Approach of Jordan Elman Neural Network to Diagnose Breast Cancer on Three Different Data Sets

Abstract: Breast cancer is the second leading cause of cancer deaths worldwide, occurs in one out of eight women .still there is no known way of preventing this pathology. Early detection of this disease can greatly enhance the chances of long-term survival of breast cancer victims. Artificial Neural Network is a branch of Artificial intelligence, has been accepted as a new technology in computer science. Neural Networks are currently a 'hot' research area in medicine, particularly in the fields of radiology, urology, cardiology, oncology and etc. It has a huge application in many areas such as education, business; medical, engineering and manufacturing. Neural Networks has been widely used for cancer prediction and prognosis. This paper highlights on Jordan Elman neural networks approaches to solve breast cancer diagnosis, using three different database of breast cancer viz. Wisconsin, WDBC and WPBC. We also introduce recurrent neural network technology as Jordan Elman neural network. To diagnose problems Jordan Elman neural network is successful on three different breast cancer data set is major feature of this paper.

Keywords: recurrent network, benign, malignant, WDBC, WPBC, mammography, FNA, mean square Error, Correlation, Sensitivity, Specificity, ROC.