PREDICTION OF BREAST CANCER USING THE NAÏVE BAYES ALGORITHM

WULANDARI, DIKA AVILA (2022) PREDICTION OF BREAST CANCER USING THE NAÏVE BAYES ALGORITHM. Other thesis, Universitas Katholik Soegijapranata Semarang.

	Text 17.K1.0018-DIKA AVILA WULANDARI-COVER_a.pdf Download (787kB)
	Text 17.K1.0018-DIKA AVILA WULANDARI-BAB I_a.pdf Download (395kB)
	Text 17.K1.0018-DIKA AVILA WULANDARI-BAB II_a.pdf Restricted to Registered users only Download (471kB)
	Text 17.K1.0018-DIKA AVILA WULANDARI-BAB III_a.pdf Download (471kB)
	Text 17.K1.0018-DIKA AVILA WULANDARI-BAB IV_a.pdf Download (1MB)
	Text 17.K1.0018-DIKA AVILA WULANDARI-BAB V_a.pdf Download (997kB)
	Text 17.K1.0018-DIKA AVILA WULANDARI-BAB VI_a.pdf Download (227kB)
	Text 17.K1.0018-DIKA AVILA WULANDARI-DAPUS_a.pdf Download (244kB)
	Text 17.K1.0018-DIKA AVILA WULANDARI-LAMP_a.pdf Download (214kB)

Abstract

Breast cancer is the most common cause of death among women worldwide. Cancer can be classified into two categories, benign and malignant. Cancers are more aggressive than tumors. Therefore, early diagnosis will be very helpful for patients. This report uses the Naïve Bayes data classification method to detect breast cancer and classify whether it is benign or malignant. The conclusion of this study is that the Naïve Bayes algorithm proposed as a classification method for breast cancer prediction is able to get a good score. The average percentage of data that is classified correctly reaches 96.47% and the average percentage of data that is classified incorrectly is only 3.53%. While the level of effectiveness where the average value of precision and recall respectively is 0.956 and 0.9685. For the highest precision and recall values, when the test data uses a 10% split percentage for testing data with values of 0.985 and 0.985.

Item Type:	Thesis (Other)
Subjects:	000 Computer Science, Information and General Works > 004 Data processing & computer science
Divisions:	Faculty of Computer Science > Department of Informatics Engineering
Depositing User:	mr AM. Pudja Adjie Sudoso
Date Deposited:	26 Oct 2022 09:15
Last Modified:	26 Oct 2022 09:15
URI:	http://repository.unika.ac.id/id/eprint/30011

Actions (login required)

View Item