Comparing the performance of ANN with FNN on mammography mass data set

Nowadays soft computing techniques such as fuzzy logic, artificial neural network and neuro- fuzzy networks are widely used for the diagnosis of various diseases at different levels. These diagnosing systems help in early detection of diseases and assist the patient to get proper medication in time. In this paper, the artificial neural network such as multilayer perceptron neural network and radial basis neural network and their hybrid model i.e. combination of fuzzy logic with neural networks (FNN) are introduced to classify the mammography mass data set into two classes benign and malignant on the basis of mammography mass data set attributes. The comparison of the ANNs' performance is done with the FNN models. In the system, the missing value of records is handled using mean substitution method. A four - fold cross validation method is used for the assessment of generalization of the system. The result shows that the FNN networks perform better than the artificial neural networks with an accuracy of 87.50% and 90.00 % and proving their usefulness in classification of mammography mass data.