数学建模必备程序.docVIP

一基于均值生成函数时间序列预测算法程序 predict」un.m为主程序； timeseries.m 和 serie**pan.m 为调川的子程序 function ima_pre= predict_fun(b,step) % main program invokes timeseries.m and serie**pan.m % in put parameters: % b the training data (vector); % step-mber of prediction data; % output parameters: % ima_pre--the prediction data(vector); old_b=b; mean_b= sum(old_b)/length(old_b); std_b=std(old_b); old_b= (o I d_b- m ean_b) / st d_b; [f,x] = timeseries(old_b); old_f2= serie** pan(old_b,step); % f(f0.0001 f-0.0001)=f(f0.0001 f-0.0001)+eps; R=corrcoef(f); [eigvector eigroot] = eig(R); eigroot=diag(eigroot); a= eigroot(end:-1:1); vector= eigvector(:,end:-1:1); Devote= a./sum(a); Devotem=cumsum( Devote); m=find(Devotem = 0.995); m=m(1); V1 = f*eigvector; V=V1(:,1:m); % old_b=old_b; old」ai=inv(V,*V)*V,*old_b; eigvector= eigvector( 1:m,1:m); fai= eigvector* old_fai; f2=oldI_f2(:,1:m); predict value= f2*fai; ima_pre= std_b* predictvalue+ mean_b; 1 ?子函数：timeseries.m % timeseries program% % this program is used to generate mean value matrix f; function [f,x] = timeseries(data) % data the in put seque nee (vector); % f- mean value matrix f; n=len gth(data); for L=1:n/2 n L=floor(n/L); for i=1:L sum=0; for j=1:nL sum= sum+ data(i+ (j-1 )* L); end x{L,i} = sum/nL; end end L=n/2; f=zeros(n3L); for i=1:L rep=floor(n/i); res= mod(n,i); b=[x{i,1:i}];b=b; f(1:rep* i ,i)=repmat(b,rep, 1); if res~ = 0 c= rep* i+1: n; f(rep*i+1:end,i)=b(1 :length(c)); end end % serie**pan.m % the program is used to generate the prediction matrix f; function f=serieipan(data,step); % data- ?- the in put seque nee (vector) % setp-— the prediction number; n=len gth(data); for L=1:n/2 n L=floor(n/L); for i=1:L sum=0; for j=1:nL sum=sum+data(i+(j-1)* L); end x{L,i} = sum/nL; end end L=n/2; f = zeros( n+st ep 丄)； for i=1:L rep=floor( (n +step)/i); res= mod (n +step3i); b=[x{i,1:i}];b=b,; f(1: rep* ij)=repmat(b,rep,1); if res~ = 0 c= rep*i+1:n+step; f(rep*i+1:end,i)= b(1 :length(c)); end end 二最短路Dijkstra算法 % dijkstra algorithm code progra