检索结果-内蒙古大学图书馆

whale optimisation algorithm for high-dimensional small-instance feature selection

INTERNATIONAL JOURNAL OF PARALLEL EMERGENT AND DISTRIBUTED SYSTEMS 2021年第2期36卷 80-96页

作者： Mafarja, Majdi Jaber, Iyad Ahmed, Sobhi Thaher, Thaer Birzeit Univ Dept Comp Sci Birzeit Palestine An Najah Natl Univ Coll Engn & Informat Technol Nablus Palestine

In this paper, eight variants of the whale optimisation algorithm (WOA), that are based on eight different transfer functions, are introduced and used as search strategies in a wrapper feature selection model. Feature selection is a challenging task in machine learning process. It aims to minimise the size of a dataset by removing redundant and/or irrelevant features, with no information loss, to improve the efficiency of the learning algorithms. The used transfer functions belong to two different families;S-shaped and V-shaped. The proposed approaches have been tested on nine different high-dimensional medical datasets, with a low number of samples and multiple classes. The results revealed a superior performance for the V-shaped based approaches over the the S-shaped approaches. Moreover, the results of the V-shaped approach is compared with well-known feature selection approaches, and the superiority of the proposed approach is proven.

关键词： whale optimisation algorithm WOA transfer functions high-dimensional data classification feature selection

来源：评论

学校读者我要写书评

暂无评论

Parameters estimation of single- and multiple-diode photovoltaic model using whale optimisation algorithm

Parameters estimation of single- and multiple-diode photovol...

引用

6th IET Renewable Power Generation (RPG) Conference

作者： Elazab, Omnia S. Hasanien, Hany M. Elgendy, Mohamed A. Abdeen, Amr M. Ain Shams Univ Elect Power & Machines Dept Fac Engn Cairo 11517 Egypt Newcastle Univ Sch Elect & Elect Engn Newcastle England

The high level of penetration of photovoltaic (PV) systems into electric power grids increases rapidly due to many merits of such promising technology. In the simulation investigation of PV systems, an accurate PV model is vital, where it plays an important role through the dynamic analysis of these systems. The mathematical model of the PV module is a nonlinear I-V characteristic including many unknown parameters as data provided by the PV manufacturers' are inadequate. This paper introduces a novel application of the whale optimisation algorithm (WOA) for estimating the parameters of the single, double, and three diode PV models of a PV module. The WOA-based PV models are validated by the simulation results, which are carried out under various environmental conditions using MATLAB program. The effectiveness of the WOA-based PV models is checked by comparing their results with that obtained using other optimisation methods. To obtain a realistic study, these simulation outcomes are compared with the experimental outcomes of a Kyocera KC200GT PV module. The WOA-based PV model is efficiently evaluated by comparing the absolute current error of this model with that obtained using other PV models. Using this meta-heuristic algorithm application, an accurate PV model can be obtained.

关键词： optimisation photovoltaic power systems power grids power system parameter estimation power system simulation multiple-diode photovoltaic model whale optimisation algorithm photovoltaic systems PV systems PV manufacturers WOA-based PV model Kyocera KC200GT PV module precise PV model nonlinear I-V characteristic parameters estimation

来源：评论

学校读者我要写书评

暂无评论

Prediction of Water-Richness Zoning of Weathered Bedrock Based on whale optimisation algorithm and Random Forest

引用

WATER 2024年第24期16卷

作者： Hou, Enke Li, Qianlong Yang, Lei Bi, Meng Li, Yan He, Yangyang Xian Univ Sci & Technol Coll Geol & Environm Xian 710054 Peoples R China Hongliulin Min Coal Ltd Shaanxi Coal Grp Shenmu 719300 Peoples R China

