检索结果-内蒙古大学图书馆

whale optimization algorithm coupled with machine learning models for quantitative prediction of soil Ni content

MICROCHEMICAL JOURNAL 2025年 209卷

作者： Fu, Chengbiao Feng, Xiqin Tian, Anhong Kunming Univ Sci & Technol Fac Informat Engn & Automat Kunming 650500 Peoples R China Kunming Univ Sci & Technol Fac Land Resource Engn Kunming 650093 Peoples R China

Under the background of environmental protection and sustainable agricultural development, it is crucial to monitor soil heavy metals, especially potentially harmful substances such as nickel. Spectroscopy technology is characterized by non-destructiveness and high efficiency, it can rapidly monitor the nickel content in the soil and provide guidance for safe agricultural production, thus promoting the green development of agriculture. There are few reports on the quantitative prediction of soil heavy metal nickel (Ni) content based on visible and nearinfrared (Vis-NIR) spectroscopy. In this study, 60 soil samples were collected from the Mojiang Hani Autonomous County, Yunnan Province, to explore a high-precision quantitative prediction model. A feature band extraction method based on whale optimization algorithm (WOA) was proposed and analyzed in comparison with the traditional feature selection methods based on genetic algorithm (GA) and particle swarm optimization (PSO). Three machine learning models (support vector regression (SVR), random forest (RF), and back propagation (BP)) were employed to study the prediction accuracy of the quantitative prediction model, and the performance of the constructed model was evaluated based on the coefficient of determination (R2), the root mean square error (RMSE), the residual prediction bias (RPD), and the performance ratio of the quartile distance (RPIQ). The results of the study indicated that: The swarm intelligent optimization algorithm based on WOA can extract fewer feature bands. The soil feature bands extracted by WOA are reduced by 15.67 % and 14.93 % compared to the GA and PSO algorithms, respectively. For quantitative prediction of soil Ni content, machine learning models based on BP had the best accuracy, GA-BP, PSO-BP and WAO-BP performance for quantitative prediction of soil Ni content was very good, extremely good, and extremely good with RPD values of 2.523, 2.644, and 3.098, respectively. Compared to the GA-

关键词： whale optimization algorithm Machine learning Soil heavy metals Vis-NIR spectroscopy Feature variable selection

来源：评论

学校读者我要写书评

暂无评论

whale optimization algorithm Using Pinhole Imaging Reverse Learning and Golden Sine Strategy

引用

INTERNATIONAL JOURNAL OF COGNITIVE INFORMATICS AND NATURAL INTELLIGENCE 2024年第1期18卷

作者： Yue, Xuezhi Jiang, Linfeng Zeng, Yuan Cheng, Yating Liao, Yihang Jiangxi Univ Sci & Technol Ganzhou Peoples R China Guangdong Commun Polytech Guangzhou Peoples R China

While handling problems of certain complex scene optimization, the whale optimization algorithm (WOA) algorithm may be affected by precocious convergence or local optimal solutions, resulting in the accuracy of low convergence and stagnation of dimensional population. To address these limitations, this research presents a whale optimization algorithm, which is established on pinhole imaging reverse learning and the golden sine strategy (LWOAG). Firstly, LWOAG employs pinhole imaging reverse learning to determine the reverse solution for optimal individual in the population, thereby improving the population's quality and algorithm convergence ability. Secondly, LWOAG utilizes the golden sine operator to perform greedy selection after the whale completes the search update, thus extending the search range and increasing the algorithm's global search capacity. Finally, after conducting comprehensive tests on 12 benchmark functions, LWOAG outperforms other enhanced whale optimization algorithms and intelligent algorithms in terms of accuracy and stability.

关键词： Global Search Golden Sine Operator Meta-Heuristic algorithm Pinhole Imaging Reverse Learning whale optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

whale optimization algorithm based MPPT control of a fuel cell system

引用

INTERNATIONAL JOURNAL OF HYDROGEN ENERGY 2023年第60期48卷 23230-23241页

作者： Percin, Hasan Bektas Caliskan, Abuzer Firat Univ TR-23119 Elazig Turkiye Firat Univ Fac Engn Dept Elect & Elect Engn TR-23119 Elazig Turkiye

Renewable energy sources have provided a great contribution to global energy demand;However, their intermittent characteristics can cause sustainability and efficiency problems. To handle these, alternative systems are utilized. Among these, proton exchange membrane fuel cells (PEMFCs) stand out with their longer lifecycle, efficient, and costeffective features. However, their performance depends on operating conditions such as temperature, gas pressure, and membrane water content. These nonlinear features require instant and proper control for maximizing efficiency and longer working life. In this study, a whale optimization algorithm (WOA) based maximum power point tracking (MPPT) controller is utilized for a PEMFC system. To validate the proposed controller, the PEMFC system has been analyzed under changing conditions in the MATLAB/Simulink environment. The proposed method has been compared with the other MPPT methods. The results indicate that the proposed controller can provide accurate and fast MPPT performance, less power fluctuations, and higher production efficiency.& COPY;2023 Hydrogen Energy Publications LLC. Published by Elsevier Ltd. All rights reserved.

