Fuzzy Kernel-Based Clustering and Support Vector Machine Algorithm in Analyzing Cerebral Infarction Dataset

Ischemic stroke is a disease that occurs due to disruption of blood circulation to the brain due to blood clots in the brain. The blockage is called cerebral infarction. In diagnosing the presence of cerebral infarction in the brain, machine learning is used because it is not enough just to use a CT scan to diagnose. To deal with the problem of classification of cerebral infarction data obtained from Dr. Cipto Mangunkusumo’s Hospital in Jakarta, this study proposes the use of Fuzzy C-Means Clustering (FCM), Fuzzy Possibilistic C-Means (FPCM), and Radial Base Function Fuzzy Possibilistic C-Means (RBFFPCM) method as a clustering method and a Support Vector Machine (SVM) method as a classification method. This method will be compared to the level of accuracy. The greatest level of accuracy is generated from the Radial Base Function Fuzzy Possibilistic C-Means (RBFFPCM) method with an accuracy value of 91%.