Opposition learning based phases in artificial bee colony

Artificial bee colony (ABC) is a recently introduced swarm intelligence algorithm (SIA). Initially only unconstrained problems were handled by ABC, which was later modified by embedding one more parameter called modified rate to handle constrained problems. Since then, ABC and its variants have shown a remarkable success in the domain of swarm intelligence optimization algorithms. The exploration capability of ABC is comparatively better than exploitation which sometimes limits the convergence rate of ABC while handling multimodal optimization problems. In this study the foraging process of two phases has been enhanced by embedding opposition based learning concept. This modification is introduced to enhance the acceleration and exploitation capability of ABC. The variant is named as O-ABC (Opposition based ABC). The efficiency of O-ABC is initially evaluated on 12 benchmark functions consulted from literature. Later O-ABC is applied for intrusion detection. The simulated comparative results have shown the competitiveness of the proposal.