Adaptive Neuro Fuzzy Inference System (ANFIS) is among the most efficient classification and prediction
modelling techniques used to develop accurate relationship between input and output parameters in
different processes. This paper reports the design and evaluation of the classification performances of
two discrete Adaptive Neuro Fuzzy Inference System models, ANFIS Matlab’s built-in model (ANFIS_
LSGD) and a newly ANFIS model with Levenberg-Marquardt algorithm (ANFIS_LSLM). Major steps
were performed, which included classification using grid partitioning method, the ANFIS trained with
least square estimates and backpropagation gradient descent method, as well as the ANFIS trained with
Levenberg-Marquardt algorithm using finite difference technique for computation of a Jacobian matrix.
The proposed ANFIS_LSLM model predicts the degree of patient’s heart disease with better, reliable
and more accurate results. This is due to its new feature of index membership function that determines
the unique membership functions in an ANFIS structure, which indexes them into a row-wise vector. In
addition, an attempt was also done to specify the effectiveness of the model’s performance measuring
accuracy, sensitivity and specificity. A comparison of the two models in terms of training and testing
with the Statlog-Cleveland Heart Disease dataset have also been done.
Medical diagnosis is the process of determining which disease or medical condition explains a person’s determinable signs and symptoms. Diagnosis of most diseases is very expensive as many tests are required for predictions. This paper aims to introduce an improved hybrid approach for training the adaptive network based fuzzy inference system (ANFIS). It incorporates hybrid learning algorithms least square estimates with Levenberg-Marquardt algorithm using analytic derivation for computation of Jacobian matrix, as well as code optimisation technique, which indexes membership functions. The goal is to investigate how certain diseases are affected by patient’s characteristics and measurement such as abnormalities or a decision about the presence or absence of a disease. In order to achieve an accurate diagnosis at this complex stage of symptom analysis, the physician may need efficient diagnosis system to classify and predict patient condition by using an adaptive neuro fuzzy inference system (ANFIS) pre-processed by grid partitioning. The proposed hybridised intelligent technique was tested with Statlog heart disease and Hepatitis disease datasets obtained from the University of California at Irvine’s (UCI) machine learning repository. The robustness of the performance measuring total accuracy, sensitivity and specificity was examined. In comparison, the proposed method was found to achieve superior
performance when compared to some other related existing methods.