You can view the full text of this article for free using the link below.

Title: A nearest neighbour classifier based on probabilistically/possibilistically intervals' number for spam filtering

Authors: Yazdan Jamshidi

Addresses: Young Researchers and Elite Club, Kermanshah Branch, Islamic Azad University, Kermanshah, Iran

Abstract: Today, e-mail has become one of the fastest and most economical forms of communication in modern life. However, the increase in e-mail users has resulted in a significant boosting in unsolicited e-mails, widely known as spam, during the past few years. This paper presents an application of Interval's Number KNN (INKNN) for spam filtering. The INKNN algorithm was described lately as a lattice data domain extension of KNN classifier. In our experiment a spam e-mail was presented in the metric space of lattice ordered Interval's Number. Indeed a population of spam e-mails was presented by an Intervals Number. Then INKNN classifier was employed distinguish spam e-mails from non-spam. To investigate the effectiveness of our methods, we conduct extensive experiments on SpamAssassin public mail corpus. Experimental results show that the proposed model is able to achieve higher performance in comparison with those from a number of state-of-the-art machine learning techniques published in the literature.

Keywords: lattice theory; k-nearest neighbour; kNN; spam filtering; interval numbers; classification; probabilistic intervals; possibilistic intervals; email spam; unsolicited emails; machine learning.

DOI: 10.1504/IJSCN.2016.077040

International Journal of Soft Computing and Networking, 2016 Vol.1 No.1, pp.4 - 16

Received: 10 Oct 2013
Accepted: 26 Jun 2014

Published online: 20 Jun 2016 *

Full-text access for editors Access for subscribers Free access Comment on this article