HR: 1340h
AN: IN33A-1167    [Abstracts]
TI: Web Service Enabled Data Mining Architecture for Digital Observatories
AU: * Sinha, P
EM: psinha3@uiuc.edu
AF: University of Illinois Urbana Champaign, Civil & Environmental Engg 2523 Hydro Sys Lab 205 N. Mathews, Urbana, IL 61801 United States
AU: Kumar, P
EM: kumar1@uiuc.edu
AF: University of Illinois Urbana Champaign, Civil & Environmental Engg 2523 Hydro Sys Lab 205 N. Mathews, Urbana, IL 61801 United States
AU: Zaslavsky, I
EM: zaslavsk@sdsc.edu
AF: Sandiego Supercomputing Center, UC San Diego, MC 0505, 9500 Gilman Drive, La Jolla, CA 92093-0505 United States
AU: Maidment, D
EM: maidment@mail.utexas.edu
AF: University of Texas, Austin, Civil Engg, 1 University Station C1786, Austin, TX 78712-0273 United States
AU: Mehra, V
EM: vmehra2@uiuc.edu
AF: University of Illinois Urbana Champaign, Civil & Environmental Engg 2523 Hydro Sys Lab 205 N. Mathews, Urbana, IL 61801 United States
AU: Bajcsy, P
EM: pbajcsy@ncsa.uiuc.edu
AF: National Center for Supercomputing Applications, University of Illinois at Urbana-Champaign, 1205 W. Clark St., Urbana, IL 61801 United States
AB: Several agencies such as USGS provide data through various web-sites. These websites are individually complex to navigate, provide data in incongruous format and require data to be downloaded locally for any processing. Web services have emerged as new tool that provide a means of transferring the data over the Internet using standard messaging system (XML). Web services are independent of operating system or programming language used. One of the potentials of web services lie in getting various heterogeneous data from different data sources directly into the application, such as a data mining system. We have designed a scientific workflow in Data to Knowledge (D2K) platform developed by National Center for Supercomputing Application (NCSA) which given a study domain, retrieves all streamflow and various water quality data using the CUAHSI (Consortium of University for Advancement of Hydrologic Science, Inc.) NWIS web services. Time series data mining in the D2K environment can be performed on a selection of these data. The analyses functionalities are extensive and include exploratory visualization (such as probability density function and box plot) as well as sophisticated pattern recognition such as similarity search in the time series. The goal of the project is to provide a robust tool for digital observatories that will enable us to better understand our natural environment system.
DE: 1600 GLOBAL CHANGE
DE: 9800 GENERAL OR MISCELLANEOUS
DE: 9820 Techniques applicable in three or more fields
SC: Earth and Space Science Informatics [IN]
MN: Fall Meeting 2005