A guided ranking-based clustering using K-Means

被引：0

作者：

Suhailan, S. ^{[1
,2
]}

Samad, S. Abdul ^{[1
]}

Burhanuddin, M. A. ^{[1
]}

Mokhairi, M. ^{[2
]}

机构：

[1] Univ Tekn Malaysia Melaka, Fac Informat & Technol, Durian Tunggal 76100, Melaka, Malaysia

[2] Univ Sultan Zainal Abidin, Fac Informat & Comp, Besut Campus, Besut 22200, Terengganu, Malaysia

来源：

PROCEEDINGS OF MECHANICAL ENGINEERING RESEARCH DAY 2017 (MERD) | 2017年

关键词：

Ranking-based clustering; K-Means;

D O I：

暂无

中图分类号：

TH [机械、仪表工业];

学科分类号：

0802 ;

摘要：

K-Means is a clustering technique that maps object features onto multidimensional coordinates and groups them based on location closeness. However, measuring closest distance can be doubtful when ranking representation of ordinal scale objects are not taken into account. An enhanced of K-Means algorithm called guided rank K-Means (GRank-K-Means) is proposed to achieve better and meaningful result of ranking-based clustering. Based on experiment to cluster marks of 92 students, it shows that by integrating ranking algorithm in K-Means as proposed in GRank-K-Means has improved result accuracy in ranking-based clustering consideration.

引用

页码：255 / 256

页数：2