Computational and Mathematical Methods in Medicine
Volume 2013 (2013), Article ID 587564, 13 pages
Research Article

A Soft Computing Based Approach Using Modified Selection Strategy for Feature Reduction of Medical Systems

1Department of Electronic and Computer Education, Technical Education Faculty, Selcuk University, Selcuklu, 42003 Konya, Turkey
2Department of Computer Engineering, Faculty of Technology, Selcuk University, 42003 Konya, Turkey
3Department of Urology, Ankara University Faculty of Medicine, 06100 Ankara, Turkey

Received 10 December 2012; Revised 10 February 2013; Accepted 16 February 2013

Academic Editor: Guang Wu

Copyright © 2013 Kursat Zuhtuogullari et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.


The systems consisting high input spaces require high processing times and memory usage. Most of the attribute selection algorithms have the problems of input dimensions limits and information storage problems. These problems are eliminated by means of developed feature reduction software using new modified selection mechanism with middle region solution candidates adding. The hybrid system software is constructed for reducing the input attributes of the systems with large number of input variables. The designed software also supports the roulette wheel selection mechanism. Linear order crossover is used as the recombination operator. In the genetic algorithm based soft computing methods, locking to the local solutions is also a problem which is eliminated by using developed software. Faster and effective results are obtained in the test procedures. Twelve input variables of the urological system have been reduced to the reducts (reduced input attributes) with seven, six, and five elements. It can be seen from the obtained results that the developed software with modified selection has the advantages in the fields of memory allocation, execution time, classification accuracy, sensitivity, and specificity values when compared with the other reduction algorithms by using the urological test data.