MultiObj.fun = @(x) [f1(x(:,1),x(:,2)), f2(x(:,1),x(:,2)), f3(x(:,1),x(:,2))]; MultiObj.nVar = 2; MultiObj.var_min = [-4, -4]; MultiObj.var_max = [4, 4]; load('Viennet2.mat'); MultiObj.truePF = PF; case 'Viennet3' f1 = @(x,y) 0.5.(x.^2+y.^2)+sin(x.^2+y.^2); f2 = @(x,y) (1/8).(3.*x-2.y+4).^2 + (1/27).(x-y+1).^2 +15; f3 = @(x,y) (1./(x.^2+y.^2+1))-1.1.*exp(-(x.^2+y.^2)); MultiObj.fun = @(x) [f1(x(:,1),x(:,2)), f2(x(:,1),x(:,2)), f3(x(:,1),x(:,2))]; MultiObj.nVar = 2; MultiObj.var_min = [-3, -10]; MultiObj.var_max = [10, 3]; load('Viennet3.mat'); MultiObj.truePF = PF; case 'ZDT1' g = @(x) 1+9.sum(x(:,2:end),2)./(size(x,2)-1); MultiObj.fun = @(x) [x(:,1), g(x).(1-sqrt(x(:,1)./g(x)))]; MultiObj.nVar = 30; MultiObj.var_min = zeros(1,MultiObj.nVar); MultiObj.var_max = ones(1,MultiObj.nVar); load('ZDT1.mat'); MultiObj.truePF = PF; case 'ZDT2' f = @(x) x(:,1); g = @(x) 1+9.*sum(x(:,2:end),2)./(size(x,2)-1); h = @(x) 1-(f(x)./g(x)).^2; MultiObj.fun = @(x) [f(x), g(x).*h(x)]; MultiObj.nVar = 30; MultiObj.var_min = zeros(1,MultiObj.nVar); MultiObj.var_max = ones(1,MultiObj.nVar); load('ZDT2.mat'); MultiObj.truePF = PF; case 'ZDT3' f = @(x) x(:,1); g = @(x) 1+(9/size(x,2)-1).*sum(x(:,2:end),2); h = @(x) 1 - sqrt(f(x)./g(x)) - (f(x)./g(x)).*sin(10.*pi.*f(x)); MultiObj.fun = @(x) [f(x), g(x).*h(x)]; MultiObj.nVar = 30; MultiObj.var_min = 0.*ones(1,MultiObj.nVar); MultiObj.var_max = 1.*ones(1,MultiObj.nVar); load('ZDT3.mat'); MultiObj.truePF = PF; case 'ZDT6' f = @(x) 1 - exp(-4.*x(:,1)).*sin(6.*pi.x(:,1)); g = @(x) 1 + 9.(sum(x(:,2:end),2)./(size(x,2)-1)).^0.25; h = @(x) 1 - (f(x)./g(x)).^2; MultiObj.fun = @(x) [f(x), g(x).*h(x)]; MultiObj.nVar = 10; MultiObj.var_min = 0.*ones(1,MultiObj.nVar); MultiObj.var_max = 1.*ones(1,MultiObj.nVar); load('ZDT6.mat'); MultiObj.truePF = PF; end
% Set problem parameters NPop = 50; % Population size T = 50; % Number of iterations dim = MultiObj.nVar; lb = MultiObj.var_min; ub = MultiObj.var_max;
% Run MOEMA with user-defined FITNESSFCN [paretoFront, paretoSet, Trajectories, fitness_history, position_history] = MOEMA(NPop, T, lb, ub, dim, MultiObj.fun);
% Plot the Pareto front figure; plot(paretoFront(:,1), paretoFront(:,2), 'ro'); xlabel('f1'); ylabel('f2'); title(['Pareto Front for ', MultiObjFnc, ' using MOEMA']);
% Calculate and display metrics disp(['Number of solutions in Pareto Front: ', num2str(size(paretoFront, 1))]); disp(['Minimum f1: ', num2str(min(paretoFront(:,1)))]); disp(['Minimum f2: ', num2str(min(paretoFront(:,2)))]);
function [paretoFront, paretoSet, Trajectories, fitness_history, position_history] = MOEMA(NPop, T, lb, ub, dim, FITNESSFCN) % Multi-Objective Evolutionary Mating Algorithm (MOEMA) % MOEMA attempts to solve multi-objective problems of the following form: % min F(X) = [f1(X), f2(X), ..., fm(X)] subject to: lb <= X <= ub %
% FITNESSFCN - function handle of the multi-objective fitness function % lb - lower bounds on X % ub - upper bounds on X % T - number of iterations % NPop - size of the population (class size)
% paretoFront - set of non-dominated solutions in objective space % paretoSet - set of non-dominated solutions in decision space % Trajectories - best solution trajectory over iterations % fitness_history - history of fitness values % position_history - history of population positions% Preallocation fitness_history = zeros(NPop, T, 2); % Assuming 2 objectives position_history = zeros(NPop, T, dim); Trajectories = zeros(dim, T);
% Generation of initial population pop = initialization(NPop, dim, ub, lb); pop_dad = pop(1:NPop/2, :); % Eqn (1) in the paper pop_mum = pop(NPop/2+1:end, :); % Eqn (2) in the paper
% Evaluation of objective function for initialization obj_dad = evaluate_population(pop_dad, FITNESSFCN); obj_mum = evaluate_population(pop_mum, FITNESSFCN); obj = [obj_dad; obj_mum];
% Initialize archive with non-dominated solutions archive = update_archive([], [], pop, obj);
