<![CDATA[Breast cancer is a malignant tumor that begins in the cells of the breast. A malignant tumor is a group of cancer cells that can grow and invade surrounding tissues or spread (metastasize) to distant areas of the body. This disease occurs almost entirely in women, but men can also get it. The hypothesis of this study is the method of Artificial Neural Network which is expected to increase the accuracy in the prediction of breast cancer patients. Results of testing to be performed by measuring method and compared with the Artificial Neural Network algorithm C.45. The dataset taken from UCI with a total number of 699 and it is found benign tumors or as many as 458 (65.5%) whereas malignant cancer or 241 (34.5%), with 699 data and 10 attributes which are processed are the thickness of breast cancer, cell size, cell shape, adhesion Margina, single epi cell size, cell nuclei, bland chromatin, normal nucleoli, myth, and the class of breast cancer benign and malignant breast cancer. From various experiments conducted with the Artificial Neural Network algorithm best results are with 500 Cycle Training and Learning Rate 0.5 to obtain an accuracy value of 95.57%, 93.00% presicion, recall 94.62% and AUC 0.986 with time 38s. So based on grouping by comparing the accuracy and AUC values of experiments shows that the algorithm has a classification Artificial Neural Network with a very good, and when compared with the C4.5 algorithm with the result 0.963 is better than Artificial Neural Network algorithm. To be able to increase the level of accuracy of previous studies that only 93.00% to 95.57% gain research or an increase of 2.57%. For computing the level of accuracy with 94.42% and the standard reached by using computational experiments that change the value of Learning Rate it generated 95.57%, an increase of 1.42%.]]>
Copyrights © 2019