关键词： whale optimization algorithm (WOA) Fuel cell PEMFC MPPT MATLAB Simulink

来源：评论

学校读者我要写书评

暂无评论

whale optimization algorithm (WOA) for Task Scheduling Problem in Multi-processors Environment

Whale Optimization Algorithm (WOA) for Task Scheduling Probl...

引用

IEEE Symposium on Industrial Electronics and Applications (ISIEA)

作者： Suliman, Saiful Izwan Khalish, Mohammad Nur Yusof, Yuslinda Wati Mohamad Rahman, Farah Yasmin Abdul Univ Teknol MARA UiTM Coll Engn Sch Elect Engn Shah Alam 40450 Selangor Malaysia

ISBN: (纸本)9798350386875;9798350386868

Use of multiprocessors applications to solve complex problems in computer's system contributes to the increase in performance and speed of today's computer. In multiprocessors environment, it is very important to have a great strategy or method on scheduling the processors that are utilized to handle a specific task in the computer system. As each scheduling problem involves problem-specific variables, multiprocessors need different and appropriate algorithm for their problems. This study introduces the whale optimization algorithm (WOA) for task scheduling. Comparisons with other existing methods were also conducted to highlight the efficiency of the proposed WOA in performing task scheduling.

关键词： Multiprocessors task scheduling whale optimization algorithm algorithm

来源：评论

学校读者我要写书评

暂无评论

whale optimization algorithm Approach for Performance optimization of Novel Xmas Tree-Shaped FinFET

引用

SILICON 2022年第7期14卷 3371-3382页

作者： Kaur, Gurpurneet Gill, Sandeep Singh Rattan, Munish IK Gujral Punjab Tech Univ Jalandhar 144603 Punjab India Guru Nanak Dev Engn Coll Ludhiana 141006 Punjab India Natl Inst Tech Teachers Training & Res Chandigarh 160019 Punjab India

Today, Fin shaped Field Effect Transistors (FinFETs) are the framework of the sub-nanometer technology node. The leading semiconductor industry deploys it in low-power (LP) and high-performance (HP) applications due to its better electrostatic control and exceptional scalability. In this paper, a novel optimized and miniaturized Xmas tree-shaped FinFET was designed that provides reduced short channel effects and better analog parameters as compared to the planar Metal Oxide Semiconductor Field Effect transistor. This proposed structure was devised with the Genetic algorithm (GA) and whale optimization algorithm (WOA) along with the Artificial Neural Network (ANN). The dataset used in ANN training was created through designing and simulating the Xmas tree shaped FinFET structure by varying its Fin-width (W-Fin) and Fin-height (H-Fin). Through ANN-GA and ANN-WOA optimization, the optimal value of W-Fin and H-Fin was calculated at the minimum Subthreshold Swing (SS) and off-current (I-OFF) along with maximum on-current (I-ON). The proposed Xmas tree shaped FinFET structure was designed and simulated with the optimal value of W-Fin and H-Fin that resulted in superior performance parameters. SS, I-OFF, and I-ON values were 63.3 mV/dec, 77.3pA, and 0.51 mu A respectively;suggesting that the optimized structure has more control over undesired Short Channel Effects. The deviation of less than 5% between optimized and simulated performance parameters substantiates the effectiveness of the optimization process. It has been estimated that the novel device consumes 40% lesser area than the rectzoidal structures designed in literature. A notable improvement has been observed in the area consumption due to the usage of multiple substrates.

