In this work we study the effectiveness of the FuzzyKohonen Clustering Network (FKCN) in the unsupervisedclassification of electron microscopic images of biologicalmacromolecules. The algorithm combines Kohonen'sSelf-Organizing Feature Map (SOM) and Fuzzy c-meansklustering technique (FCM) in order to obtain a clusteringtechnique that inherits their best properties. Twodifferent data sets obtained from the G40P helicase from B.Subtlis bacteriophage SPP1 have been used for testing theproposed method, one composed by 388 images from the samemacromolecule. Results of FKCN are compared withSelf-Organizing Maps (SOM) and manual classification.Experimental results have proved that this new technique issuitable for working with large, high dimensional and noisydata sets.
CITATION STYLE
Pascual, A., Barcéna, M., Merelo, J. J., & Carazo, J.-M. (2000). Self-Organizing Networks for Mapping and Clustering Biological Macromolecules Images (pp. 283–288). https://doi.org/10.1007/978-1-4471-0513-8_43
Mendeley helps you to discover research relevant for your work.