A Modified K-Means with Naïve Bayes (KMNB) Algorithm for Breast Cancer Classification

Authors

  • Dian Eka Ratnawati Department of Computer Science – Faculty of Computer Science, Brawijaya University.
  • Nurizal Dwi Priandani Department of Computer Science – Faculty of Computer Science, Brawijaya University.
  • Machsus Machsus Department of Civil Infrastructure Engineering, Institute of Technology Sepuluh Nopember.

Keywords:

Breast Cancer, Classification, Clustering, Data Mining,

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 KMean, 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.

Downloads

Published

2018-02-05

How to Cite

Ratnawati, D. E., Priandani, N. D., & Machsus, M. (2018). A Modified K-Means with Naïve Bayes (KMNB) Algorithm for Breast Cancer Classification. Journal of Telecommunication, Electronic and Computer Engineering (JTEC), 10(1-6), 137–140. Retrieved from https://jtec.utem.edu.my/jtec/article/view/3681