for gen = 1:T % Start iteration k1 = randperm(NPop/2); k2 = randperm(NPop/2); k1x = pop_dad(k1, :); k2x = pop_mum(k2, :);
for k = 1:NPop/2 % Mating process Imates = 1 + (var(k1x(k, :)) - var(k2x(k, :))); % Eqn (4) in the paper p = randn(1, dim); % Eqn (6) in the paper r = rand(); if Imates >= 0 % Upper part of Eqn (5) in the paper temp1 = p .* k1x(k, :); temp2 = (1-p) .* k2x(k, :); pop_child = temp1 + temp2; else % Lower part of Eqn (5) in the paper temp1 = p .* k2x(k, :); temp2 = (1-p) .* k1x(k, :); pop_child = temp1 + temp2; end % Impact of best environment (using random non-dominated solution) if ~isempty(archive.pop) best_pop = archive.pop(randi(size(archive.pop, 1)), :); K = rand(1, dim) < 0.8; % Eqn (8) in the paper pop_child = best_pop .* (1-K) + pop_child .* K; % Eqn (7) in the paper end % Bounding of the solution pop_child = max(min(ub, pop_child), lb); % Evaluate child obj_child = FITNESSFCN(pop_child); % Update population using non-dominated sorting [pop_dad, obj_dad] = update_population(pop_dad, obj_dad, pop_child, obj_child, k1(k)); [pop_mum, obj_mum] = update_population(pop_mum, obj_mum, pop_child, obj_child, k2(k)); % Exploration process if r < 0.2 if ~isempty(archive.pop) temp1 = archive.pop(randi(size(archive.pop, 1)), :); pop_child = rand(1, dim) .* temp1; % Eqn (9) in the paper pop_child = max(min(ub, pop_child), lb); obj_child = FITNESSFCN(pop_child); % Update population using non-dominated sorting [pop_dad, obj_dad] = update_population(pop_dad, obj_dad, pop_child, obj_child, randi(NPop/2)); [pop_mum, obj_mum] = update_population(pop_mum, obj_mum, pop_child, obj_child, randi(NPop/2)); end end end % Combine updated pool dad and mum pop = [pop_dad; pop_mum]; obj = [obj_dad; obj_mum]; % Update archive archive = update_archive(archive.pop, archive.obj, pop, obj); % Record the history at each iteration fitness_history(:, gen, :) = obj; position_history(:, gen, :) = pop; % Update Trajectories (using a random non-dominated solution) if ~isempty(archive.pop) Trajectories(:, gen) = archive.pop(randi(size(archive.pop, 1)), :)'; end disp(['Iteration #', num2str(gen), ' completed. Archive size: ', num2str(size(archive.pop, 1))]);end
% Return Pareto front and Pareto set paretoFront = archive.obj; paretoSet = archive.pop;
end
% Helper Functions
function pop = initialization(NPop, dim, ub, lb) pop = rand(NPop, dim) .* (ub - lb) + lb; end
function obj = evaluate_population(pop, FITNESSFCN) obj = zeros(size(pop, 1), 2); % Assuming 2 objectives for i = 1:size(pop, 1) obj(i, :) = FITNESSFCN(pop(i, :)); end end
function [pop, obj] = update_population(pop, obj, child, child_obj, index) if dominates(child_obj, obj(index, :)) pop(index, :) = child; obj(index, :) = child_obj; elseif ~dominates(obj(index, :), child_obj) if rand() < 0.5 pop(index, :) = child; obj(index, :) = child_obj; end end end
function archive = update_archive(archive_pop, archive_obj, pop, obj) combined_pop = [archive_pop; pop]; combined_obj = [archive_obj; obj];
[is_dominated, ~] = pareto_dominance(combined_obj); non_dominated = ~is_dominated; archive.pop = combined_pop(non_dominated, :); archive.obj = combined_obj(non_dominated, :);end
function [is_dominated, domination_count] = pareto_dominance(objectives) [n_solutions, n_objectives] = size(objectives); is_dominated = false(n_solutions, 1); domination_count = zeros(n_solutions, 1);
for i = 1:n_solutions for j = i+1:n_solutions if dominates(objectives(i, :), objectives(j, :)) is_dominated(j) = true; domination_count(i) = domination_count(i) + 1; elseif dominates(objectives(j, :), objectives(i, :)) is_dominated(i) = true; domination_count(j) = domination_count(j) + 1; end end endend
function result = dominates(obj1, obj2) result = all(obj1 <= obj2) && any(obj1 < obj2); end
- Assistant
The error you're encountering indicates that the file
ZDT1.matcannot be found when attempting to load it with theload('ZDT1.mat')command. This file presumably contains the true Pareto front for theZDT1multi-objective test problem.To resolve the issue, consider the following steps:
