Bicluster
Jump to navigation
Jump to search
A Bicluster is a Cluster that can be mapped to a Biclique.
- Context:
- It can be identified by a Biclustering Task.
- See: Biclique.
References
2009
- http://en.wikipedia.org/wiki/Biclustering
- Biclustering, co-clustering, or two-mode clustering is a data mining technique which allows simultaneous clustering of the rows and columns of a matrix.
- The term was first introduced by Mirkin.
- Given a set of [math]\displaystyle{ m }[/math] rows in [math]\displaystyle{ n }[/math] columns (i.e., an m×n matrix), the biclustering algorithm generates biclusters - a subset of rows which exhibit similar behavior across a subset of columns, or vice versa.
- The complexity of the biclustering problem depends on the exact problem formulation, and particularly on the merit function used to evaluate the quality of a given bicluster. However most interesting variants of this problem are NP-complete requiring either large computational effort or the use of lossy heuristics to short-circuit the calculation.
- Different biclustering algorithms have different definitions of bicluster. They are:
- Bicluster with constant values (a),
- Bicluster with constant values on rows or columns (b, c),
- Bicluster with coherent values (d, e).
1996
- (Mirkin, 1996) ⇒ Boris Mirkin. (1996). “Mathematical Classification and Clustering.” Kluwer Academic Publishers. ISBN 0792341597.