Improving spam detection using neural networks trained by memetic algorithm

Shaveen Singh; Anish Chand; Sunil Pranit Lal

doi:10.1109/CIMSim.2013.18

Improving spam detection using neural networks trained by memetic algorithm

Shaveen Singh, Anish Chand, Sunil Pranit Lal

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

7 Citations (Scopus)

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.

Original language	English
Title of host publication	Proceedings - 2013 5th International Conference on Computational Intelligence, Modelling and Simulation, CIMSim 2013
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	55-60
Number of pages	6
ISBN (Print)	9780769551555
DOIs	https://doi.org/10.1109/CIMSim.2013.18
Publication status	Published - 2013
Externally published	Yes
Event	International Conference on Computational Intelligence, Modelling and Simulation 2013 - Seoul, Korea, South Duration: 24 Sept 2013 → 26 Sept 2013 Conference number: 5th https://ieeexplore.ieee.org/xpl/conhome/6656125/proceeding (Proceedings)

Publication series

Name	Proceedings of International Conference on Computational Intelligence, Modelling and Simulation
ISSN (Print)	2166-8523
ISSN (Electronic)	2166-8531

Conference

Conference	International Conference on Computational Intelligence, Modelling and Simulation 2013
Abbreviated title	CSSim 2013
Country/Territory	Korea, South
City	Seoul
Period	24/09/13 → 26/09/13
Internet address	https://ieeexplore.ieee.org/xpl/conhome/6656125/proceeding (Proceedings)

Keywords

Genetic Algorithm
Memetic Algorithms
Neural Network
Simulated Annealing
Spam classification

Access to Document

10.1109/CIMSim.2013.18

Cite this

Singh, S., Chand, A., & Lal, S. P. (2013). Improving spam detection using neural networks trained by memetic algorithm. In Proceedings - 2013 5th International Conference on Computational Intelligence, Modelling and Simulation, CIMSim 2013 (pp. 55-60). (Proceedings of International Conference on Computational Intelligence, Modelling and Simulation). IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/CIMSim.2013.18

Singh, Shaveen ; Chand, Anish ; Lal, Sunil Pranit. / Improving spam detection using neural networks trained by memetic algorithm. Proceedings - 2013 5th International Conference on Computational Intelligence, Modelling and Simulation, CIMSim 2013. IEEE, Institute of Electrical and Electronics Engineers, 2013. pp. 55-60 (Proceedings of International Conference on Computational Intelligence, Modelling and Simulation).

@inproceedings{54b50c42e0c94b418d336356debf016f,

title = "Improving spam detection using neural networks trained by memetic algorithm",

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.",

keywords = "Genetic Algorithm, Memetic Algorithms, Neural Network, Simulated Annealing, Spam classification",

author = "Shaveen Singh and Anish Chand and Lal, \{Sunil Pranit\}",

year = "2013",

doi = "10.1109/CIMSim.2013.18",

language = "English",

isbn = "9780769551555",

series = "Proceedings of International Conference on Computational Intelligence, Modelling and Simulation",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

pages = "55--60",

booktitle = "Proceedings - 2013 5th International Conference on Computational Intelligence, Modelling and Simulation, CIMSim 2013",

address = "United States of America",

note = "International Conference on Computational Intelligence, Modelling and Simulation 2013, CSSim 2013 ; Conference date: 24-09-2013 Through 26-09-2013",

url = "https://ieeexplore.ieee.org/xpl/conhome/6656125/proceeding",

}

Singh, S, Chand, A & Lal, SP 2013, Improving spam detection using neural networks trained by memetic algorithm. in Proceedings - 2013 5th International Conference on Computational Intelligence, Modelling and Simulation, CIMSim 2013. Proceedings of International Conference on Computational Intelligence, Modelling and Simulation, IEEE, Institute of Electrical and Electronics Engineers, pp. 55-60, International Conference on Computational Intelligence, Modelling and Simulation 2013, Seoul, Korea, South, 24/09/13. https://doi.org/10.1109/CIMSim.2013.18

Improving spam detection using neural networks trained by memetic algorithm. / Singh, Shaveen; Chand, Anish; Lal, Sunil Pranit.
Proceedings - 2013 5th International Conference on Computational Intelligence, Modelling and Simulation, CIMSim 2013. IEEE, Institute of Electrical and Electronics Engineers, 2013. p. 55-60 (Proceedings of International Conference on Computational Intelligence, Modelling and Simulation).

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

TY - GEN

T1 - Improving spam detection using neural networks trained by memetic algorithm

AU - Singh, Shaveen

AU - Chand, Anish

AU - Lal, Sunil Pranit

N1 - Conference code: 5th

PY - 2013

Y1 - 2013

N2 - 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.

AB - 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.

KW - Genetic Algorithm

KW - Memetic Algorithms

KW - Neural Network

KW - Simulated Annealing

KW - Spam classification

UR - http://www.scopus.com/inward/record.url?scp=84892754142&partnerID=8YFLogxK

U2 - 10.1109/CIMSim.2013.18

DO - 10.1109/CIMSim.2013.18

M3 - Conference Paper

AN - SCOPUS:84892754142

SN - 9780769551555

T3 - Proceedings of International Conference on Computational Intelligence, Modelling and Simulation

SP - 55

EP - 60

BT - Proceedings - 2013 5th International Conference on Computational Intelligence, Modelling and Simulation, CIMSim 2013

PB - IEEE, Institute of Electrical and Electronics Engineers

T2 - International Conference on Computational Intelligence, Modelling and Simulation 2013

Y2 - 24 September 2013 through 26 September 2013

ER -

Singh S, Chand A, Lal SP. Improving spam detection using neural networks trained by memetic algorithm. In Proceedings - 2013 5th International Conference on Computational Intelligence, Modelling and Simulation, CIMSim 2013. IEEE, Institute of Electrical and Electronics Engineers. 2013. p. 55-60. (Proceedings of International Conference on Computational Intelligence, Modelling and Simulation). doi: 10.1109/CIMSim.2013.18

Improving spam detection using neural networks trained by memetic algorithm

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Cite this