Welcome to the InfoSci Platform
Comparative Study Between a Swarm Intelligence for Detection and Filtering of SPAM: Social Bees vs. Inspiration From the Human Renal

Comparative Study Between a Swarm Intelligence for Detection and Filtering of SPAM: Social Bees vs. Inspiration From the Human Renal

Mohamed Amine Boudia, Mohamed Elhadi Rahmani, Amine Rahmani
Copyright: © 2018 |Pages: 28
ISBN13: 9781522530046|ISBN10: 1522530045|EISBN13: 9781522530053
DOI: 10.4018/978-1-5225-3004-6.ch003
Cite Chapter Cite Chapter

MLA

Boudia, Mohamed Amine, et al. "Comparative Study Between a Swarm Intelligence for Detection and Filtering of SPAM: Social Bees vs. Inspiration From the Human Renal." Handbook of Research on Biomimicry in Information Retrieval and Knowledge Management, edited by Reda Mohamed Hamou, IGI Global, 2018, pp. 38-65. https://doi.org/10.4018/978-1-5225-3004-6.ch003

APA

Boudia, M. A., Rahmani, M. E., & Rahmani, A. (2018). Comparative Study Between a Swarm Intelligence for Detection and Filtering of SPAM: Social Bees vs. Inspiration From the Human Renal. In R. Hamou (Ed.), Handbook of Research on Biomimicry in Information Retrieval and Knowledge Management (pp. 38-65). IGI Global. https://doi.org/10.4018/978-1-5225-3004-6.ch003

Chicago

Boudia, Mohamed Amine, Mohamed Elhadi Rahmani, and Amine Rahmani. "Comparative Study Between a Swarm Intelligence for Detection and Filtering of SPAM: Social Bees vs. Inspiration From the Human Renal." In Handbook of Research on Biomimicry in Information Retrieval and Knowledge Management, edited by Reda Mohamed Hamou, 38-65. Hershey, PA: IGI Global, 2018. https://doi.org/10.4018/978-1-5225-3004-6.ch003

Export Reference

Mendeley
Favorite

Abstract

This chapter is a comparative study between two bio-inspired approaches based on swarm intelligence for detection and filtering of SPAM: social bees vs. inspiration from the human renal. The authors took inspiration from biological model and use two meta-heuristics because the effects allow the authors to detect the characteristics of unwanted data. Messages are indexed and represented by the n-gram words and characters independent of languages (because a message can be received in any language). The results are promising and provide an important way to use this model for solving other problems in data mining. The authors start this paper with a short introduction where they show the importance of IT security. Then they give a little insight into the state of the art, before starting the essential part of a scientific paper, where they explain and experiment with two original meta-heuristics, and explain the natural model. Then they detail the artificial model.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.