Classification of Cerebral Infarction Data Using K-Means and Kernel K-Means

A. M. Putri, A. G.M. Sari, Z. Rustam, J. Pandelaki

Research output: Contribution to journalConference articlepeer-review


A cerebral infarct is a circumscribed focus or area of brain tissue that dies as a result of localized hypoxia or ischemia due to cessation of blood flow. To diagnose the presence of cerebral infarction, it needs a CT scan result from the patient. But, in this study not only CT scan result will be used, machine learning also will be proposed to diagnosing cerebral infarction. Machine learning can be used to detect and classify of infarcts in the brain using features and label that obtained from the results of the CT scan. In this study, the machine learning method that will be used is K-Means and K-Means based on kernel or kernel K-Means. Kernel K-Means is the application of K-Means that modified by changing the inner product with kernel function. The CT scan result data used in this study was obtained from the Department of Radiology at Dr. Cipto Mangunkusumo Hospital (RSCM). The best result reached with kernel K-Means, it performed with different percentage of training data, started with 50%, 55%, until 95% data training. The average accuracy score of the kernel K-Means method attained an accuracy rate of 95.28%.

Original languageEnglish
Article number012041
JournalJournal of Physics: Conference Series
Issue number1
Publication statusPublished - 15 Feb 2021
Event3rd International Conference on Statistics, Mathematics, Teaching, and Research 2019, ICSMTR 2019 - Makassar, Indonesia
Duration: 9 Oct 201910 Oct 2019


  • cerebral infarction data
  • Classification
  • K-means
  • kernel K-means


Dive into the research topics of 'Classification of Cerebral Infarction Data Using K-Means and Kernel K-Means'. Together they form a unique fingerprint.

Cite this