Implementation and integration of clustering method to web based clustering engine
In this project, two tasks have been implemented. First, a new semi-supervised collaborative clustering process has been diligently researched and implemented. Second, an in-house developed unsupervised clustering algorithm HFCR has been successfully integrated into a web based clustering engine Car...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project |
| Language: | English |
| Published: |
2012
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/49857 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Nanyang Technological University |
| Language: | English |
| Summary: | In this project, two tasks have been implemented. First, a new semi-supervised collaborative clustering process has been diligently researched and implemented. Second, an in-house developed unsupervised clustering algorithm HFCR has been successfully integrated into a web based clustering engine Carrot2 in Eclipse. The report covers the literature review on both the clustering methods used in this project. It has also documented the design and implementation related to both the algorithms. Preliminary simulations were carried out for the collaborative process on a high dimensional dataset, RE-1. The collaborative process used a small set of labelled samples to discover other relevant patterns in the dataset. The results obtained are tabulated and thoroughly discussed. A quick test on HFCR with a given user query in Carrot2 framework has been carried out to demonstrate and report the success of the implementation. |
|---|