Reinforcement learning guided Spearman dynamic opposite Gradient-based optimizer for numerical optimization and anchor clustering DOI Creative Commons
Kangjian Sun,

Ju Huo,

Heming Jia

et al.

Journal of Computational Design and Engineering, Journal Year: 2023, Volume and Issue: 11(1), P. 12 - 33

Published: Dec. 20, 2023

Abstract As science and technology advance, the need for novel optimization techniques has led to an increase. The recently proposed metaheuristic algorithm, Gradient-based optimizer (GBO), is rooted in gradient-based Newton's method. GBO a more concrete theoretical foundation. However, gradient search rule (GSR) local escaping operator (LEO) operators still have some shortcomings. insufficient updating method simple selection process limit performance of algorithm. In this paper, improved version compensate above shortcomings, called RL-SDOGBO. First, during GSR phase, Spearman rank correlation coefficient used determine weak solutions on which perform dynamic opposite learning. This operation assists algorithm escape from optima enhance exploration capability. Secondly, optimize exploitation capability, reinforcement learning guide solution update modes LEO operator. RL-SDOGBO tested 12 classical benchmark functions CEC2022 with seven representative metaheuristics, respectively. impact improvements, scalability running time balance are analyzed discussed. Combining experimental results statistical results, exhibits excellent numerical provides high-quality most cases. addition, also solve anchor clustering problem small target detection, making it potential competitive option.

Language: Английский

MSAO: A multi-strategy boosted snow ablation optimizer for global optimization and real-world engineering applications DOI
Yaning Xiao, Hao Cui, Abdelazim G. Hussien

et al.

Advanced Engineering Informatics, Journal Year: 2024, Volume and Issue: 61, P. 102464 - 102464

Published: March 15, 2024

Language: Английский

Citations

32
Guided learning strategy: A novel update mechanism for metaheuristic algorithms design and improvement DOI
Heming Jia,

Chenghao Lu

Knowledge-Based Systems, Journal Year: 2024, Volume and Issue: 286, P. 111402 - 111402

Published: Jan. 13, 2024

Language: Английский

Citations

24
Review of the metaheuristic algorithms in applications: Visual analysis based on bibliometrics (1994–2023) DOI
Guanghui Li,

Taihua Zhang,

Chieh-Yuan Tsai

et al.

Expert Systems with Applications, Journal Year: 2024, Volume and Issue: 255, P. 124857 - 124857

Published: July 23, 2024

Language: Английский

Citations

21
Improved multi-strategy beluga whale optimization algorithm: a case study for multiple engineering optimization problems DOI
Hao Zou, Kai Wang

Cluster Computing, Journal Year: 2025, Volume and Issue: 28(3)

Published: Jan. 21, 2025

Language: Английский

Citations

1
Enhanced object detection in remote sensing images by applying metaheuristic and hybrid metaheuristic optimizers to YOLOv7 and YOLOv8 DOI Creative Commons
Khaled Mohammed Elgamily, Mohamed A. Mohamed, Ahmed Aboutaleb

et al.

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Feb. 28, 2025

Abstract Developments in object detection algorithms are critical for urban planning, environmental monitoring, surveillance, and many other applications. The primary objective of the article was to improve precision model efficiency. paper compared performance six different metaheuristic optimization including Gray Wolf Optimizer (GWO), Particle Swarm Optimization (PSO), Genetic Algorithm (GA), Remora (ROA), Aquila (AO), Hybrid PSO–GWO (HPSGWO) combined with YOLOv7 YOLOv8. study included two distinct remote sensing datasets, RSOD VHR-10. Many measures as precision, recall, mean average (mAP) were used during training, validation, testing processes, well fit score. results show significant improvements both YOLO variants following using these strategies. GWO-optimized 0.96 mAP 50, 0.69 50:95, HPSGWO-optimized YOLOv8 0.97 0.72 50:95 had best dataset. Similarly, versions on VHR-10 dataset 0.87 0.58 0.99 YOLOv8, indicating greater performance. findings supported usefulness increasing recall rates demonstrated major significance improving recognition tasks imaging, opening up a viable route applications variety disciplines.

Language: Английский

Citations

1
Memory backtracking strategy: An evolutionary updating mechanism for meta-heuristic algorithms DOI
Heming Jia,

Chenghao Lu,

Zhikai Xing

et al.

Swarm and Evolutionary Computation, Journal Year: 2023, Volume and Issue: 84, P. 101456 - 101456

Published: Dec. 27, 2023

Language: Английский

Citations

21
Modified beluga whale optimization with multi-strategies for solving engineering problems DOI Creative Commons
Heming Jia, Qixian Wen, Di Wu

et al.

