Title :
A Computational Intelligence Approach for Ranking Risk Factors in Preterm Birth
Author :
Zaharie, Daniela ; Holban, Stefan ; Lungeanu, Diana ; Navolan, Dan
Author_Institution :
Fac. of Math. & Comput. Sci., West Univ. of Timisoara, Timisoara
fDate :
Yearly 17 2007-May 18 2007
Abstract :
The aim of this paper is to propose a filter, based on a multi-objective evolutionary algorithm, for attributes´ ranking in the context of a data mining task. The behavior of this filter is analyzed for the problem of ranking risk factors in preterm birth. The results obtained by applying the proposed evolutionary approach are compared with rankings obtained by applying some classical attributes selection methods and a logistic regression procedure. The influence of the ranking on a supervised classification (based on a radial basis function neural network) is also analyzed and the results suggest that the evolutionary approach provides a good quality ranking.
Keywords :
data analysis; data mining; genetic algorithms; learning (artificial intelligence); medical computing; pattern classification; radial basis function networks; regression analysis; risk analysis; attribute ranking; attribute selection; computational intelligence approach; data mining; logistic regression; medical data analysis; multiobjective evolutionary algorithm; preterm birth; radial basis function neural network; risk factor ranking; supervised classification; Biomedical informatics; Computational efficiency; Computational intelligence; Computer science; Data mining; Evolutionary computation; Filters; Mathematics; Pathology; Space exploration;
Conference_Titel :
Applied Computational Intelligence and Informatics, 2007. SACI '07. 4th International Symposium on
Conference_Location :
Timisoara
Print_ISBN :
1-4244-1234-X
DOI :
10.1109/SACI.2007.375498
