HBWO-JS: jellyfish search boosted hybrid beluga whale optimization algorithm for engineering applications

Journal of Computational Design and Engineering, Journal Year: 2023, Volume and Issue: 10(4), P. 1615 - 1656

Published: June 27, 2023

Abstract Beluga whale optimization (BWO) algorithm is a recently proposed population intelligence algorithm. Inspired by the swimming, foraging, and falling behaviors of beluga populations, it shows good competitive performance compared to other state-of-the-art algorithms. However, original BWO faces challenges unbalanced exploration exploitation, premature stagnation iterations, low convergence accuracy in high-dimensional complex applications. Aiming at these challenges, hybrid based on jellyfish search optimizer (HBWO-JS), which combines vertical crossover operator Gaussian variation strategy with fusion (JS) optimizer, developed for solving global this paper. First, fused JS improve problem that tends fall into best local solution exploitation stage through multi-stage collaborative exploitation. Then, introduced cross solves processes normalizing upper lower bounds two stochastic dimensions agent, thus further improving overall capability. In addition, forces agent explore minimum neighborhood, extending entire iterative process alleviating Finally, superiority HBWO-JS verified detail comparing basic eight algorithms CEC2019 CEC2020 test suites, respectively. Also, scalability evaluated three (10D, 30D, 50D), results show stable terms dimensional scalability. practical engineering designs Truss topology problems demonstrate practicality HBWO-JS. The has strong ability broad application prospects.

Language: Английский

---

Multi-threshold remote sensing image segmentation with improved ant colony optimizer with salp foraging

Journal of Computational Design and Engineering, Journal Year: 2023, Volume and Issue: 10(6), P. 2200 - 2221

Published: Oct. 16, 2023

Abstract Remote sensing images can provide direct and accurate feedback on urban surface morphology geographic conditions. They be used as an auxiliary means to collect data for current geospatial information systems, which are also widely in city public safety. Therefore, it is necessary research remote images. we adopt the multi-threshold image segmentation method this paper segment research. We first introduce salp foraging behavior into continuous ant colony optimization algorithm (ACOR) construct a novel ACOR version based (SSACO). The original algorithm’s convergence ability avoid hitting local optima enhanced by behavior. In order illustrate key benefit, SSACO tested against 14 fundamental algorithms using 30 benchmark test functions IEEE CEC2017. Then, compared with other algorithms. experimental results examined from various angles, findings convincingly demonstrate main power of SSACO. performed comparison studies 12 between techniques several peer approaches benefits segmentation. Peak signal-to-noise ratio, structural similarity index, feature index evaluation demonstrated SSACO-based approach. excellent optimizer since seeks serve guide point reference

Language: Английский

---

A modified binary version of aphid–ant mutualism for feature selection: a COVID-19 case study

Journal of Computational Design and Engineering, Journal Year: 2023, Volume and Issue: 10(2), P. 549 - 577

Published: Jan. 28, 2023

Abstract The speedy development of intelligent technologies and gadgets has led to a drastic increment dimensions within the datasets in recent years. Dimension reduction algorithms, such as feature selection methods, are crucial resolving this obstacle. Currently, metaheuristic algorithms have been extensively used tasks due their acceptable computational cost performance. In article, binary-modified version aphid–ant mutualism (AAM) called binary (BAAM) is introduced solve problems. Like AAM, BAAM, intensification diversification mechanisms modeled via intercommunication aphids with other colonies’ members, including ants. However, unlike number members can change each iteration based on attraction power leaders. Moreover, second- third-best individuals take place ringleader lead pioneer colony. Also, maintain population diversity, prevent premature convergence, facilitate information sharing between colonies ants, random cross-over operator utilized BAAM. proposed BAAM compared five using several evaluation metrics. Twelve medical nine non-medical benchmark different numbers features, instances, classes from University California, Irvine Arizona State repositories considered for all experiments. coronavirus disease (COVID-19) dataset validate effectiveness real-world applications. Based acquired outcomes, outperformed comparative methods terms classification accuracy various classifiers, K nearest neighbor, kernel-based extreme learning machine, multi-class support vector choosing most informative best mean fitness values convergence speed cases. As an instance, COVID-19 dataset, achieved 96.53% average selected subset.

Language: Английский

---

Differential evolution algorithm with improved crossover operation for combined heat and power economic dynamic dispatch problem with wind power

Journal of Computational Design and Engineering, Journal Year: 2023, Volume and Issue: 10(4), P. 1821 - 1837

Published: July 4, 2023

Abstract This paper proposes a differential evolution algorithm with improved crossover operation (ICRDE) to deal combined heat and power dynamic economic dispatch (CHPDED) problems wind power. First, the is used maintain population diversity by using original individuals, first mutated second individuals. Second, scaling factor weighted are incorporated into mutation improve convergence efficiency of algorithm. Third, adaptive control parameters introduced balance local exploitation global exploration. Moreover, after being updated ICRDE at each generation, solutions will be further amended constraint handling method, which improves chance acquiring feasible solutions. Experimental results demonstrate that has strong optimization ability surpasses compared algorithms for CEC2017 benchmark functions, problems, CHPDED problem without

