الفهرس 
AbstractOnly 14 pages are availabe for public view
 |  | from | 9 |  |  |
| | | from | 9 | | |
Abstract
Data mining is an interactive process of discovering models in large datasets and transforms a large collection of data into knowledge. The aim of this thesis is to compare the prediction accuracy of three decision tree algorithms ”ID3, J48, and Random tree” to determine the class of graft status as success or failure. The weka machine learning software is used for this purpose. Results showed that ID3 and random tree outperforms J48 in prediction accuracy. A modification on ID3 algorithm is proposed looking for better accuracy and much more data sets to be taken. A weighted decision tree algorithm is introduced for prediction of graft survival in renal transplantation using preoperative patient’s data. The objective was to identify the preoperative attributes that affect the graft survival. The ID3 algorithm was chosen to build up the modified decision tree using the weka machine learning software. A modification was made on ID3 to refine the results through introducing weighted vector. The element of such a vector represents the weight of each attribute which was obtained by trial and error. The results indicated that the weighted algorithm was successful in predicting the graft survival after one year and identifying the attributes affecting graft survival.