Neural Computing and Applications, Год журнала: 2024, Номер unknown
Опубликована: Дек. 19, 2024
Язык: Английский
Artificial Intelligence Review, Год журнала: 2024, Номер 57(8)
Опубликована: Июль 4, 2024
Abstract Rapid industrialization has fueled the need for effective optimization solutions, which led to widespread use of meta-heuristic algorithms. Among repertoire over 600, 300 new methodologies have been developed in last ten years. This increase highlights a sophisticated grasp these novel methods. The biological and natural phenomena inform strategies seen paradigm shift recent observed trend indicates an increasing acknowledgement effectiveness bio-inspired tackling intricate engineering problems, providing solutions that exhibit rapid convergence rates unmatched fitness scores. study thoroughly examines latest advancements optimisation techniques. work investigates each method’s unique characteristics, properties, operational paradigms determine how revolutionary approaches could be problem-solving paradigms. Additionally, extensive comparative analyses against conventional benchmarks, such as metrics search history, trajectory plots, functions, are conducted elucidate superiority approaches. Our findings demonstrate potential optimizers provide directions future research refine expand upon intriguing methodologies. survey lighthouse, guiding scientists towards innovative rooted various mechanisms.
Язык: Английский
Процитировано
19
Heliyon, Год журнала: 2024, Номер 10(11), С. e31850 - e31850
Опубликована: Май 27, 2024
This study introduces the Worst Moth Disruption Strategy (WMFO) to enhance Fly Optimization (MFO) algorithm, specifically addressing challenges related population stagnation and low diversity. The WMFO aims prevent local trapping of moths, fostering improved global search capabilities. Demonstrating a remarkable efficiency 66.6 %, outperforms MFO on CEC15 benchmark test functions. Friedman Wilcoxon tests further confirm WMFO's superiority over state-of-the-art algorithms. Introducing hybrid model, WMFO-MLP, combining with Multi-Layer Perceptron (MLP), facilitates effective parameter tuning for carbon emission prediction, achieving an outstanding total accuracy 97.8 %. Comparative analysis indicates that MLP-WMFO model surpasses alternative techniques in precision, reliability, efficiency. Feature importance reveals variables such as Oil Efficiency Economic Growth significantly impact MLP-WMFO's predictive power, contributing up 40 Additionally, Gas Efficiency, Renewable Energy, Financial Risk, Political Risk explain 26.5 13.6 8 6.5 respectively. Finally, WMFO-MLP performance offers advancements optimization modeling practical applications prediction.
Язык: Английский
Процитировано
7
IEEE Access, Год журнала: 2024, Номер 12, С. 103271 - 103298
Опубликована: Янв. 1, 2024
A recently created optimization algorithm named the Dynamic Hunting Leadership (DHL) was inspired by leadership tactics used in hunting operations. The foundation of DHL is idea that successful can significantly increase endeavors. Although has shown to be relatively simple and tackling a variety practical issues, it been discovered suffers with efficiently balancing global exploration local search phase, particularly high-dimensional numerical problems engineering applications. Furthermore, due drawbacks, vulnerable becoming stuck optimal. present study aims tackle aforementioned challenges introducing modified variant DHL, referred as mDHL, utilizes Levy Flight technique localized development strategy augment each hunter's capacity track their prey attain superior optimal outcomes. Moreover, escape operator quasi-opposition learning are synergistically incorporated foster hunters' techniques. These knowledge sharing between leaders hunters, resulting harmonious blend capabilities. mDHL outperform existing optimizers across 20 function test suites varying dimensions from 30 200 CEC 2019 functions. In addition, successfully applied solve four design cases, demonstrating its practicality. experimental findings indicate substantial improvement over conventional emphasizing potential competitive efficient for addressing challenges.
Язык: Английский
Процитировано
4
Heliyon, Год журнала: 2024, Номер 10(16), С. e35958 - e35958
Опубликована: Авг. 1, 2024
Язык: Английский
Процитировано
4
Cluster Computing, Год журнала: 2024, Номер 28(2)
Опубликована: Ноя. 26, 2024
Язык: Английский
Процитировано
4
Archives of Computational Methods in Engineering, Год журнала: 2025, Номер unknown
Опубликована: Март 29, 2025
Язык: Английский
Процитировано
0
Egyptian Informatics Journal, Год журнала: 2024, Номер 27, С. 100486 - 100486
Опубликована: Июнь 27, 2024
Due to the classical Grey Wolf algorithm GWO does not consider characteristics of local information individual in population, a novel random optimization strategy is proposed make up for defect GWO. In this method, several points neighborhood current location each are selected at axial direction as candidates, and best participate renewal decision individual. Furthermore, our experiments, special first-element dominance characteristic found can greatly improve combination effect global information. order ensure that all constraints violated process constraint industrial design, mixed population initialization method generate individuals meet requirements contain boundary values randomly. addition, treatment shrinking specific dealing with who cross boundary. Experimental results on test function sets show compared recent improved algorithms GWO, has obvious advantages fitness value, convergence speed stability.
Язык: Английский
Процитировано
3
Cluster Computing, Год журнала: 2024, Номер unknown
Опубликована: Июнь 13, 2024
Язык: Английский
Процитировано
1
Neural Computing and Applications, Год журнала: 2024, Номер unknown
Опубликована: Дек. 19, 2024
Язык: Английский
Процитировано
0