On hard c-means using quadratic penalty-vector regularization for uncertain data

  • Authors:

  • Yasunori Endo;Arisa Taniguchi;Aoi Takahashi;Yukihiro Hamasuna

  • Affiliations:

  • Department of Risk Engineering, University of Tsukuba, Tsukuba, Ibaraki, Japan;Graduate School of Systems and Information Engineering, University of Tsukuba, Tsukuba, Ibaraki, Japan;Graduate School of Systems and Information Engineering, University of Tsukuba, Tsukuba, Ibaraki, Japan;Department of Informatics, Kinki University, Kowakae, Higashiosaka, Osaka, Japan

  • Venue:
  • MDAI'11 Proceedings of the 8th international conference on Modeling decisions for artificial intelligence
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

Clustering is one of the unsupervised classification techniques of the data analysis. Data are transformed from a real space into a pattern space to apply clustering methods. However, the data cannot be often represented by a point because of uncertainty of the data, e.g., measurement error margin and missing values in data. In this paper, we introduce quadratic penalty-vector regularization to handle such uncertain data into hard c-means (HCM) which is one of the most typical clustering algorithms. First, we propose a new clustering algorithm called hard c-means using quadratic penalty-vector regularization for uncertain data (HCMP). Second, we propose sequential extraction hard c-means using quadratic penalty-vector regularization (SHCMP) to handle datasets whose cluster number is unknown. Moreover, we verify the effectiveness of our propose algorithms through some numerical examples.