USP Electronic Research Repository

Improving spam detection using neural networks trained by memetic algorithm

Singh, Shaveen and Chand, A. and Lal, Sunil P. (2013) Improving spam detection using neural networks trained by memetic algorithm. [Conference Proceedings]

Full text not available from this repository.

Abstract

In this paper we train an Artificial Neural Network (ANN) using Memetic Algorithm (MA) and evaluate its performance on the UCI spambase dataset. The Memetic algorithm incorporates the local search capacity of Simulated Annealing (SA) and the global search capability of Genetic Algorithm (GA) to optimize the parameters of the ANN. The performance of the MA is compared with traditional GA in training the ANN. We further explore the different parameters, mechanisms and architectures used to optimize the performance of the network and attain a practical balance between the global genetic algorithm and the local search technique. Classification using ANN trained by MA yielded better results on the spambase dataset compared with other algorithms reported in literature.

Item Type: Conference Proceedings
Additional Information: DOI: 10.1109/CIMSim.2013.18
Uncontrolled Keywords: genetic algorithms;learning (artificial intelligence);neural nets;search problems;simulated annealing;unsolicited e-mail;ANN;MA;UCI spambase dataset;artificial neural network;global genetic algorithm;global search capability;hybrid learning algorithm;local search capacity;memetic algorithm;simulated annealing;spam detection;Artificial neural networks;Biological cells;Genetic algorithms;Neurons;Sociology;Training;Unsolicited electronic mail;Genetic Algorithm;Memetic Algorithms;Neural Network;Simulated Annealing;Spam classification
Subjects: Q Science > QA Mathematics
Divisions: Faculty of Science, Technology and Environment (FSTE) > School of Computing, Information and Mathematical Sciences
Depositing User: Shaveen Singh
Date Deposited: 02 Apr 2014 04:33
Last Modified: 06 Jul 2016 23:49
URI: https://repository.usp.ac.fj/id/eprint/7281

Actions (login required)

View Item View Item