Today communication has been revolutionized with email and other online communication systems. However, some computer users have abused the technology used to drive these communications, by sending out thousands and thousands of spam emails with little or no purpose other than to increase traffic or decrease bandwidth. With the electronic mail emerging as the primary means of communication, sorting of electronic mails is of prime importance. Most current sorting techniques are rule based, in which the user is supposed to give a set of rules, according to which mails are sorted. But configuring these rules is a tedious and often impossible task due to the variety of emails. In this paper a technique using neural network is deployed which automatically removes unwanted incoming mails, without the need for constant user intervention as well as its accuracy is analyzed in parallel.
[1]
Paolo Frasconi,et al.
Learning in multilayered networks used as autoassociators
,
1995,
IEEE Trans. Neural Networks.
[2]
K. C. Ho,et al.
A formal selection and pruning algorithm for feedforward artificial neural network optimization
,
1999,
IEEE Trans. Neural Networks.
[3]
Mehran Sahami.
Applications of Machine Learning to Information Access
,
1997,
AAAI/IAAI.
[4]
Yue Yang,et al.
Anti-Spam Filtering Using Neural Networks and Baysian Classifiers
,
2007,
2007 International Symposium on Computational Intelligence in Robotics and Automation.
[5]
Alberto Tesi,et al.
On the Problem of Local Minima in Backpropagation
,
1992,
IEEE Trans. Pattern Anal. Mach. Intell..