Title: Classification of data at multilevel abstraction

Authors: Varsha Namdeo; Ramjeevan Singh Thakur

Addresses: Department of Computer Application, MANIT, Bhopal, Madhya Pradesh, 462-052, India ' Department of Computer Application, MANIT, Bhopal, Madhya Pradesh, 462-052, India

Abstract: Applying the association rule in classification can improve the accuracy and obtain some valuable rules and information that cannot be captured by other classification approaches. We consider additional application requirement by extending our scope to include multilevel classification. Classification with association rules at multilevel involve concepts at different level of abstraction. For many applications, it is required to classify data at different levels due to sparsity of data. This work will help in those applications where data is scattered in multilevel hierarchy and required classification of data at all different levels of abstraction.

Keywords: multilevel abstraction; multilevel classification; CARs; associative classification; data classification; association rules.

DOI: 10.1504/IJICT.2014.060394

International Journal of Information and Communication Technology, 2014 Vol.6 No.2, pp.142 - 155

Received: 01 Apr 2013
Accepted: 28 Jun 2013
Published online: 26 Jul 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article