Visualização de Dados em Sistemas de Bases de Dados Relacionais

Agma TrainaCaetano Traina Jr.Elisângela BotelhoMaria Camila N. BarioneRenato Bueno

Completely automated data analysis techniques often fail to fulfill their jobs, due to their inability to exploit the peripheral knowledge associated with the data. Human beings have a very good ability to interpret data represented in graphical format, and have the wisdom to recognize the associated knowledge. This paper address this dichotomy through a data visualization tool which displays, in a graphical manner, data stored in database relations, without relying on any kind of data summarization. Its objective is to include human beings in the main stream of knowledge data discovery (KDD) processes. The paper develops the conceptual framework which supports the data transformation that enables the visualization of relations composed by attributes of many data types (numbers, dates and texts). This is achieved through the mapping of this multidimensional data into a 3-dimensional space, applying a user-defined distance function. The paper shows some examples of utilizations with well-known datasets. Through a set of experiments it also shows that it is scalable to any database size, regarding both number of tuples and number of attributes.

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: