检索结果-内蒙古大学图书馆

Variable-length deep convolutional neural networks by Internet Protocol Addresses whale optimization algorithm for random and complex image classification

引用

WAVES IN RANDOM AND COMPLEX MEDIA 2023年

作者： Khishe, Mohammad Imam Khomeini Marine Sci Univ Dept Elect Engn Nowshahr Iran

While Deep Convolutional Neural Network (DCNN) is one of the most reliable deep learning methods for image classification, choosing the optimal DCNN architecture for a particular application can be quite challenging. This study aims to examine the usage of the whale optimization algorithm (WOA) to discover the optimal structure for DCNNs automatically. Three advancements based on standard WOA are proposed to accomplish the objective. First, a novel Internet Protocol Address (IPA)-based coding approach is suggested, which makes it easier to encode DCNN layers utilizing whale vectors. The construction of variable-length DCNNs is then suggested using an Enfeebled layer to include certain whale vector dimensions. The learning procedure concludes by subdividing large datasets into smaller portions which are then arbitrarily assessed. In order to evaluate the proposed model's effectiveness, it is compared to the performance of twenty-three different classifiers, including the state-of-the-art algorithm, on nine standard image classification benchmark datasets. The experimental results indicate that the suggested technique outperforms other benchmarks in 81 of 95 assessments. This variable-length approach is the first of its kind, utilizing WOA to evolve the topologies of DCNNs automatically.

关键词： whale optimization algorithm image classification deep convolutional neural networks WOA

来源：评论

学校读者我要写书评

暂无评论

A Multi-Strategy whale optimization algorithm and Its Application

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2022年第0期108卷 104558-104558页

作者： Yang, Wenbiao Xia, Kewen Fan, Shurui Wang, Li Li, Tiejun Zhang, Jiangnan Feng, Yu Hebei Univ Technol Sch Elect & Informat Engn Tianjin 300401 Peoples R China Hebei Univ Technol Sch Mech Engn Tianjin 300401 Peoples R China

whale optimization algorithm (WOA) is a key tool for solving complex engineering optimization problems, aiming at adjusting important parameters to satisfy constraints and optimal objectives. WOA has a simple structure, few parameters, high search capability, and easy implementation. However, it suffers from the same problems as other metaheuristic algorithms of being prone to local optima and slow convergence, for which the Multi-Strategy whale optimization algorithm (MSWOA) is proposed. Four strategies are introduced in MSWOA. Firstly, a highly randomized chaotic logistic map is used to generate a high-quality initial population. Secondly, exploitation and exploration are enhanced by setting adaptive weights and dynamic convergence factors. Further, a Levy flight mechanism is introduced to maintain the population diversity in each iteration. Finally, the Evolutionary Population Dynamics (EPD) mechanism is introduced to improve the efficiency of search agents in finding the optimum. Another problem lies in the Semi-Supervised Extreme Learning Machine (SSELM) based on manifold regularization is an effective classification and regression model, but the random generation of input weights and hidden layer thresholds and the grid selection of hyperparameters lead to unsatisfactory classification performance. To this end, we developed the MSWOA-SSELM model, optimally selected the parameters of SSLEM using MSWOA, and applied it to logging layer recognition, which effectively improved the accuracy of logging interpretation. By comparing the experiments with 14 swarm intelligence algorithms on 18 benchmark test functions, the CEC2017 benchmark suite, and an engineering application problem, the experimental results show that MSWOA is significantly superior and effective in solving global optimization problems. Finally, the proposed MSWOA-SSELM is applied in three wells and outperforms other classification models in terms of Accuracy (ACC), Root Mean Square Error (RMSE), and

关键词： whale optimization algorithm Semi-supervised extreme learning machine Levy flight mechanism Evolutionary population dynamics Oil layer recognition

来源：评论

学校读者我要写书评

暂无评论

A novel enhanced whale optimization algorithm for global optimization

引用

COMPUTERS & INDUSTRIAL ENGINEERING 2021年 153卷 107086-107086页

作者： Chakraborty, Sanjoy Saha, Apu Kumar Sharma, Sushmita Mirjalili, Seyedali Chakraborty, Ratul Iswar Chandra Vidysagar Coll Dept Comp Sci & Engn Belonia Tripura India Natl Inst Technol Agartala Dept Comp Sci & Engn Agartala Tripura India Natl Inst Technol Agartala Dept Math Agartala Tripura India Torrens Univ Australia Ctr Artificial Intelligence Res & Optimisat Brisbane Qld 4006 Australia Yonsei Univ YFL Yonsei Frontier Lab Seoul South Korea Maharaja Bir Bikram Coll Dept Stat Agartala Tripura India King Abdulaziz Univ Jeddah Saudi Arabia

