Abstract

Breast cancer is a second biggest cause of human death on women. The death rate caused by the breast cancer has been fallen since 1989. This downfall is believed as a result from early diagnose on breast cancer, the awareness uplift on the breast cancer, also a better medical treatment. This research proposes the Modified K-Means Naïve Bayes (KMNB) method on Breast Cancer data. The modification which has been conducted was an additional on initial centroid which has been proposed by Fang. The experiment compared the accuracy of our proposed method with the original KMNB, Original K-Mean, and K-Means using initial centroid by Fang. Based on the result of the experiment, the accuracy of our proposed method was 95%. The error reduction of our proposed method was about 50% compared to the original KMNB. It can be stated that our proposed method is promising and able to enhance the prediction on Breast Cancer Wisconsin data. On the other hand, the enhancement of prediction result will increase the preventive behavior on society and give a positive impact on the number downfall of breast cancer sufferers.

Original languageEnglish
Pages (from-to)137-140
Number of pages4
JournalJournal of Telecommunication, Electronic and Computer Engineering
Volume10
Issue number1-6
Publication statusPublished - 2018

Keywords

  • Breast Cancer
  • Classification
  • Clustering
  • Data Mining

Fingerprint

Dive into the research topics of 'A modified K-Means with Naïve Bayes (KMNB) algorithm for breast cancer classification'. Together they form a unique fingerprint.

Cite this