期刊名称：International Journal of Computer Science and Network
印刷版ISSN：2277-5420
出版年度：2016
卷号：5
期号：1
页码：157-164
出版社：IJCSN publisher
摘要：Medical diagnosis is often done by expertise andexperience of phisician, but sometimes may lead tomisdiagnosis. Multiple sclerosis (MS) is a disease of thecentral nervous system. In this disease, body producesantibodies that attack and damage the Myelin, in which themyelin sheath (the insulation for nerve fibers) is in troubleand the damage to myelin in the central nervous systemcause to disconnect between brain and other organs. Themajor problem is the lack of diagnosis. To improve diagnosis,Adaptive Neuro-Fuzzy Inference System (ANFIS) is used.ANFIS main idea is that using the way the nervous system ofbiological for data processing in order to learn and createthe knowledge. This system uses neural network for learning,classification capabilities and modifying. There are severalways to train neural network. In this study, we use hybridapproach to train. This hybrid approach uses BackPropagation(BP) and Least Square Error(LSE). ANFIS hasthe ability to combine the linguistic power of fuzzy systemwith numeric power of neural network. For optimizing theinput/output, the K-fold cross validation has been used.Implementation has been done in MATLAB. The Data setconsist of 600 patients that each one has 6 columns, 5 ofthem is input and 1 of them is output that shows diagnosis
