Title :
A robust approach for classifying unknown data in medical diagnosis problems
Author :
Garc?a-laencina, Pedro J. ; Vidal, Anibal R Figueiras ; Sancho-gomez, Jose-luis
Author_Institution :
Univ. Politec. de Cartagena, Cartagena
Abstract :
Unknown data is a common drawback in medical diagnosis applications. A recommended procedure for dealing with unknown values is missing data imputation, i.e., estimating and filling missing values using all the available information. This work* presents a robust approach for incomplete data classification using an enhanced version of the K Nearest Neighbours algorithm. Experimental results on medical diagnosis databases show the usefulness of this approach.
Keywords :
medical diagnostic computing; pattern classification; K Nearest Neighbours algorithm; incomplete data classification; medical diagnosis problems; missing data imputation; unknown values; Biomedical equipment; Databases; Filling; Machine learning; Machine learning algorithms; Medical diagnosis; Medical diagnostic imaging; Medical tests; Pattern classification; Robustness; Imputation; Medical diagnosis; Missing Data; Pattern Classification;
Conference_Titel :
Automation Congress, 2008. WAC 2008. World
Print_ISBN :
978-1-889335-38-4
Electronic_ISBN :
978-1-889335-37-7
