eprintid: 1525
rev_number: 8
eprint_status: archive
userid: 45
dir: disk0/00/00/15/25
datestamp: 2013-03-07 13:07:47
lastmod: 2013-03-12 14:58:11
status_changed: 2013-03-07 13:07:47
type: article
metadata_visibility: show
creators_name: Rusu, Cristian
creators_id: cristian.rusu@imtlucca.it
title: Clustering large datasets - bounds and applications with K-SVD
ispublished: pub
subjects: QA75
divisions: CSA
full_text_status: none
keywords: sparse representations, clustering, KSVD. MSC2000: 94A 12.
abstract: This article presents a clustering method called T-mindot that is used to reduce the dimension of datasets in order to diminish the running time of the training algorithms. The T-mindot method is applied before the K-SVD algorithm in the context of sparse representations for the design of
overcomplete dictionaries. Simulations that run on image data show the efficiency of the proposed method that leads to the substantial reduction of the execution time of K-SVD, while keeping the representation performance of the dictionaries designed using the original dataset.
date: 2012
date_type: published
publication: UPB Scientific Bulletin, Series C: Electrical Engineering
volume: 20
number: 10
publisher: Politechnica University of Bucharest
pagerange: 1-10
refereed: TRUE
issn: 1454-234X
citation:   Rusu, Cristian  Clustering large datasets - bounds and applications with K-SVD.  UPB Scientific Bulletin, Series C: Electrical Engineering, 20 (10).  pp. 1-10.  ISSN 1454-234X      (2012)