关键词： Artificial neural network whale optimization algorithm FinFET Subthreshold swing Short channel effects Genetic algorithm Novel

来源：评论

学校读者我要写书评

暂无评论

whale optimization algorithm based on dynamic pinhole imaging and adaptive strategy

引用

JOURNAL OF SUPERCOMPUTING 2022年第5期78卷 6090-6120页

作者： Li, Maodong Xu, Guanghui Fu, Bo Zhao, Xilin Hubei Univ Technol Hubei Key Lab High Efficiency Utilizat Solar Ener Sch Elect & Elect Engn Wuhan 430068 Peoples R China

To solve the problems of premature convergence and easily falling into local optimum, a whale optimization algorithm based on dynamic pinhole imaging and adaptive strategy is proposed in this paper. In the exploitation phase, the dynamic pinhole imaging strategy allows the whale population to approach the optimal solution faster, thereby accelerating the convergence speed of the algorithm. In the exploration phase, adaptive inertial weights based on dynamic boundaries and dimensions can enrich the diversity of the population and balance the algorithm's exploitation and exploration capabilities. The local mutation mechanism can adjust the search range of the algorithm dynamically. The improved algorithm has been extensively tested in 20 well-known benchmark functions and four complex constrained engineering optimization problems, and compared with the ones of other improved algorithms presented in literatures. The test results show that the improved algorithm has faster convergence speed and higher convergence accuracy and can effectively jump out of the local optimum.

关键词： whale optimization algorithm Pinhole imaging Dynamic boundary Adaptive inertial weight Local mutation

来源：评论

学校读者我要写书评

暂无评论

Dynamic multi-swarm whale optimization algorithm based on elite tuning for high-dimensional feature selection classification problems

引用

APPLIED SOFT COMPUTING 2025年 169卷

作者： Miao, Fahui Wu, Yong Yan, Guanjie Si, Xiaomeng Shanghai Maritime Univ Coll Informat Engn Shanghai 201306 Peoples R China Univ Macau Zhuhai UM Sci & Technol Res Inst Zhuhai 519000 Peoples R China Shanghai Urban Construct Vocat Coll Dept Basic Educ Shanghai 201415 Peoples R China Shanghai Polytech Univ Inst Artificial Intelligence Sch Comp & Informat Engn Shanghai 201209 Peoples R China

Feature selection algorithms are crucial technologies for reducing the dimensionality of high-dimensional data. However, the exponential expansion of the decision space due to high-dimensional data makes most feature selection algorithms highly susceptible to local optima. To increase the quality of feature selection, we propose a dynamic multi-swarm whale optimization algorithm based on elite tuning (EMSWOA). First, we propose a dynamic multiple swarm construction mechanism based on the centroid distance metric, which enhances the exploitation and exploration abilities of the algorithm by improving the connectivity between sub-population topologies and preventing the algorithm from falling into precocious convergence. Secondly, to address the issue of invalid probability flips caused by random thresholds during feature space transformation, we design a novel elite tuning mechanism. This mechanism uses the high-quality information in the elite solution to assess and correct the probability of feature flipping;it effectively improves the algorithm's recognition of important features and reduces the interference of invalid probability flips in the optimization search. Finally, we validated the EMSWOA against six comparison algorithms on 19 datasets. The experimental results demonstrate that, compared with the most effective benchmark algorithms, the EMSWOA yields an average accuracy increase of 2.91 % and an average reduction in the number of features by a factor of 3.58.

关键词： whale optimization algorithm Feature selection Swarm intelligence Centroid distance metric Elite tuning strategy

来源：评论

学校读者我要写书评

暂无评论

Multi-Timescale Nested Hydropower Station optimization Scheduling Based on the Migrating Particle whale optimization algorithm

引用

ENERGIES 2025年第7期18卷 1780-1780页

作者： Zhang, Mi Zhou, Guosheng Liu, Bei Huang, Dajun Yu, Hao Mo, Li Huazhong Univ Sci & Technol Sch Civil & Hydraul Engn Hubei Key Lab Digital Valley Sci & Technol Wuhan 430074 Peoples R China Loushui Hydropower Co Ltd Hubei Energy Grp Enshi 445800 Peoples R China Changjiang Survey Planning Design & Res Co Ltd Wuhan 430010 Peoples R China

Exploring efficient and stable solution methods for hydropower generation optimization models is crucial for enhancing reservoir power generation efficiency and achieving the sustainable use of water resources. However, existing studies predominantly focus on single-timescale scheduling models, failing to fully exploit multi-timescale runoff information. Additionally, commonly used solution algorithms often face challenges such as premature convergence, susceptibility to local optima, and dimensionality issues. To address these limitations, this paper proposes the Migrating Particle whale optimization algorithm (MPWOA), which initializes the population using chaotic mapping, incorporates a particle swarm mechanism to enhance exploitation during the spiral predation phase, and integrates the black-winged kite migration mechanism to improve stochastic search performance. Validation on classical test functions and the Jiangpinghe River of the multi-timescale nested optimal scheduling model demonstrates that MPWOA exhibits faster convergence and stronger optimization capabilities and significantly improves power generation. The multi-timescale nested scheduling scheme derived from this algorithm effectively utilizes runoff information, offering a practical and highly efficient solution for hydropower scheduling.

