| Texto completo | |
| Autor(es): |
Pagliosa, Lucas
;
Pagliosa, Paulo
;
Nonato, Luis Gustavo
;
IEEE
Número total de Autores: 4
|
| Tipo de documento: | Artigo Científico |
| Fonte: | 2016 29TH SIBGRAPI CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI); v. N/A, p. 8-pg., 2016-01-01. |
| Resumo | |
Multidimensional Projection techniques can help users to find patterns in multidimensional data. However, while the visualization literature is rich in techniques designed to improve the projection itself, only a handful of papers shed light into the attributes that contribute to cluster formation or the spread of projected data. In this paper, we present a web-based visualization tool that enriches multidimensional projection layout with statistical measures derived from inputted data. Given a set of regions to analyze, we used statistical measures, such as variance, to highlight relevant attributes that contribute to the points' similarities in each region. Experimental tests show that our technique can help identify important attributes and explain projected data. (AU) | |
| Processo FAPESP: | 13/15928-9 - Visualização de Dados Multidimensionais na Web |
| Beneficiário: | Lucas de Carvalho Pagliosa |
| Modalidade de apoio: | Bolsas no Brasil - Mestrado |
| Processo FAPESP: | 11/22749-8 - Desafios em visualização exploratória de dados multidimensionais: novos paradigmas, escalabilidade e aplicações |
| Beneficiário: | Luis Gustavo Nonato |
| Modalidade de apoio: | Auxílio à Pesquisa - Temático |