-
Check for File Existence: Ensure that
ZDT1.matis indeed in the current working directory or in a directory that is part of your MATLAB path. You can use the MATLAB commandexist('ZDT1.mat', 'file')to check if the file is accessible to the script. -
Provide File Location: If
ZDT1.matis located somewhere else, provide the absolute or relative path to the file in theloadcommand, such asload('path/to/ZDT1.mat'). -
Generate the File (if it doesn't exist): If you have the equations to calculate the true Pareto front for the ZDT1 problem, you can generate the data within MATLAB and save it to a
.matfile:% Example code to generate ZDT1 true Pareto front (simplified) x = linspace(0, 1, 100)'; f1 = x; f2 = 1 - sqrt(f1); PF = [f1, f2]; save('ZDT1.mat', 'PF'); -
Remove Dependency on the File: If you do not need the true Pareto front for your current work, you can comment out or remove the
loadstatement and any related code that requiresPF:% load('ZDT1.mat'); % MultiObj.truePF = PF;
After applying one of these solutions, rerun your script to ensure it now executes without issues. If the
ZDT1.matfile is crucial for your analysis and you cannot reconstruct it from scratch, you might need to locate the file or contact the source where you initially obtained your MATLAB code for guidance. -
- User
give me full fixed code
- Assistant
Certainly! Below is the provided code with modifications to handle the absence of the
ZDT1.matfile. In this updated script, I've included code to generate the true Pareto front for theZDT1problem, assuming its shape is known. This adjustment eliminates dependency on an external file:clc; clear; close all; % Multi-objective function selector MultiObjFnc = 'ZDT1'; % Change this to use different functions MultiObj = struct(); % Initialize MultiObj structure switch MultiObjFnc case 'Schaffer' MultiObj.fun = @(x) [x(:).^2, (x(:)-2).^2]; MultiObj.nVar = 1; MultiObj.var_min = -5; MultiObj.var_max = 5; load('Schaffer.mat'); MultiObj.truePF = PF; case 'Kursawe' MultiObj.fun = @(x) [-10.*(exp(-0.2.*sqrt(x(:,1).^2+x(:,2).^2)) + exp(-0.2.*sqrt(x(:,2).^2+x(:,3).^2))), ... sum(abs(x).^0.8 + 5.*sin(x.^3),2)]; MultiObj.nVar = 3; MultiObj.var_min = -5.*ones(1,MultiObj.nVar); MultiObj.var_max = 5.*ones(1,MultiObj.nVar); load('Kursawe.mat'); MultiObj.truePF = PF; case 'Poloni' A1 = 0.5*sin(1)-2*cos(1)+sin(2)-1.5*cos(2); A2 = 1.5*sin(1)-cos(1)+2*sin(2)-0.5*cos(2); B1 = @(x,y) 0.5.*sin(x)-2.*cos(x)+sin(y)-1.5.*cos(y); B2 = @(x,y) 1.5.*sin(x)-cos(x)+2.*sin(y)-0.5.*cos(y); f1 = @(x,y) 1+(A1-B1(x,y)).^2+(A2-B2(x,y)).^2; f2 = @(x,y) (x+3).^2+(y+1).^2; MultiObj.fun = @(x) [f1(x(:,1),x(:,2)), f2(x(:,1),x(:,2))]; MultiObj.nVar = 2; MultiObj.var_min = -pi.*ones(1,MultiObj.nVar); MultiObj.var_max = pi.*ones(1,MultiObj.nVar); case 'Viennet2' f1 = @(x,y) 0.5.*(x-2).^2+(1/13).*(y+1).^2+3; f2 = @(x,y) (1/36).*(x+y-3).^2+(1/8).*(-x+y+2).^2-17; f3 = @(x,y) (1/175).*(x+2.*y-1).^2+(1/17).*(2.*y-x).^2-13; MultiObj.fun = @(x) [f1(x(:,1),x(:,2)), f2(x(:,1),x(:,2)), f3(x(:,1),x(:,2))]; MultiObj.nVar = 2; MultiObj.var_min = [-4, -4]; MultiObj.var_max = [4, 4]; load('Viennet2.mat'); MultiObj.truePF = PF; case 'Viennet3' f1 = @(x,y) 0.5.*(x.^2+y.^2)+sin(x.^2+y.^2); f2 = @(x,y) (1/8).*(3.*x-2.*y+4).^2 + (1/27).*(x-y+1).^2 +15; f3 = @(x,y) (1./(x.^2+y.^2+1))-1.1.*exp(-(x.^2+y.^2)); MultiObj.fun = @(x) [f1(x(:,1),x(:,2)), f2(x(:,1),x(:,2)), f3(x(:,1),x(:,2))]; MultiObj.nVar = 2; MultiObj.var_min = [-3, -10]; MultiObj.var_max = [10, 3]; load('Viennet3.mat'); MultiObj.truePF = PF; case 'ZDT1' g = @(x) 1+9.*sum(x(:,2:end),2)./(size(x,2)-1); MultiObj.fun = @(x) [x(:,1), g(x).*(1-sqrt(x(:,1)./g(x)))]; MultiObj.nVar = 30; MultiObj.var_min = zeros(1,MultiObj.nVar); MultiObj.var_max = ones(1,MultiObj.nVar); % Generate the true Pareto front x = linspace(0, 1, 100)'; f1 = x; f2 = 1 - sqrt(f1); MultiObj.truePF = [f1, f2]; case 'ZDT2' f = @(x) x(:,1); g = @(x) 1+9.