Automatic subspace clustering of high dimensional data for data mining applications Export

@inproceedings{citeulike:816500, abstract = {Data mining applications place special requirements on clustering algorithms including: the ability to find clusters embedded in subspaces of high dimensional data, scalability, end-user comprehensibility of the results, non-presumption of any canonical data distribution, and insensitivity to the order of input records. We present CLIQUE, a clustering algorithm that satisfies each of these requirements. CLIQUE identifies dense clusters in subspaces of maximum dimensionality. It generates cluster descriptions in the form of DNF expressions that are minimized for ease of comprehension. It produces identical results irrespective of the order in which input records are presented and does not presume any specific mathematical form for data distribution. Through experiments, we show that CLIQUE efficiently finds accurate cluster in large high dimensional datasets.}, address = {New York, NY, USA}, author = {Agrawal, Rakesh and Gehrke, Johannes and Gunopulos, Dimitrios and Raghavan, Prabhakar}, booktitle = {SIGMOD '98: Proceedings of the 1998 ACM SIGMOD international conference on Management of data}, citeulike-article-id = {816500}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=276314}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/276304.276314}, doi = {10.1145/276304.276314}, isbn = {0-89791-995-5}, location = {Seattle, Washington, United States}, pages = {94--105}, posted-at = {2007-09-11 10:05:30}, priority = {5}, publisher = {ACM}, title = {Automatic subspace clustering of high dimensional data for data mining applications}, url = {http://dx.doi.org/10.1145/276304.276314}, year = {1998} }

TY - CONF ID - citeulike:816500 L3 - citeulike-article-id:816500 N2 - Data mining applications place special requirements on clustering algorithms including: the ability to find clusters embedded in subspaces of high dimensional data, scalability, end-user comprehensibility of the results, non-presumption of any canonical data distribution, and insensitivity to the order of input records. We present CLIQUE, a clustering algorithm that satisfies each of these requirements. CLIQUE identifies dense clusters in subspaces of maximum dimensionality. It generates cluster descriptions in the form of DNF expressions that are minimized for ease of comprehension. It produces identical results irrespective of the order in which input records are presented and does not presume any specific mathematical form for data distribution. Through experiments, we show that CLIQUE efficiently finds accurate cluster in large high dimensional datasets. CY - Seattle, Washington, United States SN - 0-89791-995-5 AD - New York, NY, USA EP - 105 TI - Automatic subspace clustering of high dimensional data for data mining applications PB - ACM T2 - SIGMOD '98: Proceedings of the 1998 ACM SIGMOD international conference on Management of data SP - 94 AU - Agrawal, Rakesh AU - Gehrke, Johannes AU - Gunopulos, Dimitrios AU - Raghavan, Prabhakar PY - 1998/// UR - http://dx.doi.org/10.1145/276304.276314 ER -