01911nas a2200193 4500008004100000022001400041245010800055210006900163260011100232300001200343490000700355520111900362100001901481700001501500700002301515700002201538700002601560856013101586 2009 eng d a1386-207300aFeature selection and classification employing hybrid ant colony optimization/random forest methodology0 aFeature selection and classification employing hybrid ant colony aEXECUTIVE STE Y26, PO BOX 7917, SAIF ZONE, 1200 BR SHARJAH, U ARAB EMIRATESbBENTHAM SCIENCE PUBL LTDcJUN a507-5130 v123 a
Accurate classification of instances depends on identification and removal of redundant features. Classification of data having high dimensionality is usually performed in conjunction with an appropriate feature selection method. Feature selection enables identification of the most informative feature subset from the enormously vast search space that can accurately classify the given data. We propose an ant colony optimization (ACO)/random forest based hybrid filter-wrapper search technique, which traverses the search space and selects a feature subset with high classifying ability. We evaluate the performance of our algorithm on four widely studied CoEPrA (Comparative Evaluation of Prediction Algorithms, http://coepra.org) datasets. The performance of the software ants mediated hybrid filter/wrapper approach compares well with the available competition results. Thus, the proposed Ant Colony Optimization based technique can effectively find small feature subsets capable of classifying with a very good accuracy and can be employed for feature subset selection with a high level of confidence.
1 aPatil, Diwakar1 aRaj, Rahul1 aShingade, Prashant1 aKulkarni, Bhaskar1 aJayaraman, Valadi, K. uhttp://library.ncl.res.in/content/feature-selection-and-classification-employing-hybrid-ant-colony-optimizationrandom-forest-0