Optimizing a Multi-Layer Perceptron Based on an Improved Gray Wolf Algorithm to Identify Plant Diseases DOI Creative Commons

Chunguang Bi,

Qiaoyun Tian,

He Chen

и другие.

Mathematics, Год журнала: 2023, Номер 11(15), С. 3312 - 3312

Опубликована: Июль 27, 2023

Metaheuristic optimization algorithms play a crucial role in problems. However, the traditional identification methods have following problems: (1) difficulties nonlinear data processing; (2) high error rates caused by local stagnation; and (3) low classification resulting from premature convergence. This paper proposed variant based on gray wolf algorithm (GWO) with chaotic disturbance, candidate migration, attacking mechanisms, naming it enhanced optimizer (EGWO), to solve problem of convergence stagnation. The performance EGWO was tested IEEE CEC 2014 benchmark functions, results were compared three GWO variants, five popular algorithms, six recent algorithms. In addition, optimized weights biases multi-layer perceptron (MLP) an EGWO-MLP disease model; model verified UCI dataset including Tic-Tac-Toe, Heart, XOR, Balloon datasets. experimental demonstrate that can effectively avoid problems provide quasi-optimal solution for problem.

Язык: Английский

Dung beetle optimization algorithm based on quantum computing and multi-strategy fusion for solving engineering problems DOI
Fang Zhu, Guoshuai Li, Hao Tang

и другие.

Expert Systems with Applications, Год журнала: 2023, Номер 236, С. 121219 - 121219

Опубликована: Авг. 22, 2023

Язык: Английский

Процитировано

113

SOH early prediction of lithium-ion batteries based on voltage interval selection and features fusion DOI
Simin Peng, Junchao Zhu, Tiezhou Wu

и другие.

Energy, Год журнала: 2024, Номер 308, С. 132993 - 132993

Опубликована: Авг. 26, 2024

Язык: Английский

Процитировано

29

Hybrid beluga whale optimization algorithm with multi-strategy for functions and engineering optimization problems DOI Creative Commons

Jiaxu Huang,

Haiqing Hu

Journal Of Big Data, Год журнала: 2024, Номер 11(1)

Опубликована: Янв. 2, 2024

Abstract Beluga Whale Optimization (BWO) is a new metaheuristic algorithm that simulates the social behaviors of beluga whales swimming, foraging, and whale falling. Compared with other optimization algorithms, BWO shows certain advantages in solving unimodal multimodal problems. However, convergence speed performance still have some deficiencies when complex multidimensional Therefore, this paper proposes hybrid method called HBWO combining Quasi-oppositional based learning (QOBL), adaptive spiral predation strategy, Nelder-Mead simplex search (NM). Firstly, initialization phase, QOBL strategy introduced. This reconstructs initial spatial position population by pairwise comparisons to obtain more prosperous higher quality population. Subsequently, an designed exploration exploitation phases. The first learns optimal individual positions dimensions through avoid loss local optimality. At same time, movement motivated cosine factor introduced maintain balance between exploitation. Finally, NM added. It corrects multiple scaling methods improve accurately efficiently. verified utilizing CEC2017 CEC2019 test functions. Meanwhile, superiority six engineering design examples. experimental results show has feasibility effectiveness practical problems than methods.

Язык: Английский

Процитировано

25

Catalyzing net-zero carbon strategies: Enhancing CO2 flux Prediction from underground coal fires using optimized machine learning models DOI

Hemeng Zhang,

Pengcheng Wang,

Mohammad Rahimi

и другие.

Journal of Cleaner Production, Год журнала: 2024, Номер 441, С. 141043 - 141043

Опубликована: Янв. 31, 2024

Язык: Английский

Процитировано

24

An improved gray wolf optimization algorithm solving to functional optimization and engineering design problems DOI Creative Commons
Yihui Qiu, Xiaoxiao Yang, Shuixuan Chen

и другие.

Scientific Reports, Год журнала: 2024, Номер 14(1)

Опубликована: Июнь 20, 2024

Abstract As a newly proposed optimization algorithm based on the social hierarchy and hunting behavior of gray wolves, grey wolf (GWO) has gradually become popular method for solving problems in various engineering fields. In order to further improve convergence speed, solution accuracy, local minima escaping ability traditional GWO algorithm, this work proposes multi-strategy fusion improved (IGWO) algorithm. First, initial population is optimized using lens imaging reverse learning laying foundation global search. Second, nonlinear control parameter strategy cosine variation coordinate exploration exploitation Finally, inspired by tunicate swarm (TSA) particle (PSO), tuning parameters, correction individual historical optimal positions are added position update equations speed up The assessed 23 benchmark test problems, 15 CEC2014 2 well-known constraint problems. results show that IGWO balanced E&P capability coping with as analyzed Wilcoxon rank sum Friedman tests, clear advantage over other state-of-the-art algorithms.

