Back to Search
Start Over
diatSOM: a R-package for diatom biotypology using self-organizing maps
- Source :
- Diatom Research. 29:5-9
- Publication Year :
- 2013
- Publisher :
- Informa UK Limited, 2013.
-
Abstract
- Owing to the high complexity of diatom community data, there is a special need for methods accounting for complex non-linear gradients. A Kohonen's self-organizing map (SOM) is a neural network with unsupervised learning. It allows both unbiased classification of the communities and visualization of biological gradients on a two-dimensional plane. However, as with other neural networks, many parameters must be set. A new R-package with a SOM parameterization specifically suited to diatom communities has been developed. Further developments will consist of creating a graphical user interface in order to make this method easier to use for the scientific community.
- Subjects :
- Self-organizing map
Artificial neural network
biology
business.industry
Computer science
Ecology
Aquatic Science
biology.organism_classification
computer.software_genre
Visualization
Set (abstract data type)
ComputingMethodologies_PATTERNRECOGNITION
Software
Diatom
Unsupervised learning
Data mining
business
computer
Graphical user interface
Subjects
Details
- ISSN :
- 21598347 and 0269249X
- Volume :
- 29
- Database :
- OpenAIRE
- Journal :
- Diatom Research
- Accession number :
- edsair.doi...........4769f1df1752d97d66436ea4c1ec36bf