 |
Our aim is to come up with a sound and concrete solution so that the gigantic volume of unsorted data could be fitted in to a virtual hierarchy to make extracting relevant data more feasible.
|
 |
Recently we did a research on selecting the best clustering alogorithm which optimize our
requirements in the project.
|
|
| Our recent work |
Recently a literature survey has been carried out to decide on the optimum algorithm which could be used to obtain the document clusters. Lot of clustering algorithms were suggested at first such as self organizing maps, K - means and GSOM(Growing Self Organizing Maps). So we considered the strengths and weaknesses of each clustering algorithm and finaly selected the GSOM as our clustering algorithm.
Taking in to the consideration of the analysis we did, we thought of publishing a research paper also. That may help any one who interested in text clustering feild and people who are willing to study to the depth. |
|
 |
What we do at the moment
At this moment we are preparing the system design specification in detailed way. This will include several UML diagrams such as use case, sequence, component, class etc. |
|
|
