A Comparative Study on Feature Selection Using Data Mining Tools

Provided by: International Journal of Advanced Research in Computer Science and Software Engineering (IJARCSSE)
Topic: Data Management
Format: PDF
Clustering is an important technique of data mining. Clustering is an unsupervised learning problem that group objects based upon distance or similarity. Each group is known as a cluster. In this paper, the authors make use of a large database 'Cardiology dataset' containing 14 attributes and 303 instances to perform Feature Selection on K-means algorithm. They compared the results of simple clustering technique and clustering (K-means) with feature selection for Cardiology dataset, based upon various parameter using WEKA (Waikato Environment for Knowledge Analysis) and TANAGRA data mining tools. The results of the experiment show that clustering with feature selection give promising results on WEKA with utmost accuracy rate and robustness.

Find By Topic