*sum(x(:,2:end),2)./(size(x,2)-1); h = @(x) 1-(f(x)./g(x)).^2; MultiObj.fun = @(x) [f(x), g(x).*h(x)]; MultiObj.nVar = 30; MultiObj.var_min = zeros(1,MultiObj.nVar); MultiObj.var_max = ones(1,MultiObj.nVar); load('ZDT2.mat'); MultiObj.truePF = PF; case 'ZDT3' f = @(x) x(:,1); g = @(x) 1+(9/size(x,2)-1).*sum(x(:,2:end),2); h = @(x) 1 - sqrt(f(x)./g(x)) - (f(x)./g(x)).*sin(10.*pi.*f(x)); MultiObj.fun = @(x) [f(x), g(x).*h(x)]; MultiObj.nVar = 30; MultiObj.var_min = 0.*ones(1,MultiObj.nVar); MultiObj.var_max = 1.*ones(1,MultiObj.nVar); load('ZDT3.mat'); MultiObj.truePF = PF; case 'ZDT6' f = @(x) 1 - exp(-4.*x(:,1)).*sin(6.*pi.*x(:,1)); g = @(x) 1 + 9.*(sum(x(:,2:end),2)./(size(x,2)-1)).^0.25; h = @(x) 1 - (f(x)./g(x)).^2; MultiObj.fun = @(x) [f(x), g(x).*h(x)]; MultiObj.nVar = 10; MultiObj.var_min = 0.*ones(1,MultiObj.nVar); MultiObj.var_max = 1.*ones(1,MultiObj.nVar); load('ZDT6.mat'); MultiObj.truePF = PF; end % Set problem parameters NPop = 50; % Population size T = 50; % Number of iterations dim = MultiObj.nVar; lb = MultiObj.var_min; ub = MultiObj.var_max; % Run MOEMA with user-defined FITNESSFCN [paretoFront, paretoSet, Trajectories, fitness_history, position_history] = MOEMA(NPop, T, lb, ub, dim, MultiObj.fun); % Plot the Pareto front figure; plot(paretoFront(:,1), paretoFront(:,2), 'ro'); xlabel('f1'); ylabel('f2'); title(['Pareto Front for ', MultiObjFnc, ' using MOEMA']); % Calculate and display metrics disp(['Number of solutions in Pareto Front: ', num2str(size(paretoFront, 1))]); disp(['Minimum f1: ', num2str(min(paretoFront(:,1)))]); disp(['Minimum f2: ', num2str(min(paretoFront(:,2)))]); function [paretoFront, paretoSet, Trajectories, fitness_history, position_history] = MOEMA(NPop, T, lb, ub, dim, FITNESSFCN) % Multi-Objective Evolutionary Mating Algorithm (MOEMA) % MOEMA attempts to solve multi-objective problems of the following form: % min F(X) = [f1(X), f2(X), ..., fm(X)] subject to: lb <= X <= ub % % FITNESSFCN - function handle of the multi-objective fitness function % lb - lower bounds on X % ub - upper bounds on X % T - number of iterations % NPop - size of the population (class size) % paretoFront - set of non-dominated solutions in objective space % paretoSet - set of non-dominated solutions in decision space % Trajectories - best solution trajectory over iterations % fitness_history - history of fitness values % position_history - history of population positions % Preallocation fitness_history = zeros(NPop, T, 2); % Assuming 2 objectives position_history = zeros(NPop, T, dim); Trajectories = zeros(dim, T); % Generation of initial population pop = initialization(NPop, dim, ub, lb); pop_dad = pop(1:NPop/2, :); % Eqn (1) in the paper pop_mum = pop(NPop/2+1:end, :); % Eqn (2) in the paper % Evaluation of objective function for initialization obj_dad = evaluate_population(pop_dad, FITNESSFCN); obj_mum = evaluate_population(pop_mum, FITNESSFCN); obj = [obj_dad; obj_mum]; % Initialize archive with non-dominated solutions archive = update_archive([], [], pop, obj); for gen = 1:T % Start iteration k1 = randperm(NPop/2); k2 = randperm(NPop/2); k1x = pop_dad(k1, :); k2x = pop_mum(k2, :); for k = 1:NPop/2 % Mating process Imates = 1 + (var(k1x(k, :)) - var(k2x(k, :))); % Eqn (4) in the paper p = randn(1, dim); % Eqn (6) in the paper r = rand(); if Imates >= 0 % Upper part of Eqn (5) in the paper temp1 = p .* k1x(k, :); temp2 = (1-p) .* k2x(k, :); pop_child = temp1 + temp2; else % Lower part of Eqn (5) in the paper temp1 = p .* k2x(k, :); temp2 = (1-p) .* k1x(k, :); pop_child = temp1 + temp2; end % Impact of best environment (using random non-dominated solution) if ~isempty(archive.pop) best_pop = archive.pop(randi(size(archive.pop, 1)), :); K = rand(1, dim) < 0.8; % Eqn (8) in the paper pop_child = best_pop .* (1-K) + pop_child .