Improved multi-core arithmetic optimization algorithm-based ensemble mutation for multidisciplinary applications

Laith Abualigah, Ali Diabat

Research output: Contribution to journalArticlepeer-review

Abstract

This paper proposes a new search method based on an augmented version of the Arithmetic Optimization Algorithm to solve various benchmark functions, engineering design cases, and feature selection problems. The proposed method is called MCAOA, combined with the Marine Predators Algorithm and a new proposed Ensemble Mutation Strategy. The Arithmetic Optimization Algorithm is a new meta-heuristic technique used to solve optimization problems. Sometimes, Arithmetic Optimization Algorithm faces convergence problems and falls into local optima for specific optimization problems, especially large-scale and multimodal problems. The Marine Predators Algorithm and Ensemble Mutation Strategy improve the Arithmetic Optimization Algorithm’s convergence rate and equilibrium in the exploration and exploitation search methods. The proposed method is tested on 23 different benchmark functions, seven common engineering design cases, and sixteen feature selection problems. The obtained results are compared with other well-known and state-of-the-art methods. The experimental results indicated that the proposed method found new best solutions for different complicated problems; the general performance is promising compared to other comparative methods.

Original languageEnglish (US)
JournalJournal of Intelligent Manufacturing
DOIs
StateAccepted/In press - 2022

Keywords

  • Arithmetic optimization algorithm (AOA)
  • Engineering design problems
  • Ensemble mutation
  • Feature selection
  • Global optimization
  • Marine predators algorithm

ASJC Scopus subject areas

  • Software
  • Industrial and Manufacturing Engineering
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Improved multi-core arithmetic optimization algorithm-based ensemble mutation for multidisciplinary applications'. Together they form a unique fingerprint.

Cite this