NEURO-FUZZY WITH FEATURE EXTRACTION BASED MEDICAL DISEASE ANALYSIS
Neuro-fuzzy systems (NFS) play a vital and important role in the classification and prediction of various types of medical disorders. In order to avoid misdiagnosis, NFS supports doctors in the automation of the medical disorder domain. With time, the NFS approach has become apparent in increasing accuracy in the treatment of a wide range of complex medical diagnostic research problems. This paper examines the application in medical image classification in the past 16 years of the adaptive neurofuzzy inference system ( ANFIS). In an adaptive fuzzy neural network ANFIS is a fuzzy inference system (FIS). The explicit representation of the FIS by information is combined with the information capacity of artificial neural networks. ANFIS aims to integrate the best characteristics of fuzzy and neural systems. The principal advantages and disadvantages of this classifier are examined for a brief comparison with other classifiers. Based on the study performed, NFS has been shown to be effective in comparison with other medical AI techniques. Study shows that efficiency of NFS greatly improves when combined with other AI approaches. This study adds to the expertise of numerous medical diagnostic researchers and also provides a comprehensive view of the effectiveness of NFS techniques used in medical diagnosis.