Exploring Multidimensional Projections Through Explanatory Maps

Renato Rodrigues Oliveira da Silva, Paulo Eduardo Rauber, Rafael Messias Martins, Rosane Minghim, Alexandru Telea

Research output: Contribution to conferencePosterAcademic

62 Downloads (Pure)

Abstract

Multidimensional Projections (MPs) are popular tools used to support the analysis of multidimensional data. MPs can project data to a low dimensional space, and are typically visualized as 2D scatterplots where similar elements are conveniently
positioned in close neighborhoods. However such visualizations tell us which points are similar, but not why. Our aim is, thus, to enrich 2D MP scatterplots with explanatory information telling users which key dimensions make closely projected points similar, and their values.
Original languageEnglish
Publication statusPublished - 2016
EventICT.Open 2016: The Conference for ICT-Research in the Netherlands - Amersfoort, Netherlands
Duration: 22-Mar-201623-Mar-2016
http://www.ictopen.nl/

Conference

ConferenceICT.Open 2016
Abbreviated titleICT.Open
CountryNetherlands
CityAmersfoort
Period22/03/201623/03/2016
Internet address

Keywords

  • dimensionality reduction
  • scatterplots
  • visual explanation

Cite this