Add files via upload

Main.m

@@ -1,44 +1,45 @@
-%-------------------------------------------------------------------------%
-%  Binary Differential Evolution (BDE) source codes demo version          %
-%                                                                         %
-%  Programmer: Jingwei Too                                                %
-%                                                                         %
-%  E-Mail: jamesjames868@gmail.com                                        %
-%-------------------------------------------------------------------------%
-
-
-%---Input------------------------------------------------------------------
-% feat:  feature vector (instances x features)
-% label: labelling
-% N:     Number of vectors
-% T:     Maximum number of generations
-% CR:    Crossover rate
-%---Output-----------------------------------------------------------------
-% sFeat: Selected features (instances x features)
-% Sf:    Selected feature index
-% Nf:    Number of selected features
-% curve: Convergence curve
-%--------------------------------------------------------------------------
+%-------------------------------------------------------------------%
+%  Binary Differential Evolution (BDE) demo version                 %
+%-------------------------------------------------------------------%
+
+
+%---Input------------------------------------------------------------
+% feat     : feature vector (instances x features)
+% label    : label vector (instances x 1)
+% N        : Number of solutions
+% max_Iter : Maximum number of iterations
+% CR       : Crossover rate
+
+%---Output-----------------------------------------------------------
+% sFeat    : Selected features (instances x features)
+% Sf       : Selected feature index
+% Nf       : Number of selected features
+% curve    : Convergence curve
+%--------------------------------------------------------------------
 
 
 %% Binary Differential Evolution
 clc, clear, close 
 % Benchmark data set 
-load ionosphere.mat;
+load ionosphere.mat; 
+
 % Set 20% data as validation set
-ho=0.2; 
+ho = 0.2; 
 % Hold-out method
-HO=cvpartition(label,'HoldOut',ho,'Stratify',false);
+HO = cvpartition(label,'HoldOut',ho,'Stratify',false);
+
 % Parameter setting
-N=10; T=100; CR=0.9;
+N        = 10; 
+max_Iter = 100; 
+CR       = 0.9;
 % Binary Differential Evolution
-[sFeat,Sf,Nf,curve]=jBDE(feat,label,N,T,CR,HO);
-% Plot convergence curve
-figure(); plot(1:T,curve); xlabel('Number of generations');
-ylabel('Fitness Value'); title('BDE'); grid on;
-
-
+[sFeat,Sf,Nf,curve] = jBDE(feat,label,N,max_Iter,CR,HO);
 
+% Plot convergence curve
+plot(1:max_Iter,curve);
+xlabel('Number of generations');
+ylabel('Fitness Value'); 
+title('BDE'); grid on;
 
 
 

jBDE.m

@@ -1,60 +1,76 @@
-function [sFeat,Sf,Nf,curve]=jBDE(feat,label,N,T,CR,HO)
+function [sFeat,Sf,Nf,curve] = jBDE(feat,label,N,max_Iter,CR,HO)
 
