Comparison of ANFIS and SVM for the classification of brain MRI Pathologies

The Adaptive Neuro-Fuzzy Inference System (ANFIS) and support vector machines (SVM) are compared in terms of pathologies detection in brain magnetic resonance images (MRI). Twelve features are extracted from LH and HL sub-bands of the two dimensional discrete wavelet transform (2D-DWT) using first order statistics; then, principal component analysis is employed to retain the six most significant characteristics. The simulation results show strong evidence of the superiority of SVM over ANFIS.