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 features).
- -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:
refl[band]=(DN[band]-offset[band])/scale[band]
- --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)