* K; % Eqn (7) in the paper end % Bounding of the solution pop_child = max(min(ub, pop_child), lb); % Evaluate child obj_child = FITNESSFCN(pop_child); % Update population using non-dominated sorting [pop_dad, obj_dad] = update_population(pop_dad, obj_dad, pop_child, obj_child, k1(k)); [pop_mum, obj_mum] = update_population(pop_mum, obj_mum, pop_child, obj_child, k2(k)); % Exploration process if r < 0.2 if ~isempty(archive.pop) temp1 = archive.pop(randi(size(archive.pop, 1)), :); pop_child = rand(1, dim) .* temp1; % Eqn (9) in the paper pop_child = max(min(ub, pop_child), lb); obj_child = FITNESSFCN(pop_child); % Update population using non-dominated sorting [pop_dad, obj_dad] = update_population(pop_dad, obj_dad, pop_child, obj_child, randi(NPop/2)); [pop_mum, obj_mum] = update_population(pop_mum, obj_mum, pop_child, obj_child, randi(NPop/2)); end end end % Combine updated pool dad and mum pop = [pop_dad; pop_mum]; obj = [obj_dad; obj_mum]; % Update archive archive = update_archive(archive.pop, archive.obj, pop, obj); % Record the history at each iteration fitness_history(:, gen, :) = obj; position_history(:, gen, :) = pop; % Update Trajectories (using a random non-dominated solution) if ~isempty(archive.pop) Trajectories(:, gen) = archive.pop(randi(size(archive.pop, 1)), :)'; end disp(['Iteration #', num2str(gen), ' completed. Archive size: ', num2str(size(archive.pop, 1))]); end % Return Pareto front and Pareto set paretoFront = archive.obj; paretoSet = archive.pop; end % Helper Functions function pop = initialization(NPop, dim, ub, lb) pop = rand(NPop, dim) .* (ub - lb) + lb; end function obj = evaluate_population(pop, FITNESSFCN) obj = zeros(size(pop, 1), 2); % Assuming 2 objectives for i = 1:size(pop, 1) obj(i, :) = FITNESSFCN(pop(i, :)); end end function [pop, obj] = update_population(pop, obj, child, child_obj, index) if dominates(child_obj, obj(index, :)) pop(index, :) = child; obj(index, :) = child_obj; elseif ~dominates(obj(index, :), child_obj) if rand() < 0.5 pop(index, :) = child; obj(index, :) = child_obj; end end end function archive = update_archive(archive_pop, archive_obj, pop, obj) combined_pop = [archive_pop; pop]; combined_obj = [archive_obj; obj]; [is_dominated, ~] = pareto_dominance(combined_obj); non_dominated = ~is_dominated; archive.pop = combined_pop(non_dominated, :); archive.obj = combined_obj(non_dominated, :); end function [is_dominated, domination_count] = pareto_dominance(objectives) [n_solutions, n_objectives] = size(objectives); is_dominated = false(n_solutions, 1); domination_count = zeros(n_solutions, 1); for i = 1:n_solutions for j = i+1:n_solutions if dominates(objectives(i, :), objectives(j, :)) is_dominated(j) = true; domination_count(i) = domination_count(i) + 1; elseif dominates(objectives(j, :), objectives(i, :)) is_dominated(i) = true; domination_count(j) = domination_count(j) + 1; end end end end function result = dominates(obj1, obj2) result = all(obj1 <= obj2) && any(obj1 < obj2); endKey Changes Made:
- Added code to generate the true Pareto front for
ZDT1directly within the script. - Removed the dependency on loading the
ZDT1.matfile by calculatingMultiObj.truePFusing the known characteristics of theZDT1problem.
This script should now run without the need for separate data files, assuming that the structure of the
ZDT1true Pareto front is sufficient for your purposes. - Added code to generate the true Pareto front for
- User
how to change to zdt2
- Assistant
To switch the objective function from
ZDT1toZDT2, you'll need to update both the function selector (MultiObjFnc) and potentially the code handling for the true Pareto front. Since theZDT2true Pareto front is also a known curve, you can generate it directly within the script.Here's how you can modify the script for
ZDT2:-
Change the Function Selector: Update the
MultiObjFncvariable to'ZDT2'. -
Adjust for
ZDT2: In the switch-case structure, you'll need to modify the case forZDT2to calculate the true Pareto front. The true Pareto front forZDT2is defined byf1running from 0 to 1 andf2is1 - (f1)^2.
