Farhan Aidil Januar, 4611417066 (2023) KLASIFIKASI PENYAKIT KANKER PAYUDARA PADA ALGORITMA NAÏVE BAYES DAN SUPPORT VECTOR MACHINE MENGGUNAKAN INFORMATION GAIN RATIO DAN PARTICLE SWARM OPTIMIZATION. Under Graduates thesis, UNNES.

	PDF Download (661kB)
	PDF Restricted to Repository staff only Download (2MB) | Request a copy
	PDF Download (133kB)
	PDF Download (102kB)
	PDF Download (58kB)
	PDF Download (134kB)
	HTML Restricted to Repository staff only Download (1MB) | Request a copy
	PDF - Published Version Restricted to Repository staff only Download (671kB) | Request a copy

Abstract

Breast cancer is a type of cancer that ranks second as the most common disease. Cancer is generally divided into benign and malignant, and breast cancer is no different. In malignant status, cancer can have devastating consequences for sufferers if recognised too late. Therefore, early detection of cancer is very important so that sufferers can receive appropriate treatment. This research was conducted in order to classify the types of cancer that affect using data mining techniques. The classification of breast cancer is done using data mining methods naïve bayes algorithm and support vector machine using information gain ratio feature selection. This research was conducted using datasets taken from www.kaggle.com. From the results of research on the classification of breast cancer diagnosis using the Naïve Bayes and SVM algorithms by applying IGR feature selection followed by PSO, the best accuracy was obtained in Naïve Bayes by 98.24% and SVM by 96.49%. Thus, it can be concluded that the application of the IGR feature selection algorithm and PSO can increase the accuracy of the Naïve Bayes algorithm by 49.12% and the SVM algorithm by 19.5% in the diagnosis of breast cancer.

Actions (login required)

View Item