Spectral clustering as an automated SOM segmentation tool

A powerful method in knowledge discovery and cluster extraction is the use of self-organizing maps (SOMs), which provide adaptive quantization of the data together with its topologically ordered lower-dimensional representation on a rigid lattice. The knowledge extraction from SOMs is often performed interactively from informative visualizations. Even though interactive cluster extraction is successful, it is often time consuming and usually not straightforward for inexperienced users. In order to cope with the need of fast and accurate analysis of increasing amount of data, automated methods for SOM clustering have been popular. In this study, we use spectral clustering, a graph partitioning method based on eigenvector decomposition, for automated clustering of the SOM. Experimental results based on seven real data sets indicate that spectral clustering can successfully be used as an automated SOM segmentation tool, and it outperforms hierarchical clustering methods with distance based similarity measures.

TASDEMIR Kadim; 

2011-06-16

Springer-Verlag

JRC64867

https://publications.jrc.ec.europa.eu/repository/handle/JRC64867,   

10.1007/978-3-642-21566-7,