Paper Info
Title
Large scale data mining to improve usability of data - an intelligent archive testbed
Abstract
Research in certain scientific disciplines-including Earth science, particle physics, and astrophysics-continually faces the challenge that the volume of data needed to perform valid scientific research can at times overwhelm even a sizable research community. The desire to improve utilization of this data gave rise to the Intelligent Archives project, which seeks to make data archives active participants in a knowledge building system capable of discovering events or patterns that represent new information or knowledge.Data mining can automatically discover patterns and events, but it is generally viewed as unsuited for large-scale use in disciplines like Earth science that routinely involve very high data volumes. Dozens of research projects have shown promising uses of data mining in Earth science, but all of these are based on experiments with data subsets of a few gigabytes or less, rather than the terabytes or petabytes typically encountered in operational systems. To bridge this gap, the Intelligent Archives project is establishing a testbed with the goal of demonstrating the use of data mining techniques in an operationally-relevant environment. This paper discusses the goals of the testbed and the design choices surrounding critical issues that arose during testbed implementation.
Year
DOI
Venue
2005
10.1109/IGARSS.2005.1526050
Geoscience and Remote Sensing Symposium, 2005. IGARSS '05. Proceedings. 2005 IEEE International
Keywords
Field
DocType
geoscience,data mining,knowledge representation,data storage,information systems,usability,system testing,artificial intelligence,earth sciences,remote sensing
Information system,Data mining,Knowledge representation and reasoning,Computer science,System testing,Computer data storage,Remote sensing,Usability,Testbed
Conference
Volume
ISBN
Citations 
8
0-7803-9050-4
0
PageRank 
References 
Authors
0.34
0
4
Name
Order
Citations
PageRank
H. K. Ramapriyan110624.06
David Isaac200.34
Wenli Yang300.34
Steve Morse400.34