A wrapper approach for feature selection based on swarm optimization algorithm inspired from the behavior of social-spiders

Citation:
Hossam M. Zawbaa, E. Emary, A. E. Hassanien, and B. PARV, "A wrapper approach for feature selection based on swarm optimization algorithm inspired from the behavior of social-spiders", 7th IEEE International Conference of Soft Computing and Pattern Recognition, , Kyushu University, Fukuoka, Japan,, November 13 - 1, 2015.

Date Presented:

November 13 - 1

Abstract:

In this paper, a proposed system for feature selection
based on social spider optimization (SSO) is proposed. SSO is
used in the proposed system as searching method to find optimal
feature set maximizing classification performance and mimics
the cooperative behavior mechanism of social spiders in nature.
The proposed SSO algorithm considers two different search
agents (social members) male and female spiders, that simulate
a group of spiders with interaction to each other based on the
biological laws of the cooperative colony. Depending on spider
gender, each spider (individual) is simulating a set of different
evolutionary operators of different cooperative behaviors that are
typically found in the colony. The proposed system is evaluated
using different evaluation criteria on 18 different datasets, which
compared with two common search methods namely particle
swarm optimization (PSO), and genetic algorithm (GA). SSO
algorithm proves an advance in classification performance using
different evaluation indicators