Exact k-NN queries on clustered SVD datasets

Authors

Alexander Thomasian, Department of Computer Science
Yue Li, Department of Computer Science
Lijuan Zhang, Department of Computer Science

Document Type

Article

Publication Date

6-30-2005

Abstract

Clustered SVD-CSVD, which combines clustering and singular value decomposition (SVD), outperforms SVD applied globally, without first applying clustering. Datasets of feature vectors in various application domains exhibit local correlations, which allow CSVD to attain a higher dimensionality reduction than SVD for the same normalized mean square error. We specify an exact method for processing k-nearest-neighbor queries for CSVD, which ensures 100% recall and is experimentally shown to require less CPU processing time than the approximate method originally specified for CSVD. © 2005 Elsevier B.V. All rights reserved.

Identifier

18244400406 (Scopus)

Publication Title

Information Processing Letters

External Full Text Location

https://doi.org/10.1016/j.ipl.2005.03.003

ISSN

00200190

First Page

247

Last Page

252

Issue

6

Volume

94

Grant

0105485

Fund Ref

National Science Foundation

Recommended Citation

Thomasian, Alexander; Li, Yue; and Zhang, Lijuan, "Exact k-NN queries on clustered SVD datasets" (2005). Faculty Publications. 19655.
https://digitalcommons.njit.edu/fac_pubs/19655