Earticle

초록

영어

Spectral clustering is a powerful technique in clustering specially when the structure of data is not linear and classical clustering methods lead to fail. In this paper, we propose a spectral clustering algorithm with a feature selection schema based on extracted features of Kernel PCA. In the proposed algorithm, selecting appropriate vectors is dependent upon entropy of clusters on these vectors and weighting method is influenced by sum of the existence gap between clusters and entropy of the vectors. Tuning the parameters has a great effect on the results of spectral clustering techniques. In the ideal case, comparing our method with NJW and Kernel K-Means indicate the successful of the proposed algorithm.

목차

Abstract
 1. Introduction
 2. Preliminaries
  2.1. Spectral Clustering
  2.2. Kernel Clustering Methods
  2.3. Kernel PCA and Weighted Kernel PCA
 3. Proposed Method
  3.1. The Importance of Eigenvector Selection
  3.2. Eigenvector Selection and Weighting Schema
  3.3. Proposed Algorithm
  3.4. Parameter Selection
  3.5. Out-of-sample Extension
 4.Experimental Results
  4.1.Toy Problems
  4.2.Experiments on UCI benchmark datasets
  4.3.Robustness Analysis
 5. Conclusion
 References

키워드

저자

• Soheila Ashkezari Toussi [ Computer Department, Ferdowsi University of Mashhad, Iran ]
• Hadi Sadoghi Yazdi [ Computer Department, Ferdowsi University of Mashhad, Iran ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Signal Processing, Image Processing and Pattern Recognition

• 간기

  격월간

• pISSN

  2005-4254

• 수록기간

  2008~2016

• 십진분류

  KDC 505 DDC 605