UMBC High Performance Computing Facility
Please note that this page is under construction. We are documenting the
240-node cluster maya that will be available after Summer 2014.
Currently, the 84-node cluster tara still operates independently,
until it becomes part of maya at the end of Summer 2014.
Please see the 2013 Resources Pages under the Resources tab for tara information.
Distributed Principal Direction Divisive Partitioning
Jacob Kogan, Department of Mathematics and Statistics
Clustering is used in a number of traditionally distant fields to describe methods for grouping of unlabeled data. Clustering very large datasets is a contemporary data mining challenge. This project concerns an application of Principal Direction Divisive Partitioning clustering algorithm (PDDP) introduced by D. Boley to a dataset residing in a number of computers connected in a network. Performance of PDDP and Distributed PDDP for datasets of moderate size will be compared.