Open AccessKernel Based Comparison between Fuzzy C-Means and Support Vector Machine for Sinusitis Classification
Author(s) -
Rievanda Putri,
Zuherman Rustam,
Jacub Pandelaki,
Nafizatus Salmi
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1752/1/012031
Subject(s) - kernel (algebra) , artificial intelligence , support vector machine , pattern recognition (psychology) , mathematics , kernel method , euclidean distance , sinusitis , computer science , medicine , surgery , combinatorics
Sinusitis is an inflammation of the sinus wall, a small cavity interconnected through the airways in the skull bones. It is located on the back of the forehead, inside the cheek bone structure, on both side of the nose, and behind the eyes. Sinusitis is caused by infection, growth of nasal polyps, allergies, and others. This condition can effect adults, teenagers, and even children. To classify sinusitis, we used Kernel Based Fuzzy C-Means, which is the development of Fuzzy C-Means (FCM). FCM algorithm groups data using Euclidean distance. However, when non-linear data is separated, the convergence is inaccurate and need a long-running time. To overcome this problem, a Kernel Based Fuzzy C-Means that use kernel functions as a substitute for Euclidean distance. It maps objects from data space to a higher dimension feature space, so they can overcome FCM deficiencies. Beside we used Kernel Based Support Vector Machine to do the same thing, that separate the data set by hyperplane. From the result of both methods, we will compare both of them to get the best method for the data set. Data that is used is sinusitis data set obtained from the laboratory of radiology at Cipto Mangunkusumo National General Hospital, Jakarta. From the experiment we got 100% accuracy of Kernel Based Fuzzy C-Means and 100% accuracy of Kernel Based Support Vector Machine using the same parameter sigma for the kernel.