Perbandingan Metode Berbasis Model Dengan Metode K-Mean Dalam Analisis Gugus  

Oleh:

Pardede, Timbul

Jenis: Article from Journal - ilmiah nasional - tidak terakreditasi DIKTI
Dalam koleksi: SIGMA: Jurnal Sains dan teknologi vol. 11 no. 2 (Jul. 2008), page 157-166.
Topik: K-mean Clustering Method; Model-Based Clustering Method; Expectation-Maximization Algorithm; Bayesian Information Criterion

Ketersediaan

Perpustakaan Pusat (Semanggi) Nomor Panggil: SS25.6 Non-tandon: 1 (dapat dipinjam: 0) Tandon: tidak ada

Lihat Detail Induk

Isi artikel

K-mean method is clustering methiod in which grouping techniques are based only distance measure among observed objects, without considering statistical aspects. Model-based clustering is a method that uses statistical aspects, as its theoretical basis i.e. probabilitt maximum criterion. This model has several variations with a variety of geometrical characteristics obtained by mean Gauss component. Data partition is conducted by utilizing expectation-maximization (EM) algorithm. By using Bayesian Information Criterion (BIC) the best model is then namely model-based clustering was more effective in separating overlap groups than K-mean.

Opini Anda

Klik untuk menuliskan opini Anda tentang koleksi ini!

Kembali