Journal article
A novel cluster ensemble approach effected by subspace similarity
Intelligent data analysis, Vol.20(3), pp.561-574
01/01/2016
DOI: 10.3233/IDA-160820
Abstract
We study the cluster ensemble problem and propose a cluster ensemble approach based on subspace similarity (CEASS). From a subspace similarity perspective, we seek the optimal subspace which is most similar to the given subspaces corresponding to the cluster solutions to be combined. We formulate the cluster ensemble problem as an optimization problem of minimizing the squared sum of Euclidean distances between the standard orthogonal basis vectors of the target subspace and the given subspaces. We derived an explicit solution to the preceding problem in terms of singular value decomposition. Moreover, the solution consists of the low dimensional embeddings of instances. Finally, K-means algorithm with the minimum-maximum principle is utilized to cluster instances according to their coordinates in the embedding space. In particular, we circumvent the initialization problem of K-means by employing CEASS that combines different K-means clustering solutions obtained from random initialization to obtain a stable clustering result. We evaluate and compare CEASS so constructed with several other state-of-art cluster ensemble algorithms using nine real world datasets. Experimental results demonstrate that CEASS generally outperforms other algorithms in terms of normalized mutual information and F1 measure. In addition, CEASS is extremely efficient compared to hierarchy clustering algorithms.
Details
- Title: Subtitle
- A novel cluster ensemble approach effected by subspace similarity
- Creators
- Sen Xu - University of IowaKung-Sik Chan - University of IowaTian Zhou - Harbin Engineering UniversityJun Gao - Yancheng Institute of TechnologyXianfeng Li - Yancheng Institute of TechnologyXiaopeng Hua - Yancheng Institute of Technology
- Resource Type
- Journal article
- Publication Details
- Intelligent data analysis, Vol.20(3), pp.561-574
- Publisher
- IOS PRESS
- DOI
- 10.3233/IDA-160820
- ISSN
- 1088-467X
- eISSN
- 1571-4128
- Number of pages
- 14
- Grant note
- Jiangsu Province Qing Lan Project 13KJB520024 / Nature Science Foundation of the Jiangsu Higher Education Institutes of China U01 HL114494; NIHRO1HL089897 / US National Institutes of Health (NIH grant) BY2014108-20 / Industry Education Research Prospective Project of Jiangsu Province of China XKR2011019 / Talent Introduction Project of Yancheng Institute of Technology BE2014679 / Science and Technology Support Program of Jiangsu Province 61105057; 61272210; 61375001 / National Natural Science Foundation of China
- Language
- English
- Date published
- 01/01/2016
- Academic Unit
- Statistics and Actuarial Science; Radiology
- Record Identifier
- 9984257612102771
Metrics
7 Record Views