MVGL analyser for multi-classifier based spam filtering system
Islam, Md Rafiqul, Zhou, Wanlei and Chowdhury, Morshed U 2009, MVGL analyser for multi-classifier based spam filtering system, in ICIS 2009 : Proceedings of the 8th IEEE/ACIS International Conference on Computer and Information Science 2009, IEEE, Piscataway, N. J., pp. 394-399.
Attached Files
(Some files may be inaccessible until you login with your Deakin Research Online credentials)
Name
Description
MIMEType
Size
Downloads
Title
MVGL analyser for multi-classifier based spam filtering system
ICIS 2009 : Proceedings of the 8th IEEE/ACIS International Conference on Computer and Information Science 2009
Publication date
2009
Start page
394
End page
399
Publisher
IEEE
Place of publication
Piscataway, N. J.
Summary
In the last decade, the rapid growth of the Internet and email, there has been a dramatic growth in spam. Spam is commonly defined as unsolicited email messages and protecting email from the infiltration of spam is an important research issue. Classifications algorithms have been successfully used to filter spam, but with a certain amount of false positive trade-offs, which is unacceptable to users sometimes. This paper presents an approach to overcome the burden of GL (grey list) analyzer as further refinements to our multi-classifier based classification model (Islam, M. and W. Zhou 2007). In this approach, we introduce a ldquomajority voting grey list (MVGL)rdquo analyzing technique which will analyze the generated GL emails by using the majority voting (MV) algorithm. We have presented two different variations of the MV system, one is simple MV (SMV) and other is the ranked MV (RMV). Our empirical evidence proofs the improvements of this approach compared to the existing GL analyzer of multi-classifier based spam filtering process.
ISBN
9780769536415
Language
eng
Field of Research
080105 Expert Systems
Socio Economic Objective
810107 National Security
HERDC Research category
E2 Full written paper - non-refereed / Abstract reviewed