Open AccessComparison of Cubic SVM with Gaussian SVM: Classification of Infarction for detecting Ischemic Stroke
Author(s) -
Amanda Rizki Bagasta,
Zuherman Rustam,
Jacub Pandelaki,
Widyo Ari Nugroho
Publication year - 2019
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/546/5/052016
Subject(s) - support vector machine , infarction , gaussian , brain infarction , stroke (engine) , ischemic stroke , pattern recognition (psychology) , artificial intelligence , cerebral infarction , medicine , computer science , cardiology , ischemia , myocardial infarction , physics , quantum mechanics , thermodynamics
Ischemic Stroke is a condition whereby the blood supply to the brain is disrupted or reduced due to a blockage and if it is not treated immediately will cause the death of the brain. A decrease in blood flow resulting in dead brain tissue can be called an infarction. The classifications of infarction help the health sector in detecting ischemic stroke in patients. In medicine, CT scans can be used to identify Infarctions and for detecting Ischemic Stroke in patients. Therefore, studying the CT scans is crucial in helping doctors obtain functional information about the surrounding brain tissues which will be used for detecting infarction in the brain. Since it is important to pay more attention at the time of choosing the best method that gives the best results, therefore this study proposes to compare between two types of methods, Gaussian Support Vector Machine (Gaussian SVM) and Cubic Support Vector Machine (Cubic SVM). The Cubic SVM could be an efficient method for infarction classification with accurate performances as high as 80%.