-fun=@jFitnessFunction; 
-D=size(feat,2); X=zeros(N,D); 
-for i=1:N
-  for d=1:D
+fun = @jFitnessFunction; 
+dim = size(feat,2); 
+X   = zeros(N,dim); 
+for i = 1:N
+  for d = 1:dim
     if rand() > 0.5
-      X(i,d)=1;
+      X(i,d) = 1;
     end
   end
 end
-fit=zeros(1,N); fitG=inf;
-for i=1:N
-  fit(i)=fun(feat,label,X(i,:),HO); 
+fit  = zeros(1,N);
+fitG = inf;
+for i = 1:N
+  fit(i) = fun(feat,label,X(i,:),HO); 
   if fit(i) < fitG
-    fitG=fit(i); Xgb=X(i,:);
+    fitG = fit(i); 
+    Xgb  = X(i,:);
   end
 end
-curve=inf; Xnew=zeros(N,D); t=1; 
-%---Iterations start-------------------------------------------------------
-while t <= T
-	for i=1:N
-    R=randperm(N); R(R==i)=[];
-    r1=R(1); r2=R(2); r3=R(3);
-    jrand=randi([1,D]); 
-    for d=1:D
-      if X(r1,d)==X(r2,d) 
-        diffV=0;
+MV   = zeros(N,dim);
+Xnew = zeros(N,dim);
+
+curve = inf; 
+t = 1; 
+%---Iterations start--------------------------------------------------
+while t <= max_Iter
+	for i = 1:N
+    R     = randperm(N);  R(R == i) = [];
+    r1    = R(1); 
+    r2    = R(2); 
+    r3    = R(3);
+    for d = 1:dim
+      if X(r1,d) == X(r2,d) 
+        diffV = 0;
       else
-        diffV=X(r1,d); 
+        diffV = X(r1,d); 
       end
-      if diffV==1
-        MV=1;
+      if diffV == 1
+        MV(i,d) = 1;
       else
-        MV=X(r3,d);
+        MV(i,d) = X(r3,d);
       end
-      if d==jrand || rand() <= CR
-        Xnew(i,d)=MV;
+    end
+    jrand = randi([1,dim]); 
+    for d = 1:dim
+      if rand() <= CR  ||  d == jrand 
+        Xnew(i,d) = MV(i,d);
       else
-        Xnew(i,d)=X(i,d);
+        Xnew(i,d) = X(i,d);
       end 
     end
   end
-  for i=1:N
-    Fnew=fun(feat,label,Xnew(i,:),HO);
+  for i = 1:N
+    Fnew = fun(feat,label,Xnew(i,:),HO);
     if Fnew <= fit(i)
-      X(i,:)=Xnew(i,:); fit(i)=Fnew;
+      X(i,:) = Xnew(i,:);
+      fit(i) = Fnew;
     end
     if fit(i) < fitG
-      fitG=fit(i); Xgb=X(i,:);
+      fitG = fit(i); 
+      Xgb  = X(i,:);
     end
   end
-  curve(t)=fitG; 
+  curve(t) = fitG; 
   fprintf('\nIteration %d Best (BDE)= %f',t,curve(t))
-  t=t+1;
+  t = t + 1;
 end
-Pos=1:D; Sf=Pos(Xgb==1); Nf=length(Sf); sFeat=feat(:,Sf);
+Pos   = 1:dim;
+Sf    = Pos(Xgb == 1);
+Nf    = length(Sf);
+sFeat = feat(:,Sf);
 end
 
 

jFitnessFunction.m

@@ -1,27 +1,33 @@
 % Notation: This fitness function is for demonstration 
 
-function fitness=jFitnessFunction(feat,label,X,HO)
-if sum(X==1)==0
-  fitness=1;
+function cost = jFitnessFunction(feat,label,X,HO)
+if sum(X == 1) == 0
+  cost = 1;
 else
-  fitness=jwrapperKNN(feat(:,X==1),label,HO);
+  cost = jwrapperKNN(feat(:, X == 1),label,HO);
 end
 end
 
 
-function ER=jwrapperKNN(sFeat,label,HO)
+function error = jwrapperKNN(sFeat,label,HO)
 %---// Parameter setting for k-value of KNN //
-k=5; 
-xtrain=sFeat(HO.training==1,:); ytrain=label(HO.training==1); 
-xvalid=sFeat(HO.test==1,:); yvalid=label(HO.test==1); 
-Model=fitcknn(xtrain,ytrain,'NumNeighbors',k); 
-pred=predict(Model,xvalid); 
-N=length(yvalid); correct=0;
-for i=1:N
+k = 5; 
+
+xtrain = sFeat(HO.training == 1,:);
+ytrain = label(HO.training == 1); 
+xvalid = sFeat(HO.test == 1,:); 
+yvalid = label(HO.test == 1); 
+
+Model     = fitcknn(xtrain,ytrain,'NumNeighbors',k); 
+pred      = predict(Model,xvalid);
+num_valid = length(yvalid); 
+correct   = 0;
+for i = 1:num_valid
   if isequal(yvalid(i),pred(i))
-    correct=correct+1;
+    correct = correct + 1;
   end
 end
-Acc=correct/N; 
-ER=1-Acc;
+Acc   = correct / num_valid; 
+error = 1 - Acc;
 end
+