The effects of variable selection and dimension reduction methods on the classification model in the small round blue cell tumor dataset.

Objective: The purpose of this study is to investigate and compare the effects different dimension reduction methods (PCA, ICA, PCA + Forward Selection, ICA Selection) on K-NN classifier using open access gene expression data small round blue cell tumor types.Methods: In study, types was used for methods. PCA, Selection were as together with classification method.Results: Accuracy values obtained from model made model; EWS, BL, NB, RMS type tumors 93.51%, 91.14%, 92.31%, 94.74% respectively. 96.25%, 95.06% 95.47%, 91.89%, 90.67%, 88.31% 89.47% ICA+ 92.31% respectively.Conclusion: created gives higher results than ICA. addition, according models by applying selection method these 2 models, forward has increased performance.