How do I start coding for neural network time series?

Hi, I am very new with matlab and the neural network function. I am doing a public transport prediction data using this toolbox. I have watch the tutorials but I do not really understand. How do I start inputing the data and set the inputs and the targets. Thanks in advance

 Réponse acceptée

Greg Heath
Greg Heath le 5 Nov 2013

0 votes

Examine the help examples for
timedelaynet, narnet, narxnet and closeloop.
Next try other examples
help nndatasets.
Check back with specific questions.

2 commentaires

% input data from excel spreadsheet
Hourly = xlsread('C:\Users\user\Desktop\FYP\Datasheet.xlsx','Daily','A2:A25');
Weekday_Ridership = xlsread('C:\Users\user\Desktop\FYP\Datasheet.xlsx','Daily','B2:B25');
Weekend_Sat = xlsread('C:\Users\user\Desktop\FYP\Datasheet.xlsx','Daily','C2:C25');
t= Hourly;
% define signal
x1 = Weekday_Ridership;
% plot signal
figure;
plot(x1)
xlabel('Hourly');
ylabel('Ridership');
Target= Weekend_Sat; %targets
net = newff(x1,Target,1);
net = feedforwardnet(4)
net = train(net,x1,Target);
view(net)
y = net(x);
outputs = net(x1);
errors = outputs - Target;
perf = perform(net,outputs,Target);
Hi, after much trying here and there, I still don't get it. I still get blank graphs.
My data is as below
I am suppose to do a prediction of the ridership of public transportation be over the next few days.
I hope you are able to help me. Thanks in advance.
Confused. Is the task to predict the ridership for the next 3*24 = 72 hours? It seems like you would at least, need the ridership for the last 4*24 = 92 hours.

Connectez-vous pour commenter.

Plus de réponses (1)

You need continuation symbols after xlsread
xlsread...
Hope this helps.
Greg

Catégories

En savoir plus sur Deep Learning Toolbox dans Centre d'aide et File Exchange

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by