Abstract
Noise signi'cantly affects cluster quality. Conventional clustering methods hardly detect clusters in a data set containing a large amount of noise. Projected clustering sheds light on identifying correlation clusters in such a dataset. In order to exclude noise points which are usually scattered in a subspace, data points are projected to form dense areas in the subspace that are regardedas correlation clusters. However, we found that the existing methods for the projected clustering did not work very well with noise data, since they employ randomly generated seeds (micro clusters) to trade-off the clustering quality. In this paper, we propose a divisive method for the projected clustering that does not relyon random seeds. The proposed algorithm is capable of producing higher quality correlation clusters from noise data in a more ef'cient way than an agglomeration projected algorithm. We experimentally show that our algorithm captures correlation clusters in noise data better than a well-known projected clustering method.
Original language | English |
---|---|
Title of host publication | PAKDD 2007 |
Place of Publication | Berlin |
Publisher | Springer-Verlag London Ltd. |
Pages | 639-647 |
Number of pages | 9 |
ISBN (Electronic) | 9783540717003 |
DOIs | |
Publication status | Published - 2007 |
Event | Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD) - Nanjing, China, China Duration: 22 May 2007 → 25 May 2007 |
Conference
Conference | Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD) |
---|---|
Country/Territory | China |
Period | 22/05/07 → 25/05/07 |