Here is the revised part of the script with these changes:
clc; clear; close all; % Multi-objective function selector MultiObjFnc = 'ZDT2'; % Change this to use different functions MultiObj = struct(); % Initialize MultiObj structure switch MultiObjFnc case 'Schaffer' MultiObj.fun = @(x) [x(:).^2, (x(:)-2).^2]; MultiObj.nVar = 1; MultiObj.var_min = -5; MultiObj.var_max = 5; load('Schaffer.mat'); MultiObj.truePF = PF; case 'Kursawe' MultiObj.fun = @(x) [-10.*(exp(-0.2.*sqrt(x(:,1).^2+x(:,2).^2)) + exp(-0.2.*sqrt(x(:,2).^2+x(:,3).^2))), ... sum(abs(x).^0.8 + 5.*sin(x.^3),2)]; MultiObj.nVar = 3; MultiObj.var_min = -5.*ones(1,MultiObj.nVar); MultiObj.var_max = 5.*ones(1,MultiObj.nVar); load('Kursawe.mat'); MultiObj.truePF = PF; case 'Poloni' A1 = 0.5*sin(1)-2*cos(1)+sin(2)-1.5*cos(2); A2 = 1.5*sin(1)-cos(1)+2*sin(2)-0.5*cos(2); B1 = @(x,y) 0.5.*sin(x)-2.*cos(x)+sin(y)-1.5.*cos(y); B2 = @(x,y) 1.5.*sin(x)-cos(x)+2.*sin(y)-0.5.*cos(y); f1 = @(x,y) 1+(A1-B1(x,y)).^2+(A2-B2(x,y)).^2; f2 = @(x,y) (x+3).^2+(y+1).^2; MultiObj.fun = @(x) [f1(x(:,1),x(:,2)), f2(x(:,1),x(:,2))]; MultiObj.nVar = 2; MultiObj.var_min = -pi.*ones(1,MultiObj.nVar); MultiObj.var_max = pi.*ones(1,MultiObj.nVar); case 'Viennet2' f1 = @(x,y) 0.5.*(x-2).^2+(1/13).*(y+1).^2+3; f2 = @(x,y) (1/36).*(x+y-3).^2+(1/8).*(-x+y+2).^2-17; f3 = @(x,y) (1/175).*(x+2.*y-1).^2+(1/17).*(2.*y-x).^2-13; MultiObj.fun = @(x) [f1(x(:,1),x(:,2)), f2(x(:,1),x(:,2)), f3(x(:,1),x(:,2))]; MultiObj.nVar = 2; MultiObj.var_min = [-4, -4]; MultiObj.var_max = [4, 4]; load('Viennet2.mat'); MultiObj.truePF = PF; case 'Viennet3' f1 = @(x,y) 0.5.*(x.^2+y.^2)+sin(x.^2+y.^2); f2 = @(x,y) (1/8).*(3.*x-2.*y+4).^2 + (1/27).*(x-y+1).^2 +15; f3 = @(x,y) (1./(x.^2+y.^2+1))-1.1.*exp(-(x.^2+y.^2)); MultiObj.fun = @(x) [f1(x(:,1),x(:,2)), f2(x(:,1),x(:,2)), f3(x(:,1),x(:,2))]; MultiObj.nVar = 2; MultiObj.var_min = [-3, -10]; MultiObj.var_max = 10, 3]; load('Viennet3.mat'); MultiObj.truePF = PF; case 'ZDT1' g = @(x) 1+9.*sum(x(:,2:end),2)./(size(x,2)-1); MultiObj.fun = @(x) [x(:,1), g(x).*(1-sqrt(x(:,1)./g(x)))]; MultiObj.nVar = 30; MultiObj.var_min = zeros(1,MultiObj.nVar); MultiObj.var_max = ones(1,MultiObj.nVar); % Generate the true Pareto front x = linspace(0, 1, 100)'; f1 = x; f2 = 1 - sqrt(f1); MultiObj.truePF = [f1, f2]; case 'ZDT2' f = @(x) x(:,1); g = @(x) 1+9.*sum(x(:,2:end),2)./(size(x,2)-1); h = @(x) 1-(f(x)./g(x)).^2; MultiObj.fun = @(x) [f(x), g(x).*h(x)]; MultiObj.nVar = 30; MultiObj.var_min = zeros(1,MultiObj.nVar); MultiObj.var_max = ones(1,MultiObj.nVar); % Generate the true Pareto front x = linspace(0, 1, 100)'; f1 = x; f2 = 1 - f1.^2; MultiObj.truePF = [f1, f2]; case 'ZDT3' f = @(x) x(:,1); g = @(x) 1+(9/size(x,2)-1).*sum(x(:,2:end),2); h = @(x) 1 - sqrt(f(x)./g(x)) - (f(x)./g(x)).*sin(10.*pi.*f(x)); MultiObj.fun = @(x) [f(x), g(x).*h(x)]; MultiObj.nVar = 30; MultiObj.var_min = 0.*ones(1,MultiObj.nVar); MultiObj.var_max = 1.*ones(1,MultiObj.nVar); load('ZDT3.mat'); MultiObj.truePF = PF; case 'ZDT6' f = @(x) 1 - exp(-4.*x(:,1)).*sin(6.*pi.*x(:,1)); g = @(x) 1 + 9.*(sum(x(:,2:end),2)./(size(x,2)-1)).^0.25; h = @(x) 1 - (f(x)./g(x)).^2; MultiObj.fun = @(x) [f(x), g(x).*h(x)]; MultiObj.nVar = 10; MultiObj.var_min = 0.*ones(1,MultiObj.nVar); MultiObj.var_max = 1.*ones(1,MultiObj.nVar); load('ZDT6.mat'); MultiObj.truePF = PF; end % Set problem parameters NPop = 50; % Population size T = 50; % Number of iterations dim = MultiObj.nVar; lb = MultiObj.var_min; ub = MultiObj.var_max; % Run MOEMA with user-defined FITNESSFCN [paretoFront, paretoSet, Trajectories, fitness_history, position_history] = MOEMA(NPop, T, lb, ub, dim, MultiObj.fun); % Plot the Pareto front figure; plot(paretoFront(:,1), paretoFront(:,2), 'ro'); xlabel('f1'); ylabel('f2'); title(['Pareto Front for ', MultiObjFnc, ' using MOEMA']); % Calculate and display metrics disp(['Number of solutions in Pareto Front: ', num2str(size(paretoFront, 