Maximum Entropy Classification

Author: O.Conrad (c) 2015
Menu: Imagery | Classification | Machine Learning

Description

References

Parameters

	Name	Type	Identifier	Description	Constraints
Input	Training Areas	shapes, input	`TRAINING`	-	-
	Numerical Features	grid list, input, optional	`FEATURES_NUM`	-	-
	Categorical Features	grid list, input, optional	`FEATURES_CAT`	-	-
Output	Classification	grid, output	`CLASSES`	-	-
	Look-up Table	table, output, optional	`CLASSES_LUT`	A reference list of the grid values that have been assigned to the training classes.	-
	Probability	grid, output	`PROB`	-	-
	Probabilities	grid list, output	`PROBS`	-	-
Options	Grid System	grid system	`PARAMETERS_GRID_SYSTEM`	-	-
	Class Name	table field	`FIELD`	-	-
	Create Probabilities	boolean	`PROBS_CREATE`	-	Default: 0
	Method	choice	`METHOD`	-	Available Choices: [0] Yoshimasa Tsuruoka [1] Dekang Lin Default: 0
	Load from File...	file path	`YT_FILE_LOAD`	-	-
	Save to File...	file path	`YT_FILE_SAVE`	-	-
	Regularization	choice	`YT_REGUL`	-	Available Choices: [0] none [1] L1 [2] L2 Default: 0
	Regularization Factor	floating point number	`YT_REGUL_VAL`	-	Minimum: 0.000000 Default: 1.000000
	Real-valued Numerical Features	boolean	`YT_NUMASREAL`	-	Default: 1
	Alpha	floating point number	`DL_ALPHA`	-	Default: 0.100000
	Threshold	floating point number	`DL_THRESHOLD`	-	Minimum: 0.000000 Default: 0.000000
	Maximum Iterations	integer number	`DL_ITERATIONS`	-	Minimum: 1 Default: 100
	Number of Numeric Value Classes	integer number	`NUM_CLASSES`	-	Minimum: 1 Default: 32
	Minimum Probability	floating point number	`PROB_MIN`	Minimum probability to accept a classification result for a cell.	Minimum: 0.000000 Maximum: 1.000000 Default: 0.000000

Command Line


Usage: saga_cmd imagery_maxent 0 [-TRAINING ] [-FIELD ] [-FEATURES_NUM ] [-FEATURES_CAT ] [-CLASSES ] [-CLASSES_LUT ] [-PROB ] [-PROBS ] [-PROBS_CREATE ] [-METHOD ] [-YT_FILE_LOAD ] [-YT_FILE_SAVE ] [-YT_REGUL ] [-YT_REGUL_VAL ] [-YT_NUMASREAL ] [-DL_ALPHA ] [-DL_THRESHOLD ] [-DL_ITERATIONS ] [-NUM_CLASSES ] [-PROB_MIN ]
  -TRAINING:          Training Areas
	shapes, input
  -FIELD:             Class Name
	table field
  -FEATURES_NUM:      Numerical Features
	grid list, input, optional
  -FEATURES_CAT:      Categorical Features
	grid list, input, optional
  -CLASSES:           Classification
	grid, output
  -CLASSES_LUT:       Look-up Table
	table, output, optional
  -PROB:              Probability
	grid, output
  -PROBS:             Probabilities
	grid list, output
  -PROBS_CREATE:      Create Probabilities
	boolean
	Default: 0
  -METHOD:            Method
	choice
	Available Choices:
	[0] Yoshimasa Tsuruoka
	[1] Dekang Lin
	Default: 0
  -YT_FILE_LOAD:      Load from File...
	file path
  -YT_FILE_SAVE:      Save to File...
	file path
  -YT_REGUL:          Regularization
	choice
	Available Choices:
	[0] none
	[1] L1
	[2] L2
	Default: 0
  -YT_REGUL_VAL:   Regularization Factor
	floating point number
	Minimum: 0.000000
	Default: 1.000000
  -YT_NUMASREAL:      Real-valued Numerical Features
	boolean
	Default: 1
  -DL_ALPHA:       Alpha
	floating point number
	Default: 0.100000
  -DL_THRESHOLD:   Threshold
	floating point number
	Minimum: 0.000000
	Default: 0.000000
  -DL_ITERATIONS:     Maximum Iterations
	integer number
	Minimum: 1
	Default: 100
  -NUM_CLASSES:       Number of Numeric Value Classes
	integer number
	Minimum: 1
	Default: 32
  -PROB_MIN:
                           Minimum Probability
                           	floating point number
                           	Minimum: 0.000000
                           	Maximum: 1.000000
                           	Default: 0.000000