Claim Missing Document
Check
Articles

Found 12 Documents
Search

PERBANDINGAN K-MEANS DAN FUZZY C-MEANS UNTUK PENGELOMPOKAN DATA USER KNOWLEDGE MODELING Aditya Ramadhan; Zuliar Efendi; Mustakim Mustakim
Seminar Nasional Teknologi Informasi Komunikasi dan Industri 2017: SNTIKI 9
Publisher : UIN Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (546.094 KB)

Abstract

Pada data mining terdapat sebuah metode yang digunakan untuk mengklaster data menjadi kelompok-kelompok data, yaitu metode K-Means dan Fuzzy C-Means. Kedua metode tersebut jika dilihat dari beberapa penelitian sebelumnya mengenai clustering K-Means dan FCM, masing-masing metode mampu memberikan hasil cluster terbaik. Pengklasteran data user knowledge modeling menggunakan metode K-Means dan Fuzzy C-Means menghasilkan jumlah anggota klaster yang berbeda. Dapat dilihat dari jumlah klaster yang diperoleh dari kedua metode tersebut. Berdasarkan penelitian yang dilakukan, kedua metode tersebut mengelompokkan data user knowledge modeling menjadi 4 kluster. Perbandingan yang digunakan dalam penelitian ini adalah uji performa validitas. Untuk nilai validasi SI dari metode K-Means bernilai 0.1866, sedangkan nilai validasi PCI dari metode FCM adalah bernilai 0.2854. Hasil dari penelitian ini menunjukkan bahwa metode FCM adalah metode yang lebih baik daripada K-Means untuk melakukan clustering pada data user knowledge modeling dikarenakan nilai validasinya bernilai mendekati 1.
Eigenvalue of Analytic Hierarchy Process as The Determinant for Class Target on Classification Algorithm Mustakim Mustakim; Novia Kumala Sari; Jasril Jasril; Ismu Kusumanto; Nurul Gayatri Indah Reza
Indonesian Journal of Electrical Engineering and Computer Science Vol 12, No 3: December 2018
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v12.i3.pp1257-1264

Abstract

Data mining has two main concepts of data distribution, namely supervised learning and unsupervised learning. The most easily recognizable concepts from data distribution is related to the dataset, with and without target class. Analytic Hierarchy Process (AHP) technique that carries the concept of pairwise comparison able to answer the problem related to the dataset, which is to change unsupervised to be supervised by determining eigenvalue value of each attribute and sub attribute in AHP method. The case study conducted in this issue is related to determining the target classes used to predict the success of a student learning in UIN Suska Riau. The three main attributes are Procrastination, Total Credits (SKS) and Number of Repeated Courses, each having eigenvalues of 0.319; 0.189 and 0.171 which become the feedback in the determination of the Target Timely Graduation (TG) or Possibility of Timely Graduation (PTG). The biggest consistency ratio generated in the AHP case is 9.4% in the GPA attribute. This research recommends that further research should use datasets that have been arranged based on experimental combinations of the three main attributes above, then applied to the classification or prediction algorithm. So that it would obtain a decision of accuracy from data used against the real result on the field.