Academic Journals Database
Disseminating quality controlled scientific knowledge

A Novel Prediction on Breast Cancer from the Basis of Association rules and Neural Network

ADD TO MY LIST
 
Author(s): S. Palaniappan | T. Pushparaj

Journal: International Journal of Computer Science and Mobile Computing
ISSN 2320-088X

Volume: 2;
Issue: 4;
Start page: 269;
Date: 2013;
VIEW PDF   PDF DOWNLOAD PDF   Download PDF Original page

Keywords: Breast cancer diagnosis | Wisconsin Breast Cancer Database (WBCD) | Association Rule | Neural Network | Multilayer Perceptron (MLP) | feature selection | 3-Fold cross validation

ABSTRACT
The use of machine learning tools in medical diagnosis is increasing gradually. This is mainlybecause the effectiveness of classification and recognition systems has improved in a great deal to helpmedical experts in diagnosing diseases. Such a disease is breast cancer, which is a very common type ofcancer among woman. As the incidence of this disease has increased significantly in the recent years,machine learning applications to this problem have also took a great attention as well as medicalconsideration. This paper presents an automatic diagnosis system for predicting breast cancer based onassociation rules (AR) and neural network (NN). In this study, AR1 and AR2 are used for reducing thedimension of breast cancer dataset and NN is used for intelligent classification. The proposed AR1 + AR2 +NN system performance is compared with NN model. The dimension of input feature space is reduced fromnine to four by using AR1 & AR2. In test stage, 3-fold cross validation method was applied to the Wisconsinbreast cancer dataset to evaluate the proposed system performances. The correct classification rate ofproposed system is 98.4%. This paper demonstrated that the AR1 and AR2 can be used for reducing thedimension of feature space and proposed AR1 + AR2 + NN model can be used to obtain fast automaticdiagnostic system for breast cancer.
Why do you need a reservation system?      Affiliate Program