How can I use neural network for multi step ahead prediction

This is my script file of my neural network toolbox. I am going to predict for multi step ahead, but in this script only gave me 0ne step ahead (ys) prediction. How can I modify this script to multi-step ahead prediction?

clc; clear; close all;

% Solve an Autoregression Time-Series Problem with a NAR Neural Network % VarName1 - feedback time series. % The VarName1 is my original time series consists a matrix (272*1)

targetSeries = tonndata(VarName1,false,false);

% Create a Nonlinear Autoregressive Network feedbackDelays = 1:2; hiddenLayerSize = 10; net = narnet(feedbackDelays,hiddenLayerSize);

% Choose Feedback Pre/Post-Processing Functions net.inputs{1}.processFcns = {'removeconstantrows','mapminmax'};

% Prepare the Data for Training and Simulation [inputs,inputStates,layerStates,targets] = preparets(net,{},{},targetSeries);

% Setup Division of Data for Training, Validation, Testing net.divideFcn = 'dividerand'; % Divide data randomly net.divideMode = 'time'; % Divide up every value net.divideParam.trainRatio = 70/100; net.divideParam.valRatio = 15/100; net.divideParam.testRatio = 15/100;

% Choose a Training Function net.trainFcn = 'trainlm'; % Levenberg-Marquardt

% Choose a Performance Function net.performFcn = 'mse'; % Mean squared error

% Choose Plot Functions net.plotFcns = {'plotperform','plottrainstate','plotresponse', ... 'ploterrcorr', 'plotinerrcorr'};

% Train the Network [net,tr] = train(net,inputs,targets,inputStates,layerStates);

% Test the Network outputs = net(inputs,inputStates,layerStates); errors = gsubtract(targets,outputs); performance = perform(net,targets,outputs);

% Recalculate Training, Validation and Test Performance trainTargets = gmultiply(targets,tr.trainMask); valTargets = gmultiply(targets,tr.valMask); testTargets = gmultiply(targets,tr.testMask); trainPerformance = perform(net,trainTargets,outputs); valPerformance = perform(net,valTargets,outputs); testPerformance = perform(net,testTargets,outputs);

% Closed Loop Network netc = closeloop(net); [xc,xic,aic,tc] = preparets(netc,{},{},targetSeries); yc = netc(xc,xic,aic); perfc = perform(net,tc,yc);

% Early Prediction Network nets = removedelay(net); [xs,xis,ais,ts] = preparets(nets,{},{},targetSeries); ys = nets(xs,xis,ais); closedLoopPerformance = perform(net,tc,yc);

Thanks and Regards, Tiurmai

Answer 1

[Greg Heath]

Increase the number of feedback delays.

Hope this helps

Thank you for formally accepting my answer

Greg

[Tiurmai Hutajulu]

thank you for ur comment... still i just got one step ahead prediction... i want to predict for multi step ahead, which means many point of prediction... what code can be used??

Thank you Tiurmai

[Greg Heath]

Increase the number of feedback delays. For example

feedbackdelays = 5

Hope tis helps.

Greg

[Tiurmai Hutajulu]

how many step of prediction can be produced by increasing the number feedback delay??

Thank you Tiurmai

[Greg Heath]

FD = a sequence of increasing, not necessarily consecutive, positive integers.

If max(FD) = m, you can predict m timesteps ahead.

If the number of feedback delays is less than m (e.g., 1:2:m) you can fill in the missing delays to get FD = 1:m with ~double the number of delays However, that will not increase the prediction time because max(FD) remains constant.

However, the increased number of delays may substantially improve performance.

Hope this helps.

Greg