The Centroid Decomposition: Relationships between Discrete Variational Decompositions and SVDs
SIAM Journal on Matrix Analysis and Applications
Principal Direction Divisive Partitioning
Data Mining and Knowledge Discovery
Algebraic Techniques for Analysis of Large Discrete-Valued Datasets
PKDD '02 Proceedings of the 6th European Conference on Principles of Data Mining and Knowledge Discovery
Nonorthogonal decomposition of binary matrices for bounded-error data compression and analysis
ACM Transactions on Mathematical Software (TOMS)
Hi-index | 0.00 |
The problem of clustering continuous valued data hasbeen well studied in literature. Its application to microarrayanalysis relies on such algorithms as k-means, dimensionalityreduction techniques, and graph-based approaches forbuilding dendrograms of sample data. In contrast, similarproblems for discrete-attributed data are relatively unexplored.An instance of analysis of discrete-attributed dataarises in detecting co-regulated samples in microarrays. Inthis papel, we present an algorithm and a software framework,PROXIMUS, for error-bounded clustering of high-dimensionaldiscrete attributed datasets in the context ofextracting co-regulated samples from microarray data. Weshow that PROXIMUS delivers outstanding performance inextracting accurate patterns of gene-expression.