• Login
    View Item 
    •   USU-IR Home
    • Faculty of Computer Science and Information Technology
    • Department of Information Technology
    • Master Theses
    • View Item
    •   USU-IR Home
    • Faculty of Computer Science and Information Technology
    • Department of Information Technology
    • Master Theses
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Analisis Kinerja Algoritma K-Means dengan Penentuan Centroid Menggunakan Metode Rank Order Centroid (ROC)

    View/Open
    Fulltext (2.383Mb)
    Date
    2020
    Author
    Sari, Putri Perdana
    Advisor(s)
    Zarlis, Muhammad
    Nababan, Erna Budhiarti
    Metadata
    Show full item record
    Abstract
    Proses awal clustering algoritma k-means adalah menentukan titik pusat awal cluster (centroid). Terdapat tiga cara dalam memilih centroid pada algoritma k-means konvensional yaitu dinamik, acak dan nilai tertinggi dan terendah. Pemilihan centroid yang sering dilakukan adalah dengan acak. Akan tetapi pada penelitian ini, pemilihan centroid pada algoritma k-means konvensional dilakukan dengan nilai tertinggi dan terendah. Penelitian ini membandingkan nilai akurasi yang didapatkan dari k-means konvensional dengan k-means menggunakan ROC (Rank Order Centroid). Hasil yang didapatkan algoritma K-means menggunakan ROC mengalami peningkatan dibandingkan k-means konvensional sebesar 3.54% yaitu dari 22.88% menjadi 26.42%.
     
    The initial process of k-means algorithm clustering was to determine the initial center point of the cluster (centroid). There was three ways to choose a centroid in the conventional k-means algorithm, namely dynamic, random and the highest and lowest values. The choice of centroid is often done randomly. However, in this study, the centroid selection in the conventional k-means algorithm was carried out with the highest and lowest values. This study compares the accuracy value obtained from conventional k-means with k-means using ROC (Rank Order Centroid). The results obtained by the K-means algorithm using ROC have increased compared to conventional k-means by 3.54%, from 22.88% to 26.42%.

    URI
    http://repositori.usu.ac.id/handle/123456789/28552
    Collections
    • Master Theses [622]

    Repositori Institusi Universitas Sumatera Utara - 2025

    Universitas Sumatera Utara

    Perpustakaan

    Resource Guide

    Katalog Perpustakaan

    Journal Elektronik Berlangganan

    Buku Elektronik Berlangganan

    DSpace software copyright © 2002-2016  DuraSpace
    Contact Us | Send Feedback
    Theme by 
    Atmire NV
     

     

    Browse

    All of USU-IRCommunities & CollectionsBy Issue DateTitlesAuthorsAdvisorsKeywordsTypesBy Submit DateThis CollectionBy Issue DateTitlesAuthorsAdvisorsKeywordsTypesBy Submit Date

    My Account

    LoginRegister

    Repositori Institusi Universitas Sumatera Utara - 2025

    Universitas Sumatera Utara

    Perpustakaan

    Resource Guide

    Katalog Perpustakaan

    Journal Elektronik Berlangganan

    Buku Elektronik Berlangganan

    DSpace software copyright © 2002-2016  DuraSpace
    Contact Us | Send Feedback
    Theme by 
    Atmire NV