One of the main issues with heuristics and meta-heuristics is the local optima stagnation phenomena. It is often called premature convergence, which refers to the assumption of a locally optimal solution as the best solution for an optimization problem and failure in finding the global optimum. whale optimization algorithm (WOA) has demonstrated its merits in the optimization area. Though WOA is an effective algorithm, it may suffer from a low exploration of the search space. In this work, an enhanced WOA (WOAmM) is proposed. The mutualism phase from Symbiotic Organisms Search (SOS) is modified and integrated with WOA to alleviate premature convergence's inherent drawback. The addition of a modified mutualism phase with WOA makes the algorithm a balanced one to explore search space more extensively and avoid wasting computational resources in excessive exploitation. The proposed WOAmM method is tested on 36 benchmark functions and IEEE CEC 2019 function suite. It is compared with a wide range of algorithms, including improved WOAs and other meta-heuristics. Statistical analyses and convergence analysis are performed as well to examine its effectiveness and convergence speed. In addition, six real-world engineering optimization problems are solved by the proposed method. The performance is compared with a wide range of existing algorithms to inspect the problem-solving capability of WOAmM. The results demonstrate the performance improvement of WOAmM and its superiority over different algorithms.

关键词： whale optimization algorithm Mutualism phase Meta-heuristic Benchmark function IEEE CEC 2019 functions Real-world problem

来源：评论

学校读者我要写书评

暂无评论

A cooperative whale optimization algorithm for energy-efficient scheduling of the distributed blocking flow-shop with sequence-dependent setup time

引用

COMPUTERS & INDUSTRIAL ENGINEERING 2023年第1期178卷

作者： Zhao, Fuqing Xu, Zesong Bao, Haizhu Xu, Tianpeng Zhu, Ningning Jonrinaldi Lanzhou Univ Technol Sch Comp & Commun Lanzhou 730050 Peoples R China Univ Andalas Dept Ind Engn Padang 25163 Indonesia

The distributed blocking flow-shop sequence-dependent scheduling problem (DBFSDSP) with the production efficiency measures has been extensively concerned as its wide industrial applications. Whereas, energy effi-ciency indicators are often ignored in the literature. The DBFSDSP considered makespan, total tardiness, and total energy consumption is investigated in this paper. A cooperative whale optimization algorithm (CWOA) is proposed to solve the DBFSDSP as the complexity of the distributed and multi-objective optimization. First, the critical path of DBFSDSP is defined. An energy-saving operation for the non-critical path is designed to reduce the energy consumption of the system. Second, an accelerated operation for the critical path is designed to reduce the makespan and total tardiness. Third, three acceptance criteria for multi-objective optimization are proposed to improve the diversity of the population. The statistical and computational experimentation in an extensive benchmark testified that the CWOA outperforms the state-of-the-art algorithms regarding efficiency and sig-nificance in solving DBFSDSP.

关键词： Distributed scheduling Blocking flow -shop whale optimization algorithm Energy-efficient scheduling Sequence-dependent setup times

来源：评论

学校读者我要写书评

暂无评论

Weapon-Target Assignment Using a whale optimization algorithm

引用

INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE SYSTEMS 2023年第1期16卷 62-62页

作者： Zhang, Jinzhong Kong, Min Zhang, Gang Huang, Yourui West Anhui Univ Sch Elect & Optoelect Engn Luan 237012 Peoples R China

The weapon-target assignment (WTA) is a well-known task distribution issue in complicated combinational optimization, which is essential to management and decision-making in marine coordinated combat. This paper proposes a whale optimization algorithm (WOA) to address the WTA and the purpose was to maximize the combat effectiveness and determine the greatest decision matrix while equitably distributing the weapon unit resources of the weapon systems to the threat targets. The WOA is based on the whales' bubble-net assaulting behavior that mimics encompassing contraction strategy, bubble-net assaulting strategy and random hunting strategy to successfully resolve the optimization issue. The WOA not only has excellent stability and robustness to determine a quicker convergence speed and greater calculation accuracy but also utilizes exploration or exploitation to avoid search stagnation and accomplish the most effective solution. Four sets of experiments are utilized to confirm the superiority and productivity of the WOA, the results are compared with those of AOA, BA, GWO, MVO, SCA, SOA, SSA and TSA by maximizing the fitness value. The experimental results demonstrate that WOA has a greater convergence precision and stronger optimization efficiency, which is a practical and feasible method to satisfy the fundamental requirements of real-time decision-making.

