Focused local cluster formation for multidimensional microarray data

Authors:
Keon Myung Lee;Kyung Mi Lee;Chan Hee Lee;Jee-Hyong Lee
Affiliations:
School of Electrical and Computer Engineering and RICIS, Department of Microbiology, Chungbuk National University, Cheongju, Korea;School of Electrical and Computer Engineering and RICIS, Department of Microbiology, Chungbuk National University, Cheongju, Korea;School of Electrical and Computer Engineering and RICIS, Department of Microbiology, Chungbuk National University, Cheongju, Korea;School of Information and Communication Engineering, SungKyunKwan University, Suwon, Korea
Venue:
AEE'08 Proceedings of the 7th WSEAS International Conference on Application of Electrical Engineering
Year:
2008

Citing 6
Cited 0

Subspace clustering for high dimensional data: a review

ACM SIGKDD Explorations Newsletter - Special issue on learning from imbalanced datasets
Cluster Analysis for Gene Expression Data: A Survey

IEEE Transactions on Knowledge and Data Engineering
Comparing Subspace Clusterings

IEEE Transactions on Knowledge and Data Engineering
Exploratory Data Analysis with MATLAB (Computer Science and Data Analysis)

Exploratory Data Analysis with MATLAB (Computer Science and Data Analysis)
A Fast Subspace Clustering Algorithm Based on Pattern Similarity

FSKD '07 Proceedings of the Fourth International Conference on Fuzzy Systems and Knowledge Discovery - Volume 03
Subspace clustering of microarray data based on domain transformation

VDMB'06 Proceedings of the First international conference on Data Mining and Bioinformatics

Quantified Score

Hi-index	0.00

Visualization

Abstract

It is a challenging task to find meaningful clusters in a high dimensional data set due to the curse of dimensionality. Microarray gene expression data is a typical high dimensional one of which dimension goes up to tens of thousands. Subspace clustering is a promising approach to handling such high dimensional data. In microarray data analysis, the analysts sometimes pay special attention to specific subspace clusters rather than overall picture. This paper presents a method to find an interesting subspace cluster in an interactive way. The proposed method makes use of a hierarchical clustering result to select an interest region. The selected interest region plays role of a seed from which a subspace cluster grows up. The proposed method has been implemented as a graphical analysis tool and evaluated very helpful in the microarray data analysis.