关键词： optimal scheduling of hydropower plants generation maximization criterion multiple timescale nesting whale optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

A novel multi-strategy combined whale optimization algorithm for cascade reservoir operation of complex engineering optimization

引用

APPLIED SOFT COMPUTING 2025年 173卷

作者： Hou, Ziqi Peng, Huichun Li, Jiqing North China Elect Power Univ Dept Math & Phys Beijing 102206 Peoples R China North China Elect Power Univ Sch Water Resources & Hydropower Engn Beijing 102206 Peoples R China

Reservoir operation optimization is a complex nonlinear problem involving multiple variables and physical constraints, making it one of the most challenging optimal issues in water resources management. The whale optimization algorithm (WOA) features a straightforward mechanism and exceptional optimization performance. However, with escalating problem complexity, problems such as premature convergence and inadequate global exploration emerge. This study proposes a multi-strategy combined whale optimization algorithm (SCWOA) to address these problems. The approach retains the powerful exploitation mechanism of WOA while implementing the following improvements: introducing parallel multiplication and division operators to enhance global exploration capability, adopting the dual-strategy encirclement mechanism to enrich population diversity, and integrating dynamic spiral mechanism to improve solution accuracy coupling the adaptive escape mechanism to reduce the local stagnation times. Subsequently, numerical experiments are conducted to compare and analyze SCWOA with seven commonly used optimization algorithms across 53 benchmark functions. The analysis results indicate that SCWOA surpasses existing algorithms in global optimization accuracy, robustness, and exploration ability when handling most complex problems with varying dimensions and modes. Furthermore, a generation operation model of a practical hydropower system in China is developed under multiple constraints, such as ice prevention, flood control, and water supply. The operation results show that the schemes of SCWOA generate higher power generation than existing algorithms under different scenarios, effectively improving hydropower utilization rates. Therefore, a novel approach is provided for solving complex reservoir operation optimization problems.

关键词： whale optimization algorithm Cascade reservoir operation Random jump search Adaptive escape Operation optimization

来源：评论

学校读者我要写书评

暂无评论

Kolmogorov-Arnold networks guided whale optimization algorithm for feature selection in medical datasets

引用

JOURNAL OF BIG DATA 2025年第1期12卷

作者： Zheng, Boli Chen, Yi Wang, Chaofan Heidari, Ali Asghar Liu, Lei Chen, Huiling Liang, Guoxi Wenzhou Univ Inst Big Data & Informat Technol Wenzhou 325000 Peoples R China Univ Tehran Coll Engn Sch Surveying & Geospatial Engn Tehran *** Iran Sichuan Univ Coll Comp Sci Chengdu 610065 Sichuan Peoples R China Wenzhou Polytech Dept Artificial Intelligence Wenzhou 325035 Peoples R China

Feature selection (FS), dealing with pathological data with a high dimensionality and a small number of samples, has always been quite challenging. Among these, wrapper-based FS methods utilizing evolutionary algorithms have gained immense popularity due to their high accuracy. Additionally, utilizing surrogate models alongside wrapper-based FS methods can help save time by reducing the need for real model predictions. However, the use of surrogate models alongside evolutionary algorithms (EAs) presents two major challenges. Firstly, the training samples for the surrogate model all come from the iterative process of EAs. For surrogate models, the limited number of iterations in EAs results in a sparse amount of training samples. Additionally, FS emphasizes reducing feature quantity, which further contributes to the sparsity of the training data. In this paper, we propose a method for constructing training data based on the reliefF algorithm, which not only enables the acquisition of a large amount of training data but also helps in addressing the issue of feature sparsity. Furthermore, we propose the use of Kolmogorov-Arnold networks (KAN) as surrogate models to address the issue of sparse features. Finally, the whale optimization algorithm (WOA) was chosen as the evolutionary algorithm, as it has exhibited excellent performance in FS problems. Experimental results indicate that using KAN as a surrogate model to identify superior individuals generated by the WOA is feasible and has shown excellent performance in addressing medical FS problems.

关键词： Feature selection whale optimization algorithm Kolmogorov-Arnold networks Surrogate models Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：