Error-Correcting semi-supervised pattern recognition with mode filter on graphs

Weiwei Du, Kiichi Urahama

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

A robust semi-supervisedmethod using the mode filter has been presented for learning with partially-labeled training data including label errors. The mode filter has been originally developed for smoothing images contaminated with impulsive noises. However it needs nonlinear optimization which is usually solved with iterative methods. In this paper, we propose a direct solution method with full search of solution spaces. This direct method outperforms the iterative algorithm in classification rates and computational speeds. Additional iterations of the mode filter raise up the classification rates. We extend the mode filter by introducing weights based on the isolation degree of data, and show the effectiveness of this extension.

Original languageEnglish
Pages (from-to)1262-1268
Number of pages7
JournalJournal of Advanced Computational Intelligence and Intelligent Informatics
Volume15
Issue number9
DOIs
Publication statusPublished - Jan 1 2011

Fingerprint

Pattern recognition
Impulse noise
Iterative methods
Labels

All Science Journal Classification (ASJC) codes

  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Error-Correcting semi-supervised pattern recognition with mode filter on graphs. / Du, Weiwei; Urahama, Kiichi.

In: Journal of Advanced Computational Intelligence and Intelligent Informatics, Vol. 15, No. 9, 01.01.2011, p. 1262-1268.

Research output: Contribution to journalArticle

@article{9183b67b6432437faee52022f822f15a,
title = "Error-Correcting semi-supervised pattern recognition with mode filter on graphs",
abstract = "A robust semi-supervisedmethod using the mode filter has been presented for learning with partially-labeled training data including label errors. The mode filter has been originally developed for smoothing images contaminated with impulsive noises. However it needs nonlinear optimization which is usually solved with iterative methods. In this paper, we propose a direct solution method with full search of solution spaces. This direct method outperforms the iterative algorithm in classification rates and computational speeds. Additional iterations of the mode filter raise up the classification rates. We extend the mode filter by introducing weights based on the isolation degree of data, and show the effectiveness of this extension.",
author = "Weiwei Du and Kiichi Urahama",
year = "2011",
month = "1",
day = "1",
doi = "10.20965/jaciii.2011.p1262",
language = "English",
volume = "15",
pages = "1262--1268",
journal = "Journal of Advanced Computational Intelligence and Intelligent Informatics",
issn = "1343-0130",
publisher = "Fuji Technology Press",
number = "9",

}

TY - JOUR

T1 - Error-Correcting semi-supervised pattern recognition with mode filter on graphs

AU - Du, Weiwei

AU - Urahama, Kiichi

PY - 2011/1/1

Y1 - 2011/1/1

N2 - A robust semi-supervisedmethod using the mode filter has been presented for learning with partially-labeled training data including label errors. The mode filter has been originally developed for smoothing images contaminated with impulsive noises. However it needs nonlinear optimization which is usually solved with iterative methods. In this paper, we propose a direct solution method with full search of solution spaces. This direct method outperforms the iterative algorithm in classification rates and computational speeds. Additional iterations of the mode filter raise up the classification rates. We extend the mode filter by introducing weights based on the isolation degree of data, and show the effectiveness of this extension.

AB - A robust semi-supervisedmethod using the mode filter has been presented for learning with partially-labeled training data including label errors. The mode filter has been originally developed for smoothing images contaminated with impulsive noises. However it needs nonlinear optimization which is usually solved with iterative methods. In this paper, we propose a direct solution method with full search of solution spaces. This direct method outperforms the iterative algorithm in classification rates and computational speeds. Additional iterations of the mode filter raise up the classification rates. We extend the mode filter by introducing weights based on the isolation degree of data, and show the effectiveness of this extension.

UR - http://www.scopus.com/inward/record.url?scp=81755172825&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=81755172825&partnerID=8YFLogxK

U2 - 10.20965/jaciii.2011.p1262

DO - 10.20965/jaciii.2011.p1262

M3 - Article

AN - SCOPUS:81755172825

VL - 15

SP - 1262

EP - 1268

JO - Journal of Advanced Computational Intelligence and Intelligent Informatics

JF - Journal of Advanced Computational Intelligence and Intelligent Informatics

SN - 1343-0130

IS - 9

ER -