Visualização e análise de agrupamentos usando redes auto-organizáveis, segmentação de imagens e índices de validação

José Alfredo F. CostaMárcio L. GonçalvesMárcio L. de Andrade NettoBianca A. C. S. Costa

Self-organizing maps (SOM) had been widely used for input data quantization and visual display of data, an important property that does not exist in most of clustering algorithms. Effective data clustering using SOM involves two or three steps procedure. After proper network training, units can be clustered generating regions of neurons which are related to data clusters. The basic assumption relies on the data density approximation by the neurons through unsupervised learning. The transformation of high dimensional data into images and its visualization and clustering is addressed in this paper. The proposed method segments SOM networks via watershed algorithms and modified cluster validation indexes. Results are shown for benchmark datasets for different map sizes.

Caso o link acima esteja inválido, faça uma busca pelo texto completo na Web: Buscar na Web

Biblioteca Digital Brasileira de Computação - Contato:
     Mantida por: