@article{Boley97principaldirection, abstract = {We propose a new algorithm capable of partitioning a set of documents or other samples based on an embedding in a high dimensional Euclidean space (i.e. in which every document is a vector of real numbers). The method is unusual in that it is divisive, as opposed to agglomerative, and operates by repeatedly splitting clusters into smaller clusters. The splits are not based on any distance or similarity measure. The documents are assembled in to a matrix which is very sparse. It is this sparsity that permits the algorithm to be very efficient. The performance of the method is illustrated with a set of text documents obtained from the World Wide Web. Some possible extensions are proposed for further investigation.}, author = {Boley, Daniel}, interhash = {281afd06bd3e21ec3ef212da4ec18ee0}, intrahash = {bca740460f14035af773f665887b6fa4}, journal = {Data Mining and Knowledge Discovery}, pages = {325--344}, title = {Principal Direction Divisive Partitioning}, volume = 2, year = 1997 } @article{journals/ida/SavaresiB04, author = {Savaresi, Sergio M. and Boley, Daniel}, ee = {http://iospress.metapress.com/openurl.asp?genre=article&issn=1088-467X&volume=8&issue=4&spage=345}, interhash = {9d14ed33e5f37037919308b674eb2b29}, intrahash = {dfeb37ef40d8e8a2e740baa8e3a9cd0e}, journal = {Intell. Data Anal.}, number = 4, pages = {345-362}, title = {A comparative analysis on the bisecting K-means and the PDDP clustering algorithms.}, url = {http://www-users.cs.umn.edu/~boley/publications/papers/savaresi04.pdf}, volume = 8, year = 2004 } @misc{ieKey, author = {Boley, Daniel and Gini, Maria and Gross, Robert and Han, Eui-Hong (Sam) and Hastings, Kyle and Karypis, George and Kumar, Vipin and Mobasher, Bamshad and Moore, Jerome}, date = {1999}, interhash = {d544ef5463da700ac7209b61b5bc7eef}, intrahash = {1a1d7962e0dbc3b0afac99911db093e1}, journal = {To appear in Decision Support Systems Journal}, title = {"Partitioning-Based Clustering for Web Document Categorization}, year = 1999 } @inproceedings{BoleySIAM2002, author = {Savaresi, Sergio M. and Boley, Daniel and Bittanti, Sergio and Gazzaniga, Giovanna}, booktitle = {Proceedings of the Second SIAM International Conference on Data Mining, Arlington, VA, USA, April 11-13, 2002}, editor = {Grossman, Robert L. and Han, Jiawei and Kumar, Vipin and Mannila, Heikki and Motwani, Rajeev}, interhash = {fc9b90b549c8f7508e949aa388b2d8d0}, intrahash = {55fa1df0f552a42971753aa40b702615}, publisher = {SIAM}, title = {Cluster Selection in Divisive Clustering Algorithms}, year = 2002 }