To effectively predict the water richness of weathered bedrock aquifers, the West First Plate area of the Hongliulin coal mine was taken as the study area, and 42 sets of pumping test borehole data from the weathered bedrock in the study area were used as training and testing samples. A total of five indicators related to the water richness of weathered bedrock, namely, the aquifer thickness, sand-base ratio, core take rate, degree of weathering, and lithological structure index, were selected. A prediction model for the water richness of weathered bedrock aquifers (WOA-RF) was subsequently proposed by combining the whale optimisation algorithm (WOA) and random forest (RF). This model can predict the water-richness level of weathered bedrock in an area with no pumping test data. The geological information from 98 sets of exploration boreholes in the study area was comprehensively used to achieve water-richness zoning of the weathered bedrock. The results indicated that the WOA is effective in optimising parameters and improving model performance. The accuracies of the optimal WOA-RF model in the training set and the test set were 93.1% and 92.3%, respectively. Compared with those of the single RF model, the accuracy, recall, and F1 value of the optimal WOA-RF model were increased by 11.3%, 18.2%, and 11%, respectively, and the differences before and after optimisation were obvious. A comparison and analysis of the predictive performance of each model revealed that the overall performance of the WOA-RF model was better than that of the other models. The weathered bedrock in the study area as a whole is weakly to moderately rich in water, and the predicted results are in good agreement with reality, which can provide a reference for future safe production in the West First Plate area.

关键词： weathered bedrock whale optimisation algorithm random forest water abundance evaluation prevention and control of water in coal mines

来源：评论

学校读者我要写书评

暂无评论

A novel whale optimisation algorithm with filtering disturbance and nonlinear step

引用

INTERNATIONAL JOURNAL OF BIO-INSPIRED COMPUTATION 2022年第2期20卷 71-81页

作者： Luo, Jinkun He, Fazhi Li, Haoran Zeng, Xian-Tao Liang, Yaqian Wuhan Univ Sch Comp Sci Wuhan 430072 Peoples R China Wuhan Univ Ctr Evidence Based & Translat Med Zhongnan Hosp Wuhan 430071 Peoples R China

As a recent addition of population-based metaheuristic algorithms, whale optimisation algorithm (WOA) has attracted a lot of attention recently. However, WOA still has room for improvement in the accuracy and reliability of solution. In this study, a novel WOA with filtering disturbance and nonlinear step (FDNS-WOA) is proposed. Firstly, to enhance the population diversity and the global search ability, we design a weighted Cauchy mutation equation to perturb solution space. Secondly, the excessive disturbance may cause the imbalance between exploration and exploitation, and the quality of solutions will be decreased. Thus, before the disturbance, we propose a filtering mechanism to dynamically select different individuals for disturbance at different evolutionary stages. Thirdly, a weighted local walk mechanism is designed to improve the local exploitation capability. Different from original linear step with large fluctuation, we propose a nonlinear step to reduce blind spots in the local exploitation process. Finally, the proposed FDNS-WOA is tested on benchmark functions and applied in a real world problem. The experimental results show that the proposed FDNS-WOA not only outperforms other recent metaheuristic algorithms in term of accuracy and reliability for most benchmark functions, but also achieves satisfactory results in real world problem.

关键词： whale optimisation algorithm WOA Cauchy mutation economic load dispatch ELD metaheuristic algorithm population-based algorithm filtering disturbance nonlinear step

来源：评论

学校读者我要写书评

暂无评论

A data transmission protocol for WSN based on multi-strategy improved whale optimisation algorithm

引用

INTERNATIONAL JOURNAL OF MODELLING IDENTIFICATION AND CONTROL 2023年第4期43卷 302-311页

作者： Chen, Xi Qin, Tao Wei, Wei Fan, Yuancheng Luo, Xuemei Yang, Jing Guizhou Univ Elect Engn Coll Guiyang 550025 Peoples R China Guizhou Elect Power Design & Res Inst Co Ltd China Power Construct Grp Guiyang 550025 Peoples R China Guizhou Engn Co Ltd China Power Construct Grp Guiyang 550025 Peoples R China

This paper is a study of routing protocols for wireless sensor network (WSN) based on the whale optimisation algorithm (WOA), which has problems such as slow convergence, low convergence accuracy and the tendency to fall into local optimality. Firstly, a multi-strategy WOA named CNGS-WOA is proposed, which includes chaotic mapping, nonlinear processing of convergence factor and golden sine partition. The simulation results show that the CNGS-WOA has obvious advantages in terms of search accuracy and stability. Secondly, a data transmission protocol named CNGS-WOA-RP is proposed based on the improved WOA. By comparing four aspects of network clustering effect, network life cycle, network residual energy and network energy consumption balance, it's shown that the data transmission protocol CNGS-WOA-RP can effectively reduce and balance network energy consumption, and has greater advantages in extending network lifetime.