Journal of Computational Design and Engineering, Journal Year: 2023, Volume and Issue: 10(6), P. 2065 - 2093

Published: Oct. 5, 2023

Abstract The beluga whale optimization (BWO) algorithm is a recently proposed metaheuristic that simulates three behaviors: whales interacting in pairs to perform mirror swimming, population sharing information cooperate predation, and fall. However, the performance of BWO still needs be improved enhance its practicality. This paper proposes modified (MBWO) with multi-strategy. It was inspired by whales’ two group gathering for foraging searching new habitats long-distance migration. aggregation strategy (GAs) migration (Ms). GAs can improve local development ability accelerate overall rate convergence through fine search; Ms randomly moves towards periphery population, enhancing jump out optima. In order verify MBWO, this article conducted comprehensive testing on MBWO using 23 benchmark functions, IEEE CEC2014, CEC2021. experimental results indicate has strong ability. also tests MBWO’s solve practical engineering problems five problems. final prove effectiveness solving

Language: Английский

Citations

19
Synergistic Swarm Optimization Algorithm DOI Open Access

Sharaf Alzoubi,

Laith Abualigah,

Mohamed Sharaf

et al.

Computer Modeling in Engineering & Sciences, Journal Year: 2023, Volume and Issue: 139(3), P. 2557 - 2604

Published: Dec. 26, 2023

This research paper presents a novel optimization method called the Synergistic Swarm Optimization Algorithm (SSOA).The SSOA combines principles of swarm intelligence and synergistic cooperation to search for optimal solutions efficiently.A mechanism is employed, where particles exchange information learn from each other improve their behaviors.This enhances exploitation promising regions in space while maintaining exploration capabilities.Furthermore, adaptive mechanisms, such as dynamic parameter adjustment diversification strategies, are incorporated balance exploitation.By leveraging collaborative nature integrating cooperation, aims achieve superior convergence speed solution quality performance compared algorithms.The effectiveness proposed investigated solving 23 benchmark functions various engineering design problems.The experimental results highlight potential addressing challenging problems, making it tool wide range applications beyond.Matlab codes available at: https://www.mathworks.com/matlabcentral/fileexchange/153466-synergistic

Language: Английский

Citations

17
Improve coati optimization algorithm for solving constrained engineering optimization problems DOI Creative Commons
Heming Jia,

Shengzhao Shi,

Di Wu

et al.

Journal of Computational Design and Engineering, Journal Year: 2023, Volume and Issue: 10(6), P. 2223 - 2250

Published: Oct. 26, 2023

Abstract The coati optimization algorithm (COA) is a meta-heuristic proposed in 2022. It creates mathematical models according to the habits and social behaviors of coatis: (i) In group organization coatis, half coatis climb trees chase their prey away, while other wait beneath catch it (ii) Coatis avoidance predators behavior, which gives strong global exploration ability. However, over course our experiment, we uncovered opportunities for enhancing algorithm’s performance. When confronted with intricate problems, certain limitations surfaced. Much like long-nosed raccoon gradually narrowing its search range as approaches optimal solution, COA exhibited tendencies that could result reduced convergence speed risk becoming trapped local optima. this paper, propose an improved (ICOA) enhance efficiency. Through sound-based envelopment strategy, can capture more quickly accurately, allowing converge rapidly. By employing physical exertion have greater variety escape options when being chased, thereby exploratory capabilities ability Finally, lens opposition-based learning strategy added improve To validate performance ICOA, conducted tests using IEEE CEC2014 CEC2017 benchmark functions, well six engineering problems.

Language: Английский

Citations

14
Improved sandcat swarm optimization algorithm for solving global optimum problems DOI Creative Commons
Heming Jia, Jinrui Zhang, Honghua Rao

et al.

Artificial Intelligence Review, Journal Year: 2024, Volume and Issue: 58(1)

Published: Nov. 4, 2024

The sand cat swarm optimization algorithm (SCSO) is a metaheuristic proposed by Amir Seyyedabbasi et al. SCSO mimics the predatory behavior of cats, which gives strong optimized performance. However, as number iterations increases, moving efficiency decreases, resulting in decline search ability. convergence speed gradually and it easy to fall into local optimum, difficult find better solution. In order improve movement cat, enhance global ability performance algorithm, an improved Swarm Optimization (ISCSO) was proposed. ISCSO we propose low-frequency noise strategy spiral contraction walking according habit add random opposition-based learning restart strategy. frequency factor used control direction hunting carried out, effectively randomness population, expanded range enhanced accelerated algorithm. We use 23 standard benchmark functions IEEE CEC2014 compare with 10 algorithms, prove effectiveness Finally, evaluated using five constrained engineering design problems. results these problems, has 3.08%, 0.23%, 0.37%, 22.34%, 1.38% improvement compared original respectively, proves practical application source code website for https://github.com/Ruiruiz30/ISCSO-s-code.

Language: Английский

Citations

5