Visualizing the organization and behavior of metric access methods: Applications in similarity queries / "Visualizando a organização e o comportamento de estruturas métricas: aplicações em consultas por similaridade"

AUTOR(ES)
DATA DE PUBLICAÇÃO

2004

RESUMO

The use of computers by an increasing variety of applications led the Database Management Systems (DBMS) to be used to store a wide range of complex data types, such as images, sounds, DNA chains, etc. Queries based on the total order relationship and/or equality can not be applied or have a limited range of applications when performed over these datasets. It is necessary to use similarity queries based on the contents of the data. If these datasets can be represented as metric spaces, it is possible to use the Metric Access Methods (MAM), such as the Slim-Tree, the M-Tree and the DBM-Tree, to optimize similarity queries. However, MAM are very hard to understand and analyze due to their complex structures. This work presents a visualization system that allows the visual inspection of the organization and the behavior of MAM. The usage of this system provides to MAM developers and database administrators, an easy and fast way to acquire information about key aspects of these structures, which can lead to improvements on the performance of queries and other operations.

ASSUNTO(S)

consultas baseadas em conteúdo multimedia databases estruturas métricas visualização de informação metric access methods information visualization content based queries bases de dados multimídia

ACESSO AO ARTIGO

Documentos Relacionados