Resumo

LORA DOMINGUEZ, Yenisleidi; ARTIGAS FUENTES, Fernando; FONSECA BRUZON, Adrian  e  ORTEGA BUENO, Reynier. Optimizations for the Dynamic Compact Hierarchical Clustering Algorithm. Rev cuba cienc informat [online]. 2014, vol.8, suppl.1, pp.52-65. ISSN 2227-1899.

In this paper we propose two optimizations for the compact dynamic hierarchical clustering algorithm. This algorithm is applied to a set of documents in order to discover the structure of topics that they describe. The first one is a condense graph data structure that enables efficient use of main memory; and the second a prune graph heuristic, which allows documents to be processed in a shorter time than those used by a previous implementation. The results obtained in the experiments demonstrate that these optimizations allow processing more objects in less time.

Palavras-chave : document collection; dynamic hierarchical clustering; efficient data structure; optimization.

        · resumo em Espanhol     · texto em Espanhol     · Espanhol ( pdf )