Earticle

초록

영어

This paper discusses one method of clustering a high dimensional dataset using dimensionality reduction and context dependency measures (CDM). First, the dataset is partitioned into a predefined number of clusters using CDM. Then, context dependency measures are combined with several dimensionality reduction techniques and for each choice the data set is clustered again. The results are combined by the cluster ensemble approach. Finally, the Rand index is used to compute the extent to which the clustering of the original dataset (by CDM alone) is preserved by the cluster ensemble approach.

목차

Abstract
 1. Introduction
 2. Context-Based Proximity Measurements [19]
 3. Context-dependent Cluster Structure
 4. Similarity Within and Between Clusters 0
  4.1. Similarity between a data item and a cluster
  4.2. Similarity between clusters
 5. Dimensionality Reduction Approaches
  5.1. The Variance Approach (VAR)
  5.2. The Combined Approach (CA)
  5.3. The Direct Approach (DA)
  5.4. Top-down Approach (TD)
  5.5. The Bottom-up Approach (BU)
  5.6. The Weighted Attribute Frequency Approach (WAF)
  5.7. The Best Clustering Performance Approach (BCP)
 6. Clustering in a High Dimensional Space based on Clustering in Reduced Dimensions
 7. Illustrative Experimental Results
 8. Conclusion
 Acknowledgments
 References

키워드

저자

• Augustine S. Nsang [ CS Department, School of Inf. Tech. and Computing, American University of Nigeria Yola By-Pass, PMB 2250, Yola, Nigeria ]
• Irene Diaz [ Department of Computer Science, University of Oviedo, Spain ]
• Anca Ralescu [ EECS Department, University of Cincinnati, Cincinnati, OH 45221-0030, USA ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Advanced Science and Technology

• 간기

  월간

• pISSN

  2005-4238

• 수록기간

  2008~2016

• 십진분류

  KDC 505 DDC 605