Visual Analytics como ferramenta de auxílio ao processo de KDD : um estudo voltado ao pré-processamento

Abstract

Visual Analytics is the combination of intelligent and automatic methods with the ability of human visual perception aiming to extract knowledge from data sets. This visual capability is supported by interactive interfaces, considering the most important for this work, the Parallel Coordinates visualization. However, tools that have both automatic methods (KDD) and visual (Parallel Coordinates) in a generic and integrated way is inherent. Thus, this work presents an integrated model between the KDD process and the Information Visualization using the Parallel Coordinates with emphasis on the make sense of data, by increasing the possibility of data exploration in the preprocessing stage. To demonstrate the operation of this model, a plugin was developed on the WEKA tool. This module is responsible for expanding the possibilities of chosen tool by expanding its functionality to the point of conceptualizing it as a Visual Analytics tool. In addition to the delivered visualization of Parallel Coordinate, it is also possible to interact by permutation of the dimensions (axes), interaction by selection of samples (brushing) and possibility of detailing them in the visualization itself.