|
چکیده
|
One of the main applications of data mining is for diagnosing various diseases in medical sciences. In the recent years, numerous studies have been done in this area. The breast cancer is a major concern among women, and physicians need to have access to a smart system for predicting the illness on time before it is too late to be treated. The C5.0 is one of the important algorithms in data mining area. In this paper, we present an approach to breast canser prediction using C5.0. We use of a database called ‘wisconsin Breast Cancer database’ containing 10 attributes and 699 instances. The method used is called CRISP-DM, the C5.0 algorithm is used to create a model by Clementine software for data and subsequently, to create the confusion matrix. The results have been evaluated using sensitivity and specificity measures. Moreover, by using BOOSTING method, the model will be more precised with less percentage of error.
|