Язык: Английский

Процитировано

21

CFD-DPM data-driven GWO-SVR for fast prediction of nitrate decomposition in blast furnaces with nozzle arrangement optimization DOI
Wenchang Wu, Menghui Zhang, Zhao Liang

и другие.

Process Safety and Environmental Protection, Год журнала: 2023, Номер 176, С. 438 - 449

Опубликована: Июнь 15, 2023

Язык: Английский

Процитировано

25

Dung Beetle Optimization Algorithm Based on Improved Multi-Strategy Fusion DOI Open Access

Rencheng Fang,

Tao Zhou, Baohua Yu

и другие.

Electronics, Год журнала: 2025, Номер 14(1), С. 197 - 197

Опубликована: Янв. 5, 2025

The Dung Beetle Optimization Algorithm (DBO) is characterized by its great convergence accuracy and quick speed. However, like other swarm intelligent optimization algorithms, it also has the disadvantages of having an unbalanced ability to explore world use local resources, as well being prone settling into optimal search in latter stages optimization. In order address these issues, this research suggests a multi-strategy fusion dung beetle method (MSFDBO). To enhance quality first solution, refractive reverse learning technique expands algorithm space stage. algorithm’s increased adding adaptive curve control population size prevent from reaching optimum. improve balance exploitation global exploration, respectively, triangle wandering strategy subtractive averaging optimizer were later added Rolling Breeding Beetle. Individual beetles will congregate at current position, which near value, during last stage MSFDBO; however, value could not be value. Thus, variationally perturb solution (so that leaps out final MSFDBO) algorithmic performance (generally specifically, effect optimizing search), Gaussian–Cauchy hybrid variational perturbation factor introduced. Using CEC2017 benchmark function, MSFDBO’s verified comparing seven different intelligence algorithms. MSFDBO ranks terms average performance. can lower labor production expenses associated with welding beam reducer design after testing two engineering application challenges. When comes lowering manufacturing costs overall weight, outperforms methods.

Язык: Английский

Процитировано

1

GOHBA: Improved Honey Badger Algorithm for Global Optimization DOI Creative Commons
Yourui Huang, Sen Lu, Quanzeng Liu

и другие.

Biomimetics, Год журнала: 2025, Номер 10(2), С. 92 - 92

Опубликована: Фев. 6, 2025

Aiming at the problem that honey badger algorithm easily falls into local convergence, insufficient global search ability, and low convergence speed, this paper proposes a optimization (Global Optimization HBA) (GOHBA), which improves ability of population, with better to jump out optimum, faster stability. The introduction Tent chaotic mapping initialization enhances population diversity initializes quality HBA. Replacing density factor range in entire solution space avoids premature optimum. addition golden sine strategy capability HBA accelerates speed. Compared seven algorithms, GOHBA achieves optimal mean value on 14 23 tested functions. On two real-world engineering design problems, was optimal. three path planning had higher accuracy convergence. above experimental results show performance is indeed excellent.

Язык: Английский

Процитировано

1

Hybrid Optimization Algorithm for Solving Attack-Response Optimization and Engineering Design Problems DOI Creative Commons
Ahmad K. Al Hwaitat, Hussam N. Fakhouri, Jamal Zraqou

и другие.

Algorithms, Год журнала: 2025, Номер 18(3), С. 160 - 160

Опубликована: Март 10, 2025

This paper presents JADEDO, a hybrid optimization method that merges the dandelion optimizer’s (DO) dispersal-inspired stages with JADE’s (adaptive differential evolution) dynamic mutation and crossover operators. By integrating these complementary mechanisms, JADEDO effectively balances global exploration local exploitation for both unimodal multimodal search spaces. Extensive benchmarking against classical cutting-edge metaheuristics on IEEE CEC2022 functions—encompassing unimodal, multimodal, landscapes—demonstrates achieves highly competitive results in terms of solution accuracy, convergence speed, robustness. Statistical analysis using Wilcoxon sum-rank tests further underscores JADEDO’s consistent advantage over several established optimizers, reflecting its proficiency navigating complex, high-dimensional problems. To validate real-world applicability, was also evaluated three engineering design problems (pressure vessel, spring, speed reducer). Notably, it achieved top-tier or near-optimal designs constrained, high-stakes environments. Moreover, to demonstrate suitability security-oriented tasks, applied an attack-response scenario, efficiently identifying cost-effective, low-risk countermeasures under stringent time constraints. These collective findings highlight as robust, flexible, high-performing framework capable tackling benchmark-oriented practical challenges.

Язык: Английский

Процитировано

1

A novel interval decomposition correlation particle swarm optimization-extreme learning machine model for short-term and long-term water quality prediction DOI

Songhua Huan

Journal of Hydrology, Год журнала: 2023, Номер 625, С. 130034 - 130034

Опубликована: Авг. 11, 2023

Язык: Английский

Процитировано

23