Perbandingan Metode Ekstraksi Fitur Data Dalam Meningkatkan Akurasi Klasterisasi Bandwidth Internet Menggunakan Fuzzy C-Mean

Abstract

internet bandwidth is becoming one of the staples in all instances, because with the internet a lot of information can be obtained, in order to optimize internet bandwidth usage is necessary to do an analysis of' the internet bandwidth usage, where internet bandwidth usage analysis con be done by clustering bandwidth internet. One algorithm for clustering algorithms used are Fuzzy C-Mean, in which the clustering process before the beginning of the internet bandwidth usage data that exists in one period will be collected to be input to the Fuzzy C-Mean algorithm for the distribution of clusters on the use of existing bandwidth based application that use the internet and network user. But the initial dataset that of the Fuzzy C Mean is not optimal, so we need some optimization dataset using feature extraction data so that the resulting clusters by Fuzzy C Mean algorithm has the accurate output. The purpose of this research is to compare two methods of generating data feature extraction namely Principal Component Analysis (PCA) and Correlation Feature Selection (CFS). Results to be obtained from this research is the data feature extraction method most appropriate for clustering and analysis of internet traffic based on user applications and the amount of capacity used by user, which information the clustering results can be used to optimize internet bandwidth