关键词： Weapon-target assignment whale optimization algorithm Weapon system Decision matrix Combat effectiveness

来源：评论

学校读者我要写书评

暂无评论

A novel combined model based on echo state network optimized by whale optimization algorithm for blast furnace gas prediction

引用

ENERGY 2023年第1期279卷

作者： Wen, Shizhao Wang, Hongzeng Qian, Jinhua Men, Xuanyu Northeastern Univ Dept Math Shenyang Peoples R China

The accurate prediction of blast furnace gas (BFG) holder level is crucial for reasonable gas dispatch. Therefore, we propose an improved echo-state network (ESN) model, based on variational modal decomposition (VMD) and whale optimization algorithm (WOA), for the BFG system. This model extracts inherent characteristic components of the sequence using VMD for prediction and determines model inputs via partial autocorrelation functions (PACF). ESN effectively handles the shortcomings of other classical neural networks with many training parameters and slow calculation speed. The important parameters are optimized through WOA to improve the prediction accuracy of the proposed model. Based on our proposed model, the average MAPE of three datasets is 0.1805% for 1-Step prediction, 0.1829% for 3-Step prediction, and 0.1886% for PACF prediction. With high prediction accuracy for BFG holder level, our model takes less time to establish and calculate, meeting requirements for short-term level prediction and more reasonable BFG scheduling decisions. The experiments and discussions support the correctness, effectiveness, and superiority of our model.

关键词： Blast furnace gas Short-term forecasting Variational modal decomposition Echo state network whale optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

A Location Method for Partial Discharge Using Time Reversal and Improved whale optimization algorithm

引用

IEEE ACCESS 2020年 8卷 171977-171987页

作者： Ma, Pengchi Wang, Zhijie Liu, Yonghui Shen, Pan Wang, Hong Fu, Xiaolin Yang, Wanhao Shanghai Dianji Univ Coll Elect Engn Shanghai 201306 Peoples R China Jiangsu Hongyuan Elect Co Ltd Nanjing 211100 Peoples R China Tongji Univ Sch Econ & Management Shanghai 200092 Peoples R China

Time difference of arrival method is commonly used in the location of partial discharges. In this method, the main problem are as follows: (1) time delay error is inevitable. (2) location algorithm is sensitive to time delay error. To solve the problems above, an ultra-high frequency localization method for transformer partial discharge based on time reversal and improved whale optimization algorithm is proposed in this article. The method is consisted of three parts, that including time delay extraction, time reversal imaging and optimal solution. Firstly, the time delay is extracted by energy accumulation method. And then the approximate position of partial discharge source is determined by time reversal imaging. Combined with the time reversal imaging, the strategy of initial population selection and weight setting in the whale optimization algorithm is improved. Finally, the improved whale optimization algorithm is used to solve the optimal solution. The results are demonstrated through simulation and experiment. Compared with other localization algorithms, it is shown that the improved whale optimization algorithm has a better control performance in stability and accuracy.

关键词： Partial discharges whales optimization Delay effects Focusing Interference Transformer partial discharge ultra-high frequency time reversal whale optimization algorithm location method

来源：评论

学校读者我要写书评

暂无评论

Health-aware multi-stage charging strategy for lithium-ion batteries based on whale optimization algorithm

引用

JOURNAL OF ENERGY STORAGE 2022年 55卷

作者： Zhao, Guanghui Wang, Yujie Chen, Zonghai Univ Sci & Technol China Dept Automat Hefei 230027 Peoples R China

Lithium-ion batteries are widely used in electronics, new energy electric vehicles and energy storage plants. They have become ideal energy storage devices for their excellent characteristics of high energy density, low self-discharge rate, low carbon and environmental protection. Thus, research on lithium-ion batteries has wide scientific and engineering significance. To promote the application of lithium-ion batteries, the charging speed and aging rate of the lithium-ion batteries should be optimized to improve the convenience and economics for using them. Therefore, in this paper, a health-aware multi-stage charging strategy is presented based on the whale optimization algorithm. Specifically, the electrical model, thermal model, and the semi-empirical aging model are established firstly. Then the multi-stage charging optimization strategy considering charging time and battery health loss is proposed. The whale optimization algorithm is presented to obtain the optimal current value at each stage, followed by exploring the factors affecting the charging performance which include fitness function weight, cut-off voltage and current stage number. Compared with constant current (CC) charging, the total fitness function loss decreased by 34.64%, and the charging time decreased by 11.45%. This paper provides audiences with a strategy to meet the trade-off between charging rapidity and battery life in different scenarios by setting the optimization weights.

