Somaraki, V. and McCluskey, T.L. (2012) A robust validation framework for trend mining : a study in diabetic retinopathy. In: Proceedings of The Queen’s Diamond Jubilee Computing and Engineering Annual Researchers’ Conference 2012: CEARC’12. University of Huddersfield, Huddersfield, pp. 63-68. ISBN 978-1-86218-106-9
Abstract

Data mining is concerned with the identification of hidden patterns in data. Trand mining is a branch of data mining that focusses on the process to identify and analyze hidden trends in temporal data. A novel trend mining framework is described in this paper. The framework considers trends in terms of sequences of support values associate with frequent items sets and uses a trend mining algorithm that produces prototypes trends. To validate the framework in the analysis of the generated trends a mechanism is also proposed. The framework is evaluated using longitudinal Diabetic Retinopathy screening data.

Library
Documents
[img]
Preview
Cover page
Cover_pages.pdf - Published Version

Download (1MB) | Preview
[img]
Preview
V_Somaraki_Paper.pdf - Published Version

Download (162kB) | Preview
Statistics

Downloads

Downloads per month over past year

Downloads per month over past year for
"Cover_pages.pdf"

Downloads per month over past year for
"V_Somaraki_Paper.pdf"

Add to AnyAdd to TwitterAdd to FacebookAdd to LinkedinAdd to PinterestAdd to Email