Authors:
Juliana Keiko Yamaguchi
;
Maria Madalena Dias
and
Clélia Franco
Affiliation:
State University of Maringá, Brazil
Keyword(s):
Data visualization, Visualization techniques, Knowledge discovery, Data visualization parameters.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence
;
Data Mining
;
Databases and Information Systems Integration
;
Enterprise Information Systems
;
Sensor Networks
;
Signal Processing
;
Soft Computing
Abstract:
Visualization techniques are tools that can improve analyst's insight into the results of knowledge discovery process or to directly explore and analyze data. They allows analysts to interact with the graphical representation to get new knowledge. The choice of visualization techniques must follow some criteria to guarantee a consistent data representation. This paper presents a study based on Grounded Theory that indicates parameters for select visualization techniques, which are: data type, task type, data volume, data dimension and position of the attributes in the display. These parameters are analyzed in the context of visualization technique categories: standard 1D - 3D graphics, iconographic techniques, geometric techniques, pixel-oriented techniques and graph-based or hierarchical techniques. The analysis over the association among these parameters and visualization techniques culminated in guidelines establishment to choose the most appropriate techniques according to the da
ta characteristics and the objective of the knowledge discovery process.
(More)