pkregann - regression with artificial neural network (multi-layer perceptron)

pkregann performs a regression based on an artificial neural network.  The regression is trained from the
       input  (-ic)  and output (-oc) columns in a training text file.  Each row in the training file represents
       one sampling unit.  Multi-dimensional input features can be defined with multiple  input  options  (e.g.,
       -ic0-ic1-ic2 for three dimensional features).

       pkregann - regression with artificial neural network (multi-layer perceptron)

-ifilename, --inputfilename
              input ASCII file

       -tfilename, --trainingfilename
              training  ASCII file (each row represents one sampling unit.  Input features should be provided as
              columns, followed by output)

       -ofilename, --outputfilename
              output ASCII file for result

       -iccol, --inputColscol
              input columns (e.g., for three dimensional input data in first three columns use: -ic0-ic1-ic2-occol, --outputColscol
              output  columns  (e.g., for two dimensional output in columns 3 and 4 (starting from 0) use: -oc3-oc4-fromrow, --fromrow
              start from this row in training file (start from 0)

       -torow, --torow
              read until this row in training file (start from 0 or set leave 0 as default to read until end  of
              file)

       -cvsize, --cvsize
              n-fold cross validation mode

       -nnnumber, --nneuronnumber
              number  of  neurons in hidden layers in neural network (multiple hidden layers are set by defining
              multiple number of neurons: -n15-n1, default is one hidden layer with 5 neurons)

       -vlevel, --verboselevel
              set to: 0 (results only), 1 (confusion matrix), 2 (debug)

       Advanced options

       --offsetvalue
              offset value for each spectral band input features: refl[band]=(DN[band]-offset[band])/scale[band]

       --scalevalue
              scale value for each spectral band input features: refl=(DN[band]-offset[band])/scale[band] (use 0
              if scale min and max in each band to -1.0 and 1.0)

       --connectionrate
              connection rate (default: 1.0 for a fully connected network)

       -lrate, --learningrate
              learning rate (default: 0.7)

       --maxitnumber
              number of maximum iterations (epoch) (default: 500)

                                                 01 January 2025                                     pkregann(1)

pkregann-iinput-ttraining [-iccol] [-occol] -ooutput [options] [advancedoptions]