Centronit: Initial Centroid Designation Algorithm for K-Means Clustering
Journal Title: EMITTER International Journal of Engineering Technology - Year 2014, Vol 2, Issue 1
Abstract
Clustering performance of the K-means highly depends on the correctness of initial centroids. Usually initial centroids for the K- means clustering are determined randomly so that the determined initial centers may cause to reach the nearest local minima, not the global optimum. In this paper, we propose an algorithm, called as Centronit, for designation of initial centroidoptimization of K-means clustering. The proposed algorithm is based on the calculation of the average distance of the nearest data inside region of the minimum distance. The initial centroids can be designated by the lowest average distance of each data. The minimum distance is set by calculating the average distance between the data. This method is also robust from outliers of data. The experimental results show effectiveness of the proposed method to improve the clustering results with the K-means clustering.
Authors and Affiliations
Ali Ridho Barakbah, Kohei Arai
Keywords
Related Articles
- EP ID EP170943
- DOI 10.24003/emitter.v2i1.17
- Views 102
- Downloads 0
Spatio-Temporal Deforestation Measurement Using Automatic Clustering
Deforestation is one of the crucial issues in Indonesia. In 2012, deforestation rate in Indonesia reached 0.84 million hectares, exceeding Brazil. According to the 2009 Guinness World Records, Indonesia's deforestation r...
Decision Support System for Indonesian Government Fast E-Tendering Based on Vendor Classification
In the last few years in the world of auctions, electronic auctions become a hot topic for discussion, especially in Indonesia. In Indonesia, the auction has been using online electronic system since 2007 with all its ad...
Optimizing Fuzzy Rule Base for Illumination Compensation in Face Recognition using Genetic Algorithms
Fuzzy rule optimization is a challenging step in the development of a fuzzy model. A simple two inputs fuzzy model may have thousands of combination of fuzzy rules when it deals with large number of input variations. Int...
Secure Communication and Information Exchange using Authenticated Ciphertext Policy Attribute-Based Encryption in Mobile Ad-hoc Network
MANETs are considered as suitable for commercial applications such as law enforcement, conference meeting, and sharing information in a student classroom and critical services such as military operations, disaster relief...
Performance of Implementation IBR-DTN and Batman-Adv Routing Protocol in Wireless Mesh Networks
Wireless mesh networks is a network which has high mobility and flexibility network. In Wireless mesh networks nodes are free to move and able to automatically build a network connection with other nodes. High mobility,...