Artificial hummingbird algorithm with chaotic-opposition-based population initialization for solving real-world problems

The artificial hummingbird algorithm is a global search mechanism with many applications in engineering design, but it tends to stall in high-dimensional problems with locally optimal solutions. To address this issue, this paper enhances an artificial hummingbird algorithm by using a chaos map and o...

Full description

Saved in:
Bibliographic Details
Published in:Neural computing & applications Vol. 37; no. 27; pp. 22529 - 22572
Main Authors: Kaur, Sumandeep, Kaur, Lakhwinder, Lal, Madan
Format: Journal Article
Language:English
Published: London Springer London 01.09.2025
Springer Nature B.V
Subjects:
Algorithms
Artificial Intelligence
Benchmarks
Computational Biology/Bioinformatics
Computational Science and Engineering
Computer Science
Convergence
Data Mining and Knowledge Discovery
Design engineering
Effectiveness
Exploitation
Foraging behavior
Genetic algorithms
Heuristic methods
Hunting
Image Processing and Computer Vision
Leadership
Machine learning
Mathematical models
Optimization
Optimization algorithms
Optimization techniques
Physics
Probability and Statistics in Computer Science
S.I.: Hybrid Approaches to Nature-inspired Optimization Algorithms and Their Applications
Social behavior
Special Issue on Hybrid Approaches to Nature-inspired Optimization Algorithms and Their Applications
Statistical analysis
Statistical tests
Whales & whaling
Wolves
Artificial hummingbird
Modified artificial hummingbird
Opposition-based learning
Metaheuristic algorithms
Chaotic maps
ISSN:0941-0643, 1433-3058
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The artificial hummingbird algorithm is a global search mechanism with many applications in engineering design, but it tends to stall in high-dimensional problems with locally optimal solutions. To address this issue, this paper enhances an artificial hummingbird algorithm by using a chaos map and opposition-based method for population initialization to combat the lack of population diversity, the imbalance between exploration and exploitation, and the algorithm’s premature convergence. The randomness of chaos maps has been leveraged to prevent solutions trapped in local optima and facilitate faster convergence. Moreover, an opposition-based population can serve as a better initial solution and accelerate convergence when compared to random initialization. Two numerical test suites are used to evaluate the efficacy of the proposed algorithm: 50 benchmark functions and the CEC 2018 benchmark test suite. The outcomes are compared to eight other cutting-edge metaheuristic algorithms. Wilcoxon rank sum test, Friedman test, and mean absolute error are used to conduct additional statistical analysis on the data. Moreover, experiments are conducted on the aforementioned 57 real-world optimization problems to demonstrate the efficacy of the proposed method. The outcomes are contrasted to the algorithms SASS, MAgES, EnMODE, and COLSHADE (which won the CEC2020 Competition on Real-World Single-Objective Constrained Optimization). All quantitative and qualitative results on benchmark functions, statistical tests, as well as real-world optimization problem results demonstrate that the proposed algorithm is competitive and preferable to the metaheuristics considered in the experiments. Hence it is concluded that the proposed algorithm balances exploration and exploitation more effectively and the population initialization technique is conducive to augmenting the search capabilities of the artificial hummingbird algorithm.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0941-0643
1433-3058
DOI:10.1007/s00521-024-10621-4