Provided by: pktools_2.6.7.6+ds-1build1_amd64 bug


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


       pkregann -i input -t training [-ic col] [-oc col] -o output [options] [advanced options]


       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., -ic 0 -ic 1  -ic  2  for  three  dimensional


       -i filename, --input filename
              input ASCII file

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

       -o filename, --output filename
              output ASCII file for result

       -ic col, --inputCols col
              input columns (e.g., for three dimensional input data in first three  columns  use:
              -ic 0 -ic 1 -ic 2

       -oc col, --outputCols col
              output  columns (e.g., for two dimensional output in columns 3 and 4 (starting from
              0) use: -oc 3 -oc 4

       -from row, --from row
              start from this row in training file (start from 0)

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

       -cv size, --cv size
              n-fold cross validation mode

       -nn number, --nneuron number
              number  of  neurons  in hidden layers in neural network (multiple hidden layers are
              set by defining multiple number of neurons: -n 15 -n 1, default is one hidden layer
              with 5 neurons)

       -v level, --verbose level
              set to: 0 (results only), 1 (confusion matrix), 2 (debug)

       Advanced options

       --offset value
              offset      value      for      each      spectral     band     input     features:

       --scale value
              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)

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

       -l rate, --learning rate
              learning rate (default: 0.7)

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

                                         05 January 2019                              pkregann(1)