Backpropagation Learning Algorithms for Email Classification.
Journal Title: International Journal on Computer Science and Engineering - Year 2016, Vol 8, Issue 7
Abstract
Today email has become one the fastest and most effective form of communication. The popularity of this mode of transmitting goods, information and services has motivated spammers to perfect their technical skills to fool spam filters. This development has worsened the problems faced by Internet users as they have to deal with email congestion, email overload and unprioritised email messages. The result was an exponential increase in the number of email classification management tools for the past few decades. In this paper we propose a new spam classifier using a learning process of multilayer neural network to implement back propagation technique. Our contribution to the body of knowledge is the use of an improved empirical analysis to choose an optimum, novel collection of attributes of a user’s email contents that allows a quick detection of most important words in emails. We also demonstrate the effectiveness of two equal sets of emails training and testing data.
Authors and Affiliations
*David Ndumiyana and Tarirayi Mukabeta
Keywords
Related Articles
- EP ID EP128488
- DOI -
- Views 106
- Downloads 0
An Enhanced Active contour based Segmentation for Fingerprint Extraction
Fingerprint Segmentation is one of the critical and important steps in Automatic Fingerprint Recognition System (AFIS). It is a process that separates the fingerprint image into two regions, the foreground and background...
Destination Sequenced – Distance Vector Algorithm
Mobile Ad Hoc Network (MANET) is an infrastructure where nodes communicate without any central administration. Nodes are connected through wireless channels and can use multiple hops to exchange data. Routing protocols a...
Overload Identification for Multiprocessor in Real Time System
In spite of many real time scheduling algorithms available it is not clear that these scheduling algorithms support fully the problems in the real time system in a local area network. There are certain “open loop” algori...
Association Rules Extraction from Incremental Databases through ICPT
Association Rule Mining is an important task in data mining. This paper proposes two stage ICPT (Incremental Compact Pattern Tree) Construction Methodology. This methodology facilitates to obtain incidental association r...
IP Address Blocking System
Hosting a site on the Internet makes it available everywhere. There are certain sites that are just meant for local use like local shopping marts that do not provide products for purchase in other countries. Also, there...