关键词： data transmission whale optimisation algorithm WOA minimum energy consumption optimal clustering energy balance

来源：评论

学校读者我要写书评

暂无评论

optimisation driven-based secure routing in MANET using atom whale optimisation algorithm

引用

INTERNATIONAL JOURNAL OF COMMUNICATION NETWORKS AND DISTRIBUTED SYSTEMS 2021年第1期27卷 77-99页

作者： Halhalli, Suresh R. Sugave, Shounak Rushikesh Jagdale, B. N. MS Bidve Engn Coll Elect Engn Latur India Dr Vishwanath Karad MIT World Peace Univ Sch CET Pune Maharashtra India

Mobile ad hoc networks (MANETs) routing is a very challenging task because of the dynamic nature of the network. The linking of provisional communication assures based on the infrastructure of MANET, however, there is no centralised monitoring process for making the routing in MANETs in terms of trust and security. Therefore, the stability routing is not considered, which may break easily in dynamic MANETs. Thus, this paper introduces a trust-based secure routing protocol using the proposed atom whale optimisation algorithm (AWOA), which is the trust-aware routing protocol. The developed atom whale optimisation is utilised to select the optimal route with respect to the trust factors, like average encounter rate (AER), and successful cooperation frequency (SCF), integrity factor, and the forwarding rate. Moreover, secure routing is performed between the nodes using the proposed AWOA. The AWOA is the integration of atom search optimisation (ASO), and whale optimisation algorithm (WOA) that inherits the faster global convergence. The fitness function is newly modelled considering mobility, and trust factors. The proposed AWOA outperformed other methods with a minimal end-to-end delay of 0.0083 sec, maximal packet delivery ratio (PDR) of 97.73%, and the maximal throughput of 85.05% respectively.

关键词： mobile ad hoc networks MANETs mobility average encounter rate AER whale optimisation algorithm WOA atom search optimisation ASO

来源：评论

学校读者我要写书评

暂无评论

An improved whale optimisation algorithm for distributed assembly flow shop with crane transportation

引用

INTERNATIONAL JOURNAL OF AUTOMATION AND CONTROL 2021年第6期15卷 710-743页

作者： Li, Qing-Hua Li, Jun-Qing Zhang, Qing-Ke Duan, Peng Meng, Tao Shandong Normal Univ Sch Informat & Engn Jinan 250014 Peoples R China Liaocheng Univ Sch Comp Sci Liaocheng 252059 Shandong Peoples R China Univ Rhode Isl Dept Elect Comp & Biomed Engn Kingston RI 02881 USA Liaocheng Univ Sch Math Liaocheng 252059 Shandong Peoples R China

In this study, we investigate a classical distributed assembly flow shop scheduling problem with crane transportation. The objectives are to minimise the weighted value of the makespan and the energy consumptions. An improved whale optimisation algorithm (IWOA) which is embedded with a simulated annealing (SA) algorithm is proposed to solve the considered problem. First, a clustering method is applied to divide the solutions to improve the performance of the algorithm. Then, a right shift heuristic is developed to reduce the number of machine switches, therefore decreasing the energy consumption. In addition, two novel crossover operators, namely, factory crossover and solution crossover, are designed to increase the overall performance of the proposed algorithm. Furthermore, a SA-based global search heuristic is embedded in the algorithm to enhance its exploration abilities. Finally, several real-world instances were generated to test the performance of the proposed algorithm. The experimental results show that this algorithm performs better than other comparable algorithms.

关键词： distributed assembly flow shop scheduling crane energy consumptions whale optimisation algorithm

来源：评论

学校读者我要写书评

暂无评论

Finite-time control for MJSs under protocol-based fading network and input saturation: a WOA-assisted method

引用

INTERNATIONAL JOURNAL OF SYSTEMS SCIENCE 2025年

作者： Wang, Ruihao Yu, Tao He, Shuping Anhui Univ Engn Res Ctr Autonomous Unmanned Syst Technol Sch Artificial Intelligence Minist Educ Hefei Peoples R China Anhui Univ Sch Elect Engn & Automat Yunnan Key Lab Unmanned Autonomous Syst Hefei Peoples R China Anhui Univ Sch Elect Engn & Automat Informat Mat & Intelligent Sensing Lab Anhui Prov Hefei Peoples R China

