.jpg)
Laboratory Clustering using K-Means, K-Medoids, and Model-Based Clustering
Abstract
Institut Teknologi Sepuluh Nopember (ITS) is an institute which has about 100 laboratories to support some academic activity like teaching, research and society service. This study is clustering the laboratory in ITS based on the productivity of laboratory in carrying out its function. The methods used to group laboratory are K-Means, K-Medoids, and Model-Based Clustering. K-Means and K-Medoids are non-hierarchy clustering method that the number of cluster can be given at first. The difference of them is datapoints that selected by K-Medoids as centers (medoids or exemplars) and mean for K-Means. Whereas, Model-Based Clustering is a clustering method that takes into account statistical models. This statistical method is quite developed and considered to have advantages over other classical method. Comparison of each cluster method using Integrated Convergent Divergent Random (ICDR). The best method based on ICDR is Model-Based Clustering.
Keywords : K-Means, K-Medoids, Laboratory, Model-Based Clustering
Full Text:
PDFReferences
Sonhadji, A. Laboratorium Sebagai Basis Pendidikan Teknik di Perguruan Tinggi. Universitas Negeri Malang. Malang. 2002.
Agustini, M. Model-Based Clustering dengan Distribusi t Multivariat Menggunakan Kriteria Integrated Completed Likelihood dan Minimum Message Length. Institut Teknologi Sepuluh Nopember. Surabaya. 2017.
Johnson, R. A. and Dean W. W. Applied Multivariate Statistical Analysis Sixth Edition. Person Prentice Hall. New Jersey. 2007.
Banfield, J. D. and Raftery, A. E. Model-Based Gaussian and non-Gaussian Clustering. Biometrics. 49(3): 803-821. 1993.
Park, H. S. and Jun, C. H. A Simple and Fast Algorithm for K-Medoids Clustering. Elsevier. South Korea. 2008.
Fraley, C. and Raftery, A. E. Model-Based Clustering, Discriminant Analysis, and Density Estimation. Journal of the American Statistical Association. 97(458): 611–631. 2002.
Refbacks
- There are currently no refbacks.
