Perbandingan Decision Tree C4.5 dan Support Vector Machine (SVM) Dalam Klasifikasi Penderita Stroke Berbasis PSO

Abstract

Stroke is a major health problem for today's modern society. At present, stroke is increasingly becoming a serious problem that is faced almost all over the world. This is because a sudden stroke can result in death, physical and mental disability in both productive and old age. To obtain stroke information data, it is necessary to carry out data mining processes such as classification. Classification is a process for determining a model that explains or distinguishes concepts or data classes, with the aim of being able to estimate the class of an object whose class is unknown, in classification a number of records are also given which are called training sets, which consist of several attributes, attributes can be be continuous or categorical, one of the attributes specifies the class for the record In the above problems regarding stroke, to be able to overcome this problem, a lot of research has been carried out in the field of computer science, including the Classification of Stroke Patients Using the C4.5 Decision Tree Algorithm and the Support Vector Machine (SVM) Algorithm to classify the most important factors for this disease. The test resulted in a fairly high accuracy of the C4.5 Decision Tree Algorithm, which was 96.11%. Referring to the results of the accuracy of the research, it can be seen that the Decision Tree produces high accuracy, but the results of this accuracy can still be improved by conducting further research to produce higher accuracy by adding Optimization Feature Weighting PSO.

Keywords: Accuracy, Stroke, PSO, C4.5 Decision Tree Algorithm. Support Vector Machine (SVM) Algorithm