<![CDATA[AbstrakKanker payudara merupakan tumor ganas yang tumbuh pada sel-sel payudara dan dapat menyebar di antara jaringan atau organ di sekitar payudara dan berpindah ke bagian tubuh lainnya. Jika deteksi kanker dilakukan sejak dini, memungkinkan dilakukan penanganan yang lebih baik dan timbulnya sel-sel kanker dapat diatasi dengan segera dan dihentikan penyebarannya. Untuk membantu meningkatkan kemampuan pendeteksian otomatis dapat digunakan teknik machine learning dengan metode klasifikasi. Salah satu metode klasifikasi yang dapat digunakan yaitu metode Support Vector Machine. Pada penelitian ini, metode Support Vector Machine diterapkan pada Breast Cancer Coimbra Data Set. Penerapan Backward Elimination bertujuan untuk mengoptimalkan performa suatu model dengan sistem kerja pemilihan mundur dan memilih atribut yang paling relevan pada proses klasifikasi. Hasil penelitian klasifikasi pasien kanker payudara menggunakan metode Support Vector Machine menghasilkan nilai akurasi sebesar 65,22% dan nilai AUC sebesar 0,700 yang termasuk ke dalam kategori Fair Classification. Sedangkan hasil penelitian klasifikasi pasien kanker payudara menggunakan metode Support Vector Machine dengan Backward Elimination menghasilkan nilai akurasi sebesar 95,65% dan nilai AUC sebesar 1,000 yang termasuk ke dalam kategori Excellent Classification. Kata Kunci: backward elimination, kanker payudara, klasifikasi, support vector machine AbstractBreast cancer is a malignant tumor that grows on the cells of the breast and can spread between tissues or organs around the breast and move to other parts of the body. If the detection of cancer is done early, it is possible to do better treatment and the emergence of cancer cells can be treated immediately and stopped spreading. To help improve automatic detection capabilities, machine learning techniques with classification methods can be used. One of the classification methods that can be used is the Support Vector Machine method. In this study, the Support Vector Machine method was applied to the Breast Cancer Coimbra Data Set. The application of Backward Elimination aims to optimize the performance of a model with a backward selection work system and select the most relevant attributes in the classification process. The results of the classification study of breast cancer patients using the Support Vector Machine method resulted in an accuracy value of 65.22% and an AUC value of 0.700 which was included in the Fair Classification category. Meanwhile, the results of the classification research of breast cancer patients using the Support Vector Machine method with Backward Elimination resulted in an accuracy value of 95.65% and an AUC value of 1,000 which is included in the Excellent Classification category. Keywords: backward elimination, breast cancer, classification, support vector machine]]>
Copyrights © 2021
