MATLAB: How to set target data in matlab for neural network

#macinelearningannecgneuralnetwork

I have a matrix of ECGs signal that has 256*128 where the ECGs are saved in the rows of this matrix, and I want to design a target data that tells the difference between normal 'N', super ventricular ectopic 'S', ventricular ectopic 'V', fusion 'F', and Unknown beats 'Q'. where each indicated to be: N = [1 -1 -1 -1 -1] S = [-1 1 -1 -1 -1] V = [-1 -1 1 -1 -1] F = [-1 -1 -1 1 -1] Q = [-1 -1 -1 -1 1] which 5*5 matrix. How can I do it in Matlab ???

Best Answer

If you have 128 EEGs of length 256, you will need 128 targets of length 5 arranged so that the matrix sizes are
 size(input) = [ 256 128 ]
 size(target) = [ 5 128 ]
HOWEVER, YOU WOULD BE WELL ADVISED TO TRY TO USE FEATURE EXTRACTION TO TRY TO REDUCE THE SIZE OF THE INPUT VECTORS AS FAR BELOW 128 AS POSSIBLE.
Hope this helps,
Thank you for formally accepting my answer
Greg
Related Question