A Three-Phase Artificial Orcas Algorithm for Continuous and Discrete Problems

TL;DR

This paper introduces a novel swarm intelligence algorithm inspired by orca behaviors, simulating multiple animal behaviors simultaneously, and demonstrates its effectiveness on discrete maze problems compared to existing algorithms.

Contribution

The paper presents the first meta-heuristic that models multiple behaviors of a single species simultaneously, enhancing problem-solving capabilities.

Findings

AOA outperforms other algorithms in success rate

AOA has faster run times

AOA achieves smaller solution paths

Abstract

In this paper, a new swarm intelligence algorithm based on orca behaviors is proposed for problem solving. The algorithm called artificial orca algorithm (AOA) consists of simulating the orca lifestyle and in particular the social organization, the echolocation mechanism, and some hunting techniques. The originality of the proposal is that for the first time a meta-heuristic simulates simultaneously several behaviors of just one animal species. AOA was adapted to discrete problems and applied on the maze game with four level of complexity. A bunch of substantial experiments were undertaken to set the algorithm parameters for this issue. The algorithm performance was assessed by considering the success rate, the run time, and the solution path size. Finally, for comparison purposes, the authors conducted a set of experiments on state-of-the-art evolutionary algorithms, namely ACO, BA, BSO, EHO, PSO, and WOA. The overall obtained results clearly show the superiority of AOA over the other tested algorithms.