Language: Английский

---

Slime mould algorithm with horizontal crossover and adaptive evolutionary strategy: performance design for engineering problems

Journal of Computational Design and Engineering, Journal Year: 2024, Volume and Issue: 11(4), P. 83 - 108

Published: June 19, 2024

Abstract In optimization, metaheuristic algorithms have received extensive attention and research due to their excellent performance. The slime mould algorithm (SMA) is a newly proposed algorithm. It has the characteristics of fewer parameters strong optimization ability. However, with increasing difficulty problems, SMA some shortcomings in complex problems. For example, main concerns are low convergence accuracy prematurely falling into local optimal solutions. To overcome these this paper developed variant called CCSMA. an improved based on horizontal crossover (HC) covariance matrix adaptive evolutionary strategy (CMAES). First, HC can enhance exploitation by crossing information between different individuals promote communication within population. Finally, CMAES facilitates exploration reach balanced state dynamically adjusting size search range. This benefits allowing it go beyond space explore other solutions better quality. verify superiority algorithm, we select new original as competitors. CCSMA compared competitors 40 benchmark functions IEEE CEC2017 CEC2020. results demonstrate that our work outperforms terms jumping out space. addition, applied tackle three typical engineering These problems include multiple disk clutch brake design, pressure vessel speed reducer design. showed achieved lowest cost. also proves effective tool for solving realistic

Language: Английский

---

An advanced RIME Optimizer with Random Reselection and Powell Mechanism for Engineering Design

Journal of Computational Design and Engineering, Journal Year: 2024, Volume and Issue: 11(6), P. 139 - 179

Published: Oct. 18, 2024

Abstract RIME is a recently introduced optimization algorithm that draws inspiration from natural phenomena. However, has certain limitations. For example, it prone to falling into Local Optima, thus failing find the Global and problem of slow convergence. To solve these problems, this paper introduces an improved (PCRIME), which combines random reselection strategy Powell mechanism. The enhances population diversity helps escape while mechanism improve convergence accuracy optimal solution. verify superior performance PCRIME, we conducted series experiments at CEC 2017 2022, including qualitative analysis, ablation studies, parameter sensitivity comparison with various advanced algorithms. We used Wilcoxon signed-rank test Friedman confirm advantage PCRIME over its peers. experimental data show ability robustness. Finally, applies five real engineering problems proposes feasible solutions comprehensive index definitions for prove stability proposed algorithm. results can not only effectively practical but also excellent stability, making

Language: Английский

---

Optimizing Microseismic Monitoring: A Fusion of Gaussian-Cauchy and Adaptive Weight Strategies

Journal of Computational Design and Engineering, Journal Year: 2024, Volume and Issue: 11(5), P. 1 - 28

Published: Aug. 8, 2024

Abstract In mining mineral resources, it is vital to monitor the stability of rock body in real time, reasonably regulate area ground pressure concentration, and guarantee safety personnel equipment. The microseismic signals generated by monitoring rupture can effectively predict disaster, but current technology not ideal. order address issue deep wells, this research suggests a machine learning-based model for predicting phenomena. First, work presents random spare, double adaptive weight, Gaussian–Cauchy fusion strategies as additions multi-verse optimizer (MVO) an enhanced MVO algorithm (RDGMVO). Subsequently, RDGMVO-Fuzzy K-Nearest Neighbours (RDGMVO-FKNN) prediction presented combining with FKNN classifier. experimental section compares 12 traditional recently algorithms RDGMVO, demonstrating latter’s excellent benchmark optimization performance remarkable improvement effect. Next, comparison experiment, classical classifier dataset feature selection experiment confirm precision RDGMVO-FKNN problem. According results, has accuracy above 89%, indicating that reliable accurate method classifying occurrences. Code been available at https://github.com/GuaipiXiao/RDGMVO.

Language: Английский

---

An Enhanced Slime Mould Algorithm with Triple Strategy for Engineering Design Optimization

Journal of Computational Design and Engineering, Journal Year: 2024, Volume and Issue: 11(6), P. 36 - 74

Published: Oct. 16, 2024

Abstract This paper introduces an enhanced slime mould algorithm (EESMA) designed to address critical challenges in engineering design optimization. The EESMA integrates three novel strategies: the Laplace logistic sine map technique, adaptive t-distribution elite mutation mechanism, and ranking-based dynamic learning strategy. These enhancements collectively improve algorithm’s search efficiency, mitigate convergence local optima, bolster robustness complex optimization tasks. proposed demonstrates significant advantages over many conventional algorithms performs on par with, or even surpasses, several advanced benchmark tests. Its superior performance is validated through extensive evaluations diverse test sets, including IEEE CEC2014, CEC2020, CEC2022, its successful application six distinct problems. Notably, excels solving economic load dispatch problems, highlighting capability tackle challenging scenarios. results affirm that a competitive effective tool for addressing issues, showcasing potential widespread beyond.

Language: Английский

---