MATLAB: Predicting if a time-series nonlinear signal will reach end positions( 0 or max)

Deep Learning ToolboxDSP System ToolboxexponentialforecastMATLABneural networksnonlinearpredictionsimulink

Hello All, I am trying to build a Matlab/Simulink model to predict if a signal would reach end values. However the incoming data is realtime/dynamic , I have less control over the past data(only a few samples to say) in order to avoid more delay in the control system.

Can this done using Neural Nets considering less delay/few past samples? I went through some answers related to market trends here but seemed complex. Could a simple NN model be built with limited(Sorry,I am beginner to NN) or any simple method is possible ?

Please any idea or direction would be helpful. Thank you in advance

Note:In realtime data is NON LINEAR/EXPONENTIAL.

Best Answer

The answer to questions you have about input and feedback delays can be answered if you have relevant design data by using

 1. SIGNIFICANT DELAYS OF THE INPUT-TARGET CROSS-CORRELATION 
    FUNCTION
 2.  SIGNIFICANT DELAYS OF THE TARGET AUTO-CORRELATION FUNCTION
 3. If you use the NN Toolbox function NNCORR
    help NNCORR
    doc NNCORR
   It will be worthwhile to see some of my NEWSGROUP and ANSWERS 
   posts. Search with
    greg nncorr

Hope this helps.

Thank you for formally accepting my answer

Greg

Related Solutions

MATLAB: Sum of coins using neural network

Inappropriate application of a NN. Check out NN example data using the line commands

 help nndatasets
 doc nndatasets

Check out the regression/curve-fitting example with the commands

 help fitnet
 doc fitnet

Hope this helps

Thank you for formally accepting my answer

Greg

MATLAB: Is the neural network overfitting

The best approach for regression is to start with FITNET using as many defaults as possible. The default I-H-O node topology contains Nw = (I+1)*H+(H+1)*O unknown weights. Ntrn training examples yields Ntrneq = Ntrn*O training equations with Ntrndof = Ntrneq-Nw training degrees of freedom. The average variance in the training target examples is MSEtrn00 = mean(var(target')). Obtaining a mean-square-error lower than MSEtrngoal = 0.01*Ntrndof*MSEtrn00a/Ntrneq for Ntrndof > 0 results in a normalized DOF adjusted MSE of NMSEtrna <= 0.01 and the corresponding adjusted training Rsquared R2trna = 1-NMSEtrna >= 0.99. That is interpreted as the successful modeling of at least 99% of the variation in the target.

The training objective is to try and minimize H with the constraint R2trna >=0.99. This is usually achieved by trial and error over a double for loop with the outer loop of hidden node candidate values h = Hmin:dH:Hmax and an inner loop of i = 1:Ntrials random weight initializations. I have posted many, many examples. Search NEWSGROUP and ANSWERS using

 greg fitnet Ntrials

If Ntrneq < ~2*Nw, validation stopping and/or regularization should be used to mitigate the problem of overtraining and overfit net.

The best approach to avoid overtraining is to use BOTH validation set stopping AND regularization.

HOWEVER FOR SOME STRANGE REASON, using validation stopping with TRAINBR is NOT AVAILABLE IN THE NNTOOLBOX !!!

Your choice of TRAINBR instead of FITNET is not wrong. However, you have made numerous errors, especially by not accepting as many defaults as possible.

Why not just use the syntax in

 help trainbr
 doc trainbr

with the double loop approach?

Don't forget to initialize the RNG before the first loop so that you can duplicate results.

Hope this helps.

Thank you for formally accepting my answer

Greg

Best Answer

Related Solutions

MATLAB: Sum of coins using neural network

MATLAB: Is the neural network overfitting

Related Question