Institusion
Institut Teknologi Telkom Purwokerto
Author
Indira, Sarasmitha Batu Bara
Subject
T Technology (General)
Datestamp
2022-07-01 04:09:29
Abstract :
Cancer is one of the leading causes of death worldwide. Cancer has many types, depending on where
it develops. One of the most common cancer is breast cancer. The difficulty of classifying the
malignancies of breast cancer can lead to delays in treatment, which leads to a higher risk of death.
Currently in the field of data mining developed an algorithm that can classify malignancy of breast
cancer, some of which are Support Vector Machine (SVM) and Naïve Bayes. SVM is a supervised
learning algorithm that classifies the class using hyperplane. The advantages of SVM is over the
high level of accuracy produced. Naïve Bayes is a learning algorithm that uses the probability of
classifying data. Naïve Bayes has an advantage on the capability of classifying large amounts of
data. The study used a dataset from Wisconsin Breast Cancer with 699 data obtained from
http://archive.ics.uci.edu/ml/index.php. The results showed SVM accuracy was 98.56% and Naïve
Bayes 97.74%.
Keywords: Classification, Breast Cancer, SVM, Naïve Bayes