دانلود Mining XML data using K-means and Manhattan algorithms

Abstract

over the last two decades, XML has astonishing developed for describing semi-structured data and exchanging data over the web. Thus,  applying data mining techniques to XML data has become necessary  .

K-means clustering is one of the most popular algorithms in the clustering of data mining. Recently, there have been some researches undertaken on the mining XML data.

In this paper, applying k-means algorithm, which is one of the clustering algorithms, on XML data is proposed. K-means as an algorithm chooses centroids and then clustering the XML data into groups according to the centroids. The comparison distances between each element vary with every centroid and will make groups of elements together. The closest elements from each others will be in the same group. The distances are measured using the Manhattan algorithm. In this research a specific application has been build, the application allows the user to upload an XML file, choose the target field and select the number of clusters. As a result, the application shows the clusters and centroids used in all of the steps.