Comparison of anfis Neural Network with several other ANNs and Support Vector Machine for diagnosing hepatitis and thyroid diseases
Saeed Shariati, Mahdi Motavalli Haghighi · 2010
In this paper we use self organized fuzzy system to diagnosis and prognosis hepatitis and thyroid diseases. Moreover, we compare the result of fuzzy Neural Networks with Support Vector Machine(SVM) and artificial neural networks. In addition to diagnosis of disease, we identify the type and the phase of disease via the networks which include six classes for hepatitis disease, namely: hepatitis B (two phase) Hepatitis C (two phase), non-viral hepatitis and non-hepatitis and for thyroid disease we determine five classes, namely: Hypothyroid, Hyperthyroid, Sub-clinical hypothyroid, Sub-clinical hyperthyroid and No thyroid. The performance of each of them has studied and the best method is selected for each of classification tasks. The overall accuracy of diagnosis systems are improved as compared with previously published papers. For hepatitis disease the best accuracies range from 97.6% to 98.77% and for thyroid disease from 95.4% to 99.5%.