Journal of the Korean Data and Information Science Society

한국데이터정보과학회 (The Korean Data and Information Science Society)
권호 표지

More Efficient k-Modes Clustering Algorithm

  • 발행 : 2005.08.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

A hard-type centroids in the conventional clustering algorithm such as k-modes algorithm cannot keep the uncertainty inherently in data sets as long as possible before actual clustering(decision) are made. Therefore, we propose the k-populations algorithm to extend clustering ability and to heed the data characteristics. This k-population algorithm as found to give markedly better clustering results through various experiments.

키워드

참고문헌

  1. Pattern Recognition v.24 no.6 Symbolic clustering using a new dissimilaity measure Gowda, K.C.;Diday, E.
  2. Data Mining and Knowledge Discriminations v.2 no.3 Extensions to the k-modes algorithm for clustering large data sets with categorical values Huang, Z.
  3. IEEE Tr. Fuzzy Systems v.7 no.4 A fuzzy k-modes algorithm for clustering categorical data Huang, Z.;Ng, M.K.
  4. Methods of Multivariate Analysis Rencher, A.
  5. Categorical Data Analysis Alan, A.