Which classifier (SVM or Neural Networks) is accurate for fault detection in Power Systems?

I want to implement classifiers for fault diagnoses in Transformer

Answer 1

[Greg Heath]

N pairs of I-dimensional "I"nputs and corresponding O-dimensional "O"utput targets in two matrices:

 [ I N ] = size(input)
 [ O N ] = size(target)

For c classes, the columns of target are c-dimensional unit vectors.

 help patternnet
 doc patternnet

Search mathworks.com

 greg patternnet

Hope this helps.

Thank you for formally accepting my answer*

Greg

[Machine Learning Enthusiast]

can you provide me with simple code for creating dataset?

 [ I N ] = size(input)

 [ O N ] = size(target)

Answer 2

[Greg Heath]

It depends on which one you are most comfortable wth.

Thank you for formally accepting my answer

Greg

[Machine Learning Enthusiast]

Thank you Greg for your reply. I know both classifiers can be used but which one gives more accuracy and perfect results?

[Greg Heath]

NNs are universal approximators.

I'm not sure whether SVMs are in that category.

Greg

[Machine Learning Enthusiast]

can you tell me how we can create our own data-set to implement is NNs?