Analysis of K-Mean and X-Mean Clustering Algorithms Using Ontology-Based Dataset Filtering

In the field of computer science, data mining facilitates the extraction of useful knowledge and patterns from a huge amount of data. Various techniques exist in the data mining domain to explore the links, associations, and patterns from data in data warehouses. Among these techniques, clustering is more prominent in analyzing raw and unlabeled data from a large volume of datasets. The clustering mechanism identifies similar features between data objects and arranges them into clusters. In this paper, we have compared the performance of K-Mean and X Mean clustering algorithms using two datasets of student enrollment in higher education institutions. Our methodology incorporated ontology to filter the datasets and exploited Rapidminer environment to evaluate the performance of clustering algorithms. The results showed that X-Mean is more suitable for large datasets in terms of discovery and accuracy of clusters.