Search All of the Math Forum:
Views expressed in these public forums are not endorsed by
Drexel University or The Math Forum.
|
|
|
|
Re: neural network input
Posted:
Feb 21, 2013 8:44 PM
|
|
"srishti " <srishti.sondele@gmail.com> wrote in message <kg30rq$5i3$1@newscl01ah.mathworks.com>...
> hi everyone,
> I am using Empirical mode decomposition, for feature extraction of an image, I will take first three IMFs, then suppose I want to take statistical features like mean, standard deviation,energy . So can anybody suggest me how to prepare that data for neural network classifier input ?
If you have N samples of I features, the size of the input matrix is
[ I N ] = size(input)
The size of the corresponding target matrix for c classes is
[ c N ] = size(target)
The target columns are columns of the c-dimensional unit matrix eye(c) with the row index of the 1 indicating the class index of the corresponding input vector.
See the classification/pattern-recognition demos using patternnet.
help/doc patternnet
help/doc nndatasets
Hope this helps.
Greg
|
|
|
|