This paper tackles finite-time control of Markov jump systems (MJSs) under stochastic communication protocol (SCP) based fading network and actuator saturation. Specifically, only one channel of the fading signal can be transmitted at each transmission moment. In addition, the actuator input is typically limited due to actual physical conditions. The SCP channel selection and fading coefficient changes are modelled as MJSs. A dynamic output feedback controller ensures the system state remains within a threshold for a finite time. Using the Lyapunov method, sufficient conditions for closed-loop stability and $ H_{\infty } $ H infinity performance are derived. However, the developed stability and controller design conditions include nonlinear and non-convex constraints. To address nonlinear constraints and achieve optimal finite-time $ H_\infty $ H infinity performance, an algorithm that integrates the whale optimisation algorithm (WOA) with linear matrix inequality method is introduced, including an initial value selection method for WOA. Finally, a numerical example and an example of a DC chopper circuit system are presented to demonstrate the effectiveness of the proposed control method.

关键词： Markov jump system fading channel input saturation stochastic communication protocol whale optimisation algorithm

来源：评论

学校读者我要写书评

暂无评论

Deep learning:an study on financial crisis forewarning in small and medium-sized listed enterprises

引用

Journal of Control and Decision 2025年第1期12卷 159-166页

作者： Shaonan Pang Lixia Du Department of Accounting Hebei Vocational University of Technology and EngineeringXingtaiPeople’s Republic of China Department of Economic Management Xinzhou Normal UniversityXinzhouPeople’s Republic of China

Early warning of financial crisis will greatly promote the stable development of small and medium-sized listed enterprises(listed SMEs).In this article,13 warning indicators were selected for financial crisis prediction from five aspects:profit level,debt service level,business level,cash level,and development ***,the parameters of the long short-term memory(LSTM)neural network model were optimised by the whale optimisation algorithm(WOA),resulting in the WOA-LSTM *** WOA-LSTM model achieved an accuracy of 0.975 in predicting financial crises for listed *** performance of the WOA-LSTM model was significantly enhanced when using the filtered 13 indicators as inputs,compared to using the original 24 *** findings prove the dependability of the WOA-LSTM model in warning financial crises of listed SMEs and the feasibility of its application in practice.

关键词： Deep learning small and medium-sized listed enterprise financial crisis whale optimisation algorithm

来源：评论

学校读者我要写书评

暂无评论

Prediction of the fracture energy properties of concrete using COOA-RBF neural network

引用

INTERNATIONAL JOURNAL OF CRITICAL INFRASTRUCTURES 2025年第2期21卷 187-208页

作者： Zhang, Yongcun Bai, Zhe Henan Univ Urban Construct Sch Civil & Transportat Engn Pingdingshan 467036 Henan Peoples R China Chongqing Vocat Inst Engn Sch Civil Engn Chongqing 402260 Peoples R China

Evaluating the energy requirements for crack propagation in concrete structures has been a subject of considerable interest since applying fracture mechanics principles to concrete. Concrete fracture energy is important for safe structural design and failure behaviour modelling because it is quasi-brittle. The complex nonlinear behaviour of concrete during fracture has led to ongoing debates regarding fracture energy prediction using existing estimation techniques. Using the previous dataset, prediction approaches were developed to measure the preliminary (Gf) and total (GF) fracture energies of concrete utilising mechanical properties and mixed design elements. Two hundred sixty-four experimental recordings were gathered from an earlier study to construct and analyse ideas. This study combines the radial basis function neural network (RBFNN) with the Coot optimisation algorithm (COOA) and whale optimisation algorithm (WOA). The computation and analysis of Gf and GF used five performance measures, which show that both optimised COOA-RBFNN and WOA-RBFNN evaluations could execute superbly during the estimation mechanism. Therefore, even though the WOA-RBFNN approach has unique characteristics for simulating, the COOA-RBFNN analysis seems quite dependable for calculating. Gf and GF given the rationale and model processing simplicity.

关键词： concrete fracture energy neural network estimation radial basis function coot optimisation algorithm whale optimisation algorithm WOA

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：