Kernel Entropy Based Fuzzy C-Means (KEFCM) for Acute Sinusitis

Z. Rustam, N. Shandri, T. Siswantining, J. Pandelaki

Research output: Contribution to journalConference articlepeer-review

Abstract

Sinusitis is a condition when sinuses membranes are plugged or inflamed or swollen due to infection. There are several types of sinusitis, one of them, which will be explained in this study, is acute and chronic sinusitis. There are many ways to diagnose sinusitis such as allergy tests, nasal endoscopy, CT Scans and MRI. In this study, a diagnosis will be made whether someone has acute sinusitis or chronic sinusitis by using clustering techniques with machine learning. In medical field machine learning can be used to help to analyse medical data more quickly and accurately therefore the patient can get the treatment sooner. in this study, the machine learning method used is kernel entropy fuzzy c-means (KEFCM). The kernel will be used in the Entropy Fuzzy C-means (EFCM) method which can represent multiplication in a high-dimensional space and the kernel that will be used is RBF and Polynomial. This sinusitis data used in this study were obtained from the Laboratory of Radiology at Cipto Mangunkusumo National General Hospital, Indonesia with this method it will get 97% Accuracy.

Original languageEnglish
Article number012040
JournalJournal of Physics: Conference Series
Volume1752
Issue number1
DOIs
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

Keywords

  • acute sinusitis
  • Entropy
  • fuzzy c-means

Fingerprint

Dive into the research topics of 'Kernel Entropy Based Fuzzy C-Means (KEFCM) for Acute Sinusitis'. Together they form a unique fingerprint.

Cite this