Francesco Maiorana and Giacomo Fazio
Knowledge discovery from text, parallel clustering, cloud computing
In this paper we present a Knowledge Discovery from Text (KDT) framework and its applications to bioinformatics into a cloud architecture. The text mining framework consists of three building blocks: document retrieval and indexing; classification; and relevant class feature identification and discovery of associations. The proposed architecture is deployed on a private cloud architecture using the Eucalyptus project. A case study is described and results are reported.
Important Links:
Go Back
