On the configuration of the similarity search data structure d-index for high dimensional objects

  • Authors:
  • Arnoldo José Müller-Molina;Takeshi Shinohara

  • Affiliations:
  • Department of Artificial Intelligence, Kyushu Institute of Technology, Iizuka, Japan;Department of Artificial Intelligence, Kyushu Institute of Technology, Iizuka, Japan

  • Venue:
  • ICCSA'10 Proceedings of the 2010 international conference on Computational Science and Its Applications - Volume Part III
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

Among similarity search indexes, the D-index introduced by Gennaro et al. in 2001 is regarded as an efficient metric access method. The performance of this index depends on several parameters, and their optimal configuration remains an open problem. We study two performance issues that occur when the D-index handles high dimensional objects. To solve these problems, we introduce an optimization that simplifies the D-index. By doing this, we remove two configuration parameters and improve performance.