MODIFIKASI K-MEANS BERBASIS ORDERED WEIGHTED AVERAGING (OWA) UNTUK KASUS KLASTERING
Abstract
K-means clustering method based on Ordered Weighted Averaging (OWA) was developed by Cheng et al (2009) to resolve problem in classification using integrating k-means clustering and OWA. K-means clustering is a method of clustering and OWA is an aggregation operator. OWA was able to reduce the complexity of experimental data and helpin representing sophisticated relationships between the criteria. Based on the original function of k-means and OWA algorithm used, it is predicted that OWA-based k-means clustering (Cheng et al, 2009) works by modifying some of its stages. In this study, it will be done by modification of OWA-based k-means clustering (Cheng et al, 2009) and validated it in the clustering of iris dataset. This research aims to apply OWA-based k-means clustering in clustering iris data sets for validation and measure accuracy rateof OWA-based k-means clustering in the iris data sets. Resultshowed that accuracy of OWA-based k-means clustering in clustering iris data sets is 96.67%, which was better than k-means clustering method of 89.33%.
Keywords
clustering, k-means, OWA.
Full Text:
PDF (Bahasa Indonesia)DOI
https://doi.org/10.21107/agrointek.v5i2.1943Metrics
Refbacks
- There are currently no refbacks.
Copyright (c) 2016 AGROINTEK
This work is licensed under a Creative Commons Attribution 4.0 International License.