Tool K-Means Clustering for Grids
This tool implements the K-Means cluster analysis for grids in two variants, iterative minimum distance (Forgy 1965) and hill climbing (Rubin 1967).
References
- Forgy, E. (1965): Cluster analysis of multivariate data: efficiency vs. interpretability of classifications. Biometrics 21:768.
- Rubin, J. (1967): Optimal classification into groups: an approach for solving the taxonomy problem. J. Theoretical Biology, 15:103-144.
- Author: O.Conrad (c) 2001
- Menu: Imagery|Classification|Unsupervised
Parameters
| Name | Type | Identifier | Description | Constraints |
Input | Grids | Grid list, input | GRIDS | - | - |
Output | Clusters | Grid, output | CLUSTER | - | - |
Statistics | Table, output | STATISTICS | - | - |
Options | Grid System | Grid system | PARAMETERS_GRID_SYSTEM | - | - |
Method | Choice | METHOD | - | Available Choices: [0] Iterative Minimum Distance (Forgy 1965) [1] Hill-Climbing (Rubin 1967) [2] Combined Minimum Distance / Hillclimbing Default: 1 |
Clusters | Integer | NCLUSTER | Number of clusters | Minimum: 2 Default: 10 |
Maximum Iterations | Integer | MAXITER | maximum number of iterations, ignored if set to zero (default) | Minimum: 0 Default: 10 |
Normalise | Boolean | NORMALISE | Automatically normalise grids by standard deviation before clustering. | Default: 0 |
Update Colors from Features | Boolean, GUI | RGB_COLORS | Use the first three features in list to obtain blue, green, red components for class colour in look-up table. | Default: 0 |
Start Partition | Choice | INITIALIZE | - | Available Choices: [0] random [1] periodical [2] keep values Default: 0 |
Old Version | Boolean | OLDVERSION | slower but memory saving | Default: 0 |
Update View | Boolean | UPDATEVIEW | - | Default: 1 |
Command-line
Usage: saga_cmd imagery_classification 1 [-GRIDS <str>] [-CLUSTER <str>] [-STATISTICS <str>] [-METHOD <str>] [-NCLUSTER <num>] [-MAXITER <num>] [-NORMALISE <str>] [-INITIALIZE <str>] [-OLDVERSION <str>] [-UPDATEVIEW <str>]
-GRIDS:<str> Grids
Grid list, input
-CLUSTER:<str> Clusters
Grid, output
-STATISTICS:<str> Statistics
Table, output
-METHOD:<str> Method
Choice
Available Choices:
[0] Iterative Minimum Distance (Forgy 1965)
[1] Hill-Climbing (Rubin 1967)
[2] Combined Minimum Distance / Hillclimbing
Default: 1
-NCLUSTER:<num> Clusters
Integer
Minimum: 2
Default: 10
-MAXITER:<num> Maximum Iterations
Integer
Minimum: 0
Default: 10
-NORMALISE:<str> Normalise
Boolean
Default: 0
-INITIALIZE:<str> Start Partition
Choice
Available Choices:
[0] random
[1] periodical
[2] keep values
Default: 0
-OLDVERSION:<str> Old Version
Boolean
Default: 0
-UPDATEVIEW:<str> Update View
Boolean
Default: 1