---------- Forwarded Message ----------
Subject: [Announcement] CFP: A special issue of Data Mining and Knowledge Discovery journal Date: Thursday 07 October 2004 23:33 From: Computational Science Announcements computational.science@optimanumerics.com To: computational.science@optimanumerics.com
*Call for Papers*
* *
*/Data Mining and Knowledge Discovery/**: A Special Issue on***
*Mining Multiple Data Sources: Local Pattern Analysis*
* *
Many large organizations have multiple data sources, such as different branches of a multi-national company. Also, as the Web has emerged as a large, distributed data repository, it is easy nowadays to access a multitude of data sources. Therefore, companies must confront the multiple data source mining problem. Mining local patterns at different data sources and forwarding the local patterns (rather than the original raw data) to a centralized place for global pattern analysis provides a feasible way to deal with multiple data source problems. As such the local patterns at each data source may be required for that data source in the first instance, so knowledge discovery at each data source is also important and useful.
/Local pattern analysis/ is an in-place strategy specifically designed for mining multiple data sources, providing a feasible way to generate globally interesting models from data in multidimensional spaces. With local pattern analysis, one can better understand the distribution and inconsistency of local/global data patterns, and develop high-performance data mining systems to deal with multiple data sources in which local patterns are fused to make global patterns.
Although the data collected from the Web brings us opportunities in improving the quality of decisions, it generates a significant challenge: how to efficiently identify quality knowledge from different data sources and how to integrate them. This problem is difficult to solve due to the facts that multiple data source mining is a procedure of searching for useful patterns in multidimensional spaces; and putting all data together from different sources might amass a huge database for centralized processing and cause problems such as data privacy breaches, data inconsistency, data conflict, and irrelevant data.
This special issue will provide a leading forum for timely, in-depth presentation of progress in the theory and principles underlying local pattern analysis for multiple data source mining.
*Topics of Interest *
We solicit papers on the following non-exhaustive list of topics pertaining to multiple data source mining:
·Foundational issues
·Application case studies
·Data privacy issues
·Data cleansing, data preparation, data/pattern selection, conflict and inconsistency resolution
·Data/pattern clustering, data source classification
·Ontology
·Local pattern analysis and fusion
·Post-processing of local patterns
·Resource-bounded local pattern analysis
·New solutions for multiple data source mining
·Distributed and parallel data mining
*Submission Guidelines*
Please follow the guideline of the submissions on: http://www.kluweronline.com/issn/1384-5810/contents **
*Important Dates*
Submission Deadline March 25, 2005
Author Notification July 20, 2005
Camera-readies Due September 5, 2005
Special issue to be published in First half of 2006
*Special Issue Guest Editors*
*Dr. Shichao Zhang http://www-staff.it.uts.edu.au/%7Ezhangsc/** (*University of Technology, Sydney, Australia)
*Prof. Xindong Wu http://www.cs.uvm.edu/%7Exwu/home.html* (University of Vermont, USA)
*Prof. Mohammed J. Zaki http://www.cs.rpi.edu/%7Ezaki/* (Rensselaer Polytechnic Institute, USA)
--------------------------------------------------------------------- To unsubscribe, e-mail: computational.science-unsubscribe@OptimaNumerics.com For additional commands, e-mail: computational.science-help@OptimaNumerics.com
Computational Science mailing list hosting is provided by OptimaNumerics (http://www.OptimaNumerics.com) ---------------------------------------------------------------------
-------------------------------------------------------