关键词： Lithium-ion batteries Optimal charging strategy whale optimization algorithm Semi-empirical aging model

来源：评论

学校读者我要写书评

暂无评论

A novel path planning approach for AUV based on improved whale optimization algorithm using segment learning and adaptive operator selection

引用

OCEAN ENGINEERING 2023年第1期280卷

作者： Huang, Yujie Li, Yibing Zhang, Zitang Sun, Qian Harbin Engn Univ Coll Informat & Commun Harbin 150001 Peoples R China Minist Ind & Informat Technol Key Lab Adv Marine Commun & Informat Technol Harbin 150001 Peoples R China

A novel path planning approach for autonomous underwater vehicles is proposed in this paper. It seeks a better navigation path under complex terrain and uncertain ocean currents. On the one hand, this problem is converted into a deterministic optimization problem using the order relation of interval number and vector analysis method. On the other hand, the whale optimization algorithm using segment learning and adaptive operator selection is proposed to solve this problem. Firstly, the elite and edge sets are judged by fitness and Euclidean distance, respectively. Based on them, a dynamic partitioning strategy and a weighted mean strategy are used to construct virtual individuals. The virtual individuals are incorporated into the whale optimization algorithm to construct an evolutionary pool, which can realize the balance between exploration to exploitation to improve the search ability of the algorithm. Second, an adaptive operator selection mechanism considering individual preferences is added to the algorithm. This mechanism uses the operators' historical information and future projections to guide the individual in choosing an appropriate evolutionary operator. The simulation results show that the robustness and search capability of the algorithm presented in this study are more potent than other comparative algorithms.

关键词： Path planning Autonomous underwater vehicle Uncertain ocean currents whale optimization algorithm Segment learning Adaptive operator selection

来源：评论

学校读者我要写书评

暂无评论

A newly developed hybrid method on pavement maintenance and rehabilitation optimization applying whale optimization algorithm and random forest regression

引用

INTERNATIONAL JOURNAL OF PAVEMENT ENGINEERING 2023年第2期24卷

作者： Naseri, Hamed Jahanbakhsh, Hamid Foomajd, Amirabbas Galustanian, Narek Karimi, Mohammad M. D. Waygood, E. O. Ecole Polytech Montreal Univ Dept Civil Engn Montreal PQ Canada Amirkabir Univ Technol Dept Civil & Environm Engn Tehran Iran Univ Sci & Culture Dept Civil Engn Tehran Iran Southern Illinois Univ Edwardsville Sch Engn Carbondale IL USA Tarbiat Modares Univ Dept Civil & Environm Engn Tehran Iran

Developing an accurate pavement prediction model plays a dominant role in pavement M&R optimization. Despite employing different robust machine learning techniques to predict pavement conditions, these methods have some weaknesses in synchronising with exact optimization algorithms. The main contribution of this study is to propose a novel method for optimizing the pavement M&R plan with high accuracy. Contrary to conventional approaches, a robust prediction algorithm, Random Forest Regression (RFR), is applied to predict the pavement International Roughness Index (IRI). In addition, Multiple Linear Regression (MLR) is employed to assess the performance of the proposed technique in terms of IRI prediction accuracy. whale optimization algorithm (WOA), as a powerful metaheuristic optimization algorithm, is utilised to obtain the optimal solution to the pavement M&R optimization problem. RFR is run as an internal part of the WOA in the introduced method. Furthermore, Genetic algorithm (GA) is used to examine the performance of the proposed approach in finding the optimal solution. The RFR results conclude a more accurate prediction of IRI than MLR based on all machine learning performance indicators. Furthermore, the newly developed hybrid model significantly outperforms GA in finding the optimal and cost-effective solution to the M&R optimization problem.

关键词： whale optimization algorithm maintenance and rehabilitation random forest regression international roughness index pavement performance model pavement management system

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：