%A NIM.: 21106010038 Refina Nur Asmia
%O Muhamad Rashif Hilmi, S.Si., M.Sc. dan Deddy Rahmadi, M.Sc.
%T KLASIFIKASI KANKER PAYUDARA MENGGUNAKAN ALGORITMA SUPPORT VECTOR MACHINE
%X Breast cancer is one of the non-communicable diseases that causes death worldwide, particularly among women. Early detection and classification of the survival status or death of breast cancer patients are crucial in determining appropriate treatment. This study aims to examine the performance steps of the SVM algorithm, assess the performance of the SVM algorithm using linear, polynomial, RBF, and sigmoid kernel methods, and identify the best-performing SVM kernel in this classification. The data used in this study were obtained from the Surveillance, Epidemiology, and End Results (SEER) Program, November 2017 version, which includes female patients diagnosed with infiltrating duct and lobular carcinoma breast cancer between 2006 and 2010. There are 14 independen variables, namely: age, race, marital status, t stage, n stage, 6th stage, grade, a stage, tumor size, estrogen status, progesterone status, regional node examined, regional node positive, and survival months. The dependen variable is status. The method used involves four SVM kernels: linear, polynomial, Radial Basis Function (RBF), and sigmoid. The accuracy results obtained are as follows: linear kernel: 91.105%, polynomial kernel: 90.384%, RBF kernel: 91.225%, and sigmoid kernel: 90.384%. The best performance result in this classification was achieved by the RBF kernel.
%K Support Vector Machine (SVM), Kanker Payudara, Kernel Linier, Kernel Polinomial, Kernel RBF, Kernel Sigmoid, Akurasi
%D 2025
%I UIN SUNAN KALIJAGA YOGYAKARTA
%L digilib71769