1))]); disp(['Minimum f1: ', num2str(min(paretoFront(:,1)))]); disp(['Minimum f2: ', num2str(min(paretoFront(:,2)))]); function [paretoFront, paretoSet, Trajectories, fitness_history, position_history] = MOEMA(NPop, T, lb, ub, dim, FITNESSFCN) % Multi-Objective Evolutionary Mating Algorithm (MOEMA) % MOEMA attempts to solve multi-objective problems of the following form: % min F(X) = [f1(X), f2(X), ..., fm(X)] subject to: lb <= X <= ub % % FITNESSFCN - function handle of the multi-objective fitness function % lb - lower bounds on X % ub - upper bounds on X % T - number of iterations % NPop - size of the population (class size) % paretoFront - set of non-dominated solutions in objective space % paretoSet - set of non-dominated solutions in decision space % Trajectories - best solution trajectory over iterations % fitness_history - history of fitness values % position_history - history of population positions % Preallocation fitness_history = zeros(NPop, T, 2); % Assuming 2 objectives position_history = zeros(NPop, T, dim); Trajectories = zeros(dim, T); % Generation of initial population pop = initialization(NPop, dim, ub, lb); pop_dad = pop(1:NPop/2, :); % Eqn (1) in the paper pop_mum = pop(NPop/2+1:end, :); % Eqn (2) in the paper % Evaluation of objective function for initialization obj_dad = evaluate_population(pop_dad, FITNESSFCN); obj_mum = evaluate_population(pop_mum, FITNESSFCN); obj = [obj_dad; obj_mum]; % Initialize archive with non-dominated solutions archive = update_archive([], [], pop, obj); for gen = 1:T % Start iteration k1 = randperm(NPop/2); k2 = randperm(NPop/2); k1x = pop_dad(k1, :); k2x = pop_mum(k2, :); for k = 1:NPop/2 % Mating process Imates = 1 + (var(k1x(k, :)) - var(k2x(k, :))); % Eqn (4) in the paper p = randn(1, dim); % Eqn (6) in the paper r = rand(); if Imates >= 0 % Upper part of Eqn (5) in the paper temp1 = p .* k1x(k, :); temp2 = (1-p) .* k2x(k, :); pop_child = temp1 + temp2; else % Lower part of Eqn (5) in the paper temp1 = p .* k2x(k, :); temp2 = (1-p) .* k1x(k, :); pop_child = temp1 + temp2; end % Impact of best environment (using random non-dominated solution) if ~isempty(archive.pop) best_pop = archive.pop(randi(size(archive.pop, 1)), :); K = rand(1, dim) < 0.8; % Eqn (8) in the paper pop_child = best_pop .* (1-K) + pop_child .* K; % Eqn (7) in the paper end % Bounding of the solution pop_child = max(min(ub, pop_child), lb); % Evaluate child obj_child = FITNESSFCN(pop_child); % Update population using non-dominated sorting [pop_dad, obj_dad] = update_population(pop_dad, obj_dad, pop_child, obj_child, k1(k)); [pop_mum, obj_mum] = update_population(pop_mum, obj_mum, pop_child, obj_child, k2(k)); % Exploration process if r < 0.2 if ~isempty(archive.pop) temp1 = archive.pop(randi(size(archive.pop, 1)), :); pop_child = rand(1, dim) .* temp1; % Eqn (9) in the paper pop_child = max(min(ub, pop_child), lb); obj_child = FITNESSFCN(pop_child); % Update population using non-dominated sorting [pop_dad, obj_dad] = update_population(pop_dad, obj_dad, pop_child, obj_child, randi(NPop/2)); [pop_mum, obj_mum] = update_population(pop_mum, obj_mum, pop_child, obj_child, randi(NPop/2)); end end end % Combine updated pool dad and mum pop = [pop_dad; pop_mum]; obj = [obj_dad; obj_mum]; % Update archive archive = update_archive(archive.pop, archive.obj, pop, obj); % Record the history at each iteration fitness_history(:, gen, :) = obj; position_history(:, gen, :) = pop; % Update Trajectories (using a random non-dominated solution) if ~isempty(archive.pop) Trajectories(:, gen) = archive.pop(randi(size(archive.pop, 1)), :)'; end disp(['Iteration #', num2str(gen), ' completed. Archive size: ', num2str(size(archive.pop, 1))]); end % Return Pareto front and Pareto set paretoFront = archive.obj; paretoSet = archive.pop; end % Helper Functions function pop = initialization(NPop, dim, ub, lb) pop = rand(NPop, dim) .