PENYARINGAN CONSTRAINT PADA PROSES ACTIVE CONSTRAINT ACQUISITION

Abstract

The objective of giving the constraint to semi-supervised clustering, is the increasing of clustering result accuracy. Sometime, it does not give any effect, even can decrease the clustering result accuracy. So, to solve that, before clustering begin, we must filter the constraint. We will filter the constraint by constraint utility, informativeness and coherence. The experiment result shows, that the increasing of clustering result accuracy with giving the high infomativeness and coherence, can not valid for any kind of data. In Iris, Ionosphere, and Digit data, it will give better results, but in Wine, Protein, and Letter give the opposite results.

Keywords: Semi-supervised clustering, constraint, informativeness, coherence

REFERENCE

[1].Basu, Sugato, http://www.cs.utexas.edu/users/ml/risc, diakses pada bulan November 2007.

[2].Basu, Sugato., Banerjee, Arindam., Mooney, Raymond, Active Semi-Supervision for Pairwise Constrained Clustering, Proceedings of the SIAM International Conference on Data Mining (SDM-2004), pp. 333-344, Lake Buena Vista, FL, April, 2004.

[3].Basu, Sugato., Mikhail, Bilenko., Arindam, Banerjee., Raymond, Mooney, Probabilistic Semi-supervised Clustering with Constraints, dalam buku Semi-supervised learning, The MIT Press, 2006.

[4].Bilenko, Mikhail., Basu, Sugato., Mooney, Raymond.(2004), Integrating constraints and metric learning in semi-supervised clustering, Procedings of the 21 st International Conference on Machine Learning, ICML-2004, Banff, Canada, 81-88.

[5].Davidson, Ian., Wagstaff, Kiri., Basu, Sugato, Measuring Constraint-Set Utility for Partitional Clustering Algorithms, dalam Proceedings of the Tenth European Conference on Principles and Practice of Knowledge Discovery in Databases (PKDD), halaman 115-126, 2006.

[6].Han, Jiawei., M, Kamber, Data mining: concepts and techniques, penerbit Morgan Kaufmann, 449-451, 2006.

[7].Wagstaff, Kiri, Value, Cost, and Sharing: Open Issues in Constrained Clustering, dalam Proceedings of the Fifth International Workshop on Knowledge Discovery in Inductive Databases (KDID), halaman 1-7, 2006.

Advertisements

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s