Two-Phase Mapping for Projecting Massive Data Sets


Autoria(s): PAULOVICH, Fernando V.; SILVA, Claudio T.; NONATO, L. Gustavo
Contribuinte(s)

UNIVERSIDADE DE SÃO PAULO

Data(s)

20/10/2012

20/10/2012

2010

Resumo

Most multidimensional projection techniques rely on distance (dissimilarity) information between data instances to embed high-dimensional data into a visual space. When data are endowed with Cartesian coordinates, an extra computational effort is necessary to compute the needed distances, making multidimensional projection prohibitive in applications dealing with interactivity and massive data. The novel multidimensional projection technique proposed in this work, called Part-Linear Multidimensional Projection (PLMP), has been tailored to handle multivariate data represented in Cartesian high-dimensional spaces, requiring only distance information between pairs of representative samples. This characteristic renders PLMP faster than previous methods when processing large data sets while still being competitive in terms of precision. Moreover, knowing the range of variation for data instances in the high-dimensional space, we can make PLMP a truly streaming data projection technique, a trait absent in previous methods.

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Fapesp-Brazil

CNPq-NSF

U.S. National Science Foundation (NSF)

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

U.S. National Science Foundation (NSF)

National Science Foundation (NSF)

Department of Energy (DOE)

U.S. Department of Energy (DOE)

IBM

IBM

Identificador

IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS, v.16, n.6, p.1281-1290, 2010

1077-2626

http://producao.usp.br/handle/BDPI/28903

10.1109/TVCG.2010.207

http://dx.doi.org/10.1109/TVCG.2010.207

Idioma(s)

eng

Publicador

IEEE COMPUTER SOC

Relação

Ieee Transactions on Visualization and Computer Graphics

Direitos

restrictedAccess

Copyright IEEE COMPUTER SOC

Palavras-Chave #Dimensionality Reduction #Projection Methods #Visual Data Mining #Streaming Technique #HIGH-DIMENSIONAL DATA #REDUCTION #EXPLORATION #EIGENMAPS #LAYOUT #MDS #GPU #Computer Science, Software Engineering
Tipo

article

original article

publishedVersion