- title = "A Hybrid Approach to Cluster Detection",
- author = "Samir Tout and Junping Sun and William Sverdlik",
- journal = "IAENG International Journal of Computer Science",
- year = "2007",
- volume = "34",
- number = "1",
- month = "15 " # aug,
- keywords = "genetic algorithms, genetic programming, Data Mining, Clustering, Density, Parallelism",
- ISSN = "1819-9224",
-
URL = "
http://www.iaeng.org/IJCS/issues_v34/issue_1/IJCS_34_1_14.pdf",
-
URL = "
http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.148.7725",
- bibsource = "OAI-PMH server at citeseerx.ist.psu.edu",
- contributor = "CiteSeerX",
- language = "en",
- oai = "oai:CiteSeerXPSU:10.1.1.148.7725",
- abstract = "Recent technological advances require computer algorithms that can effectively analyze and classify data on a large scale that was unachievable just a few years ago. For instance, in response to a query, commercial search engines routinely consider web pages amounting into billions while genomic searches may deal with a search space of a similar or even higher magnitude. Clustering algorithms are an ideal choice to quickly categorize data; they are conceptually simple and require little background knowledge. Many clustering algorithms have been introduced in recent decades; but each approach brought along new challenges to consider, such as outlier handling, detection of arbitrary shaped clusters, processing speed, and dependence on user supplied parameters. PYRAMID, or parallel hybrid clustering using genetic programming and multiobjective fitness with density, is a clustering algorithm that we introduced in a previous research. It addresses several of the above challenges by using a combination of data parallelism, a form of genetic programming, and a multi-objective density-based fitness function. This paper summarizes some of the characteristics of PYRAMID along with experiments that were performed on multiple challenging datasets. Empirical results derived from these experiments are presented and future directions are proposed.",
-
notes = "Samir Tout is a consultant with Keane, Inc., 24901
Northwestern Hwy, Southfield, MI 48075 and an adjunct
professor at the Department of Computer Science,
Eastern Michigan University, Ypsilanti, MI,
48197
Junping Sun is a professor at the Graduate School of Computer and Information Sciences, Nova Southeastern University, 3301 College Avenue, Fort Lauderdale, Florida 33314, USA
William Sverdlik is an associate professor at the Department of Computer Science, Eastern Michigan University, Ypsilanti, MI, 48197",
