Effectiveness of Rotation Forest in Meta-learning Based Gene Expression Classification

A lot of research has been done in the field of assembling classifiers in ensembles and on the other hand selecting the most appropriate single classifiers for a given problem which was solved by meta-learning techniques. This paper presents application of recently proposed ensemble of classifiers called Rotation Forest to Grading meta-learning scheme, where it is used as one of the base classifiers and meta-level classifier at the same time. Our proposed Grading variation is compared to four widely used classifiers on 14 datasets from the domain of gene expression classification problems. Experimental evaluations show that using Rotation Forest at meta-level most significantly impacts the accuracy of Grading scheme and confirms that it can be used for estimation of classifiers regions of strong and weak classification.