Kernel-Reliability-Based K-Means (KRKM) Clustering Algorithm and Image Processing

Chunsheng HUA; Juntong QI; Jianda HAN; Haiyuan WU

doi:10.1587/transinf.2013EDP7439

Kernel-Reliability-Based K-Means (KRKM) Clustering Algorithm and Image Processing

Chunsheng HUA, Juntong QI, Jianda HAN, Haiyuan WU

Full Text Views

0

Cite this

Errata[Uploaded on November 1,2014]

Summary :

In this paper, we introduced a novel Kernel-Reliability-based K-Means (KRKM) clustering algorithm for categorizing an unknown dataset under noisy condition. Compared with the conventional clustering algorithms, the proposed KRKM algorithm will measure both the reliability and the similarity for classifying data into its neighbor clusters by the dynamic kernel functions, where the noisy data will be rejected by being given low reliability. The reliability for classifying data is measured by a dynamic kernel function whose window size will be determined by the triangular relationship from this data to its two nearest clusters. The similarity from a data item to its neighbor clusters is measured by another adaptive kernel function which takes into account not only the similarity from data to clusters but also that between its two nearest clusters. The main contribution of this work lies in introducing the dynamic kernel functions to evaluate both the reliability and similarity for clustering, which makes the proposed algorithm more efficient in dealing with very strong noisy data. Through various experiments, the efficiency and effectiveness of proposed algorithm have been confirmed.

Publication: IEICE TRANSACTIONS on Information Vol.E97-D No.9 pp.2423-2433

Publication Date: 2014/09/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2013EDP7439

Type of Manuscript: PAPER

Category: Artificial Intelligence, Data Mining

Authors

Chunsheng HUA
  Chinese Academy of Sciences
Juntong QI
  Chinese Academy of Sciences
Jianda HAN
  Chinese Academy of Sciences
Haiyuan WU
  Wakayama University

Keyword

kernel reliability, adaptive kernel function, K-Means clustering

Cite this

Copy

Chunsheng HUA, Juntong QI, Jianda HAN, Haiyuan WU, "Kernel-Reliability-Based K-Means (KRKM) Clustering Algorithm and Image Processing" in IEICE TRANSACTIONS on Information, vol. E97-D, no. 9, pp. 2423-2433, September 2014, doi: 10.1587/transinf.2013EDP7439.
Abstract: In this paper, we introduced a novel Kernel-Reliability-based K-Means (KRKM) clustering algorithm for categorizing an unknown dataset under noisy condition. Compared with the conventional clustering algorithms, the proposed KRKM algorithm will measure both the reliability and the similarity for classifying data into its neighbor clusters by the dynamic kernel functions, where the noisy data will be rejected by being given low reliability. The reliability for classifying data is measured by a dynamic kernel function whose window size will be determined by the triangular relationship from this data to its two nearest clusters. The similarity from a data item to its neighbor clusters is measured by another adaptive kernel function which takes into account not only the similarity from data to clusters but also that between its two nearest clusters. The main contribution of this work lies in introducing the dynamic kernel functions to evaluate both the reliability and similarity for clustering, which makes the proposed algorithm more efficient in dealing with very strong noisy data. Through various experiments, the efficiency and effectiveness of proposed algorithm have been confirmed.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2013EDP7439/_p

Copy

@ARTICLE{e97-d_9_2423,
author={Chunsheng HUA, Juntong QI, Jianda HAN, Haiyuan WU, },
journal={IEICE TRANSACTIONS on Information},
title={Kernel-Reliability-Based K-Means (KRKM) Clustering Algorithm and Image Processing},
year={2014},
volume={E97-D},
number={9},
pages={2423-2433},
abstract={In this paper, we introduced a novel Kernel-Reliability-based K-Means (KRKM) clustering algorithm for categorizing an unknown dataset under noisy condition. Compared with the conventional clustering algorithms, the proposed KRKM algorithm will measure both the reliability and the similarity for classifying data into its neighbor clusters by the dynamic kernel functions, where the noisy data will be rejected by being given low reliability. The reliability for classifying data is measured by a dynamic kernel function whose window size will be determined by the triangular relationship from this data to its two nearest clusters. The similarity from a data item to its neighbor clusters is measured by another adaptive kernel function which takes into account not only the similarity from data to clusters but also that between its two nearest clusters. The main contribution of this work lies in introducing the dynamic kernel functions to evaluate both the reliability and similarity for clustering, which makes the proposed algorithm more efficient in dealing with very strong noisy data. Through various experiments, the efficiency and effectiveness of proposed algorithm have been confirmed.},
keywords={},
doi={10.1587/transinf.2013EDP7439},
ISSN={1745-1361},
month={September},}

Copy

TY - JOUR
TI - Kernel-Reliability-Based K-Means (KRKM) Clustering Algorithm and Image Processing
T2 - IEICE TRANSACTIONS on Information
SP - 2423
EP - 2433
AU - Chunsheng HUA
AU - Juntong QI
AU - Jianda HAN
AU - Haiyuan WU
PY - 2014
DO - 10.1587/transinf.2013EDP7439
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E97-D
IS - 9
JA - IEICE TRANSACTIONS on Information
Y1 - September 2014
AB - In this paper, we introduced a novel Kernel-Reliability-based K-Means (KRKM) clustering algorithm for categorizing an unknown dataset under noisy condition. Compared with the conventional clustering algorithms, the proposed KRKM algorithm will measure both the reliability and the similarity for classifying data into its neighbor clusters by the dynamic kernel functions, where the noisy data will be rejected by being given low reliability. The reliability for classifying data is measured by a dynamic kernel function whose window size will be determined by the triangular relationship from this data to its two nearest clusters. The similarity from a data item to its neighbor clusters is measured by another adaptive kernel function which takes into account not only the similarity from data to clusters but also that between its two nearest clusters. The main contribution of this work lies in introducing the dynamic kernel functions to evaluate both the reliability and similarity for clustering, which makes the proposed algorithm more efficient in dealing with very strong noisy data. Through various experiments, the efficiency and effectiveness of proposed algorithm have been confirmed.
ER -