High-dimensional multi-view dataset pre-processing and clustering
The objective of this project is two-fold: the first one is to perform pre-processing on high-dimensional multi-view datasets and to investigate potential applications of new data mining techniques with the new datasets. The second part of the project is to design and implement an existing...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project |
| Language: | English |
| Published: |
2012
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/49881 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Nanyang Technological University |
| Language: | English |
| Summary: | The objective of this project is two-fold: the first one is to perform pre-processing on
high-dimensional multi-view datasets and to investigate potential applications of new
data mining techniques with the new datasets.
The second part of the project is to design and implement an existing clustering
algorithm and conduct extensive experimental study to test the performances of the
clustering algorithm on various text benchmark datasets. This report highlights the
implementation of the pre-processing approach for the data processing. It also includes
the design and implementation ideas of the clustering algorithm Semi-Supervised
Spherical K-Means and the simulation results. The performances of SS-SKM are
documented and reported. |
|---|