Comparison of genetic algorithm and sequential search methods for classifier subset selection
Hongwei Hao, Cheng-Lin Liu, Hiroshi Sako · 2005
Classifier subset selection (CSS) from a large ensemble isan effective way to design multiple classifier systems(MCSs). Given a validation dataset and a selectioncriterion, the task of CSS is reduced to searching thespace of classifier subsets to find the optimal subset. Thisstudy investigates the search efficiency of geneticalgorithm (GA) and sequential search methods for CSS.In experiments of handwritten digit recognition, we selecta subset from 32 candidate classifiers with aim to achievehigh accuracy of combination. The results show that inrespect of optimality, no method wins others in all cases.All the methods are very fast except the generalized plus land take away r(GPTA) method.