* (ub - lb) + lb; end function obj = evaluate_population(pop, FITNESSFCN) obj = zeros(size(pop, 1), 2); % Assuming 2 objectives for i = 1:size(pop, 1) obj(i, :) = FITNESSFCN(pop(i, :)); end end function [pop, obj] = update_population(pop, obj, child, child_obj, index) if dominates(child_obj, obj(index, :)) pop(index, :) = child; obj(index, :) = child_obj; elseif ~dominates(obj(index, :), child_obj) if rand() < 0.5 pop(index, :) = child; obj(index, :) = child_obj; end end end function archive = update_archive(archive_pop, archive_obj, pop, obj) combined_pop = [archive_pop; pop]; combined_obj = [archive_obj; obj]; [is_dominated, ~] = pareto_dominance(combined_obj); non_dominated = ~is_dominated; archive.pop = combined_pop(non_dominated, :); archive.obj = combined_obj(non_dominated, :); end function [is_dominated, domination_count] = pareto_dominance(objectives) [n_solutions, n_objectives] = size(objectives); is_dominated = false(n_solutions, 1); domination_count = zeros(n_solutions, 1); for i = 1:n_solutions for j = i+1:n_solutions if dominates(objectives(i, :), objectives(j, :)) is_dominated(j) = true; domination_count(i) = domination_count(i) + 1; elseif dominates(objectives(j, :), objectives(i, :)) is_dominated(i) = true; domination_count(j) = domination_count(j) + 1; end end end end function result = dominates(obj1, obj2) result = all(obj1 <= obj2) && any(obj1 < obj2); endKey Changes for
ZDT2:- Function Definition for
ZDT2: The main difference in the objective functionh(x)is set to1 - (f1/g)^2. - Generated Pareto Front for
ZDT2: The script now generates an estimated Pareto front forZDT2directly, withf2as1 - (f1)^2, which represents the typical Pareto front for this problem. - Updated
MultiObjFncto'ZDT2': This switch ensures that the right function is chosen in theswitchstatement.
Ensure this script meets your specific requirements for evaluating the
ZDT2problem, including parameters and any other specific constraints you may have in your context. -
- User
why i can only try on zdt1 and zdt2
- Assistant
The script you've provided includes definitions for several multi-objective test functions (Schaffer, Kursawe, Poloni, Viennet2, Viennet3, ZDT1, ZDT2, ZDT3, and ZDT6). To try different problems, you can modify the
MultiObjFncvariable at the beginning of your script to any of these predefined cases by setting it to the desired test problem. For instance, you can set it to'Schaffer','Kursawe','Poloni','Viennet2','Viennet3','ZDT3', or'ZDT6'.Here's how you can run the script for different functions by changing the selector:
% Multi-objective function selector MultiObjFnc = 'Kursawe'; % Change this to use different functionsInstructions for Trying Other Test Problems:
-
Select a Test Problem: Change the
MultiObjFncvariable to any of the following problem names:'Schaffer''Kursawe''Poloni''Viennet2''Viennet3''ZDT3''ZDT6'
-
Understand the Test Problem Definition: Each test problem is defined within a
caseblock in theswitchstatement. The objective functions and variable bounds for each problem are specified there. -
Generate True Pareto Front (If Required): For some problems, you may need an external
.matfile for the true Pareto front (PF). Ensure that the required file exists or modify the code to generate the Pareto front if known analytically (as demonstrated forZDT1andZDT2). -
Run the Script: With the appropriate
MultiObjFncset, run the script, and it will execute the MOEMA algorithm for the selected test problem, providing the Pareto front and related outputs.
Example:
To run the script with the
Kursaweproblem, change the selector as follows:% Multi-objective function selector MultiObjFnc = 'Kursawe'; % Switch to the Kursawe test problemAfter selecting a test problem, ensure that your MATLAB environment is properly set up with any additional data files needed or adjust the script to handle functions without the need for external data files.
-