Semi-supervised classification with spectral projection of multiplicatively modulated similarity data

Weiwei Du, Kiichi Urahama

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

A simple and efficient semi-supervised classification method is presented. An unsupervised spectral mapping method is extended to a semi-supervised situation with multiplicative modulation of similarities between data. Our proposed algorithm is derived by linearization of this nonlinear semi-supervised mapping method. Experiments using the proposed method for some public benchmark data and color image data reveal that our method outperforms a supervised algorithm using the linear discriminant analysis and a previous semi-supervised classification method.

Original languageEnglish
Pages (from-to)1456-1459
Number of pages4
JournalIEICE Transactions on Information and Systems
VolumeE90-D
Issue number9
DOIs
Publication statusPublished - Jan 1 2007

Fingerprint

Discriminant analysis
Linearization
Modulation
Color
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Hardware and Architecture
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering
  • Artificial Intelligence

Cite this

Semi-supervised classification with spectral projection of multiplicatively modulated similarity data. / Du, Weiwei; Urahama, Kiichi.

In: IEICE Transactions on Information and Systems, Vol. E90-D, No. 9, 01.01.2007, p. 1456-1459.

Research output: Contribution to journalArticle

@article{072d1b34f152428d9d35e1e847274e03,
title = "Semi-supervised classification with spectral projection of multiplicatively modulated similarity data",
abstract = "A simple and efficient semi-supervised classification method is presented. An unsupervised spectral mapping method is extended to a semi-supervised situation with multiplicative modulation of similarities between data. Our proposed algorithm is derived by linearization of this nonlinear semi-supervised mapping method. Experiments using the proposed method for some public benchmark data and color image data reveal that our method outperforms a supervised algorithm using the linear discriminant analysis and a previous semi-supervised classification method.",
author = "Weiwei Du and Kiichi Urahama",
year = "2007",
month = "1",
day = "1",
doi = "10.1093/ietisy/e90-d.9.1456",
language = "English",
volume = "E90-D",
pages = "1456--1459",
journal = "IEICE Transactions on Information and Systems",
issn = "0916-8532",
publisher = "一般社団法人電子情報通信学会",
number = "9",

}

TY - JOUR

T1 - Semi-supervised classification with spectral projection of multiplicatively modulated similarity data

AU - Du, Weiwei

AU - Urahama, Kiichi

PY - 2007/1/1

Y1 - 2007/1/1

N2 - A simple and efficient semi-supervised classification method is presented. An unsupervised spectral mapping method is extended to a semi-supervised situation with multiplicative modulation of similarities between data. Our proposed algorithm is derived by linearization of this nonlinear semi-supervised mapping method. Experiments using the proposed method for some public benchmark data and color image data reveal that our method outperforms a supervised algorithm using the linear discriminant analysis and a previous semi-supervised classification method.

AB - A simple and efficient semi-supervised classification method is presented. An unsupervised spectral mapping method is extended to a semi-supervised situation with multiplicative modulation of similarities between data. Our proposed algorithm is derived by linearization of this nonlinear semi-supervised mapping method. Experiments using the proposed method for some public benchmark data and color image data reveal that our method outperforms a supervised algorithm using the linear discriminant analysis and a previous semi-supervised classification method.

UR - http://www.scopus.com/inward/record.url?scp=68249138613&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=68249138613&partnerID=8YFLogxK

U2 - 10.1093/ietisy/e90-d.9.1456

DO - 10.1093/ietisy/e90-d.9.1456

M3 - Article

AN - SCOPUS:68249138613

VL - E90-D

SP - 1456

EP - 1459

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

SN - 0916-8532

IS - 9

ER -