Prev 
Up 
Next
The modules are
clustered automatically according to different aspects:
- direct
dependencies in between components (attracting force)
- dependencies to
common neighbors (attracting force)
- dependencies to
different neighbors (distracting force)
- similar names
(attracting force)
The inner nodes are
associated with the similarity of the two subtrees clustered
together. Note how the similarity decreases the closer you get to
the root of the tree.
The factors of the
underlying metric can be adjusted to your needs.
Last modified: Wed Aug 27 16:46:21 MET DST 2003