A REVIEW ON K-mean ALGORITHM AND IT’S DIFFERENT DISTANCE MATRICS

Abstract

-Data mining is a process of extracting desired and useful information from the pool of data. Clustering in data mining is the grouping of data points with some common similarity. Clustering is an important aspect of data mining. It simply clusters the data sets into given no. of clusters. Various no. of methods have been used for the data clustering among which K-means is the most widely used clustering algorithm. In this paper we have briefed in the form of a review work done by different researchers using K-means clustering algorithm. We have also analysed different distance metrics used by them for distance evaluation.

Evaluation the influence of distance-based K-means method for detecting moving vehicles

“…The K-Means clustering algorithm employs Euclidean distance [17], [18] to measure the similarity between objects. Besides using the Euclidean distance, other distance metrics can also be used and this method is called the median-K method.…”

Implementasi Algoritma K-Means untuk Klasterisasi Peserta Olimpiade Sains Nasional Tingkat SMA

“…Salah satu metode yang dapat digunakan dalam Data Mining adalah metode Clustering dengan algoritma K-Means [4]. Algoritma K-Means Clustering adalah teknik dalam Data Mining yang mempartisi data yang ada ke dalam beberapa cluster sehingga data yang memiliki karakteristik yang sama akan dikelompokkan ke dalam satu cluster sedangkan data dengan karakteristik yang berbeda akan dikelompokkan ke dalam cluster lain [5]. Algoritma K-Means melakukan dua proses yaitu proses penentuan pusat cluster (centroid) dan proses pencarian anggota dari tiap-tiap cluster [6].…”