DocumentCode
436366
Title
LEFRA: learning from associations
Author
Hashemi, R.R. ; LeBlanc, L. ; Westgeest, D.J. ; Tyler, A.A.
Author_Institution
Department of Computer Science, Armstrong Atlantic State University, Savannah, CA 31419
Volume
17
fYear
2004
fDate
June 28 2004-July 1 2004
Firstpage
549
Lastpage
554
Abstract
In data mining, a Multi-level Association Analysis (MAA) produces a set of association rules. These rules mainly identify those values of multiple attributes that are associated to cach other. In this paper, we introduce a new learning paradigm based on association rules called ??Learning from Association (LEFRA)?? which is used as a part of 8 predictive system to predict the effect of a number of carcinogens on liver. The validity of the proposed learning paradigm is established by comparing its performance with the performance of logistic regression which has been applied on the same dataset .
Keywords
Algorithm design and analysis; Computer science; Data mining; Educational institutions; Logistics; Optical wavelength conversion; Association Analysis; Data Mining; Learning from Association; Predictive Systems;
fLanguage
English
Publisher
ieee
Conference_Titel
Automation Congress, 2004. Proceedings. World
Conference_Location
Seville
Print_ISBN
1-889335-21-5
Type
conf
Filename
1439424
Link To Document