检索结果-内蒙古大学图书馆

FLSN-MVO: Edge Computing and Privacy Protection Based on Federated Learning Siamese Network With multi-verse optimization algorithm for Industry 5.0

IEEE OPEN JOURNAL OF THE COMMUNICATIONS SOCIETY

引用

IEEE OPEN JOURNAL OF THE COMMUNICATIONS SOCIETY 2025年 6卷 3443-3458页

作者： Yin, Shoulin Li, Hang Laghari, Asif Ali Teng, Lin Gadekallu, Thippa Reddy Almadhor, Ahmad Shenyang Normal Univ Software Coll Shenyang 110034 Peoples R China Harbin Engn Univ Sch Informat & Commun Engn Harbin 150000 Peoples R China Lovely Profess Univ Div Res & Dev Phagwara 144411 India Jouf Univ Coll Comp & Informat Sci Dept Comp Engn & Networks Sakaka Al Jouf Saudi Arabia Al Jouf Univ Coll Comp & Informat Sci Dept Comp Engn & Networks Sakaka 72388 Saudi Arabia

With the development of deep learning technology, artificial intelligence has important applications in all aspects of society, but the lack of data has become a vital factor restricting the further evolution of artificial intelligence in industry 5.0. Federated learning can effectively use the edge node data and solve the data problem of artificial intelligence model training by sharing gradient. In federated learning, the terminal transmits the updated model parameter values instead of the primordial data to the server, thus becoming a key technology to ensure data privacy and security in edge computing. However, since attackers can use the shared gradient to launch malicious attacks to steal users' privacy, how to securely upload the gradient and aggregate it has become an important topic to ensure privacy security in federated learning. Therefore, this paper proposes an edge computing and privacy protection based on federated learning Siamese network with multi-verse optimization algorithm for industry 5.0. This scheme can reduce the expenditure of endpoint participation in federated learning while protecting user privacy. In the federated learning structure, the feature information of the input samples is mapped to a new output vector through the subnetwork of the Siamese network, and the approximation degree between the input samples is judged by comparing the similarity degree between the output vectors. The parameters of the network are optimized by multi-verse optimization algorithm to reduce the convergence time. Meanwhile, an adaptive weight aggregation algorithm is designed to reduce the degradation of model performance and stability caused by data quality differences, so as to improve the accuracy of the model and accelerate the model to reach the optimal value. Finally, comprehensive experiments on three public standard data sets show that the proposed method achieves higher model accuracy and faster model convergence than the most advanced methods.

关键词： Privacy Data privacy Federated learning Computational modeling Data models Protection Fifth Industrial Revolution Artificial intelligence optimization Edge computing Siamese network edge computing privacy protection multi-verse optimization algorithm adaptive weight aggregation

来源：评论

学校读者我要写书评

暂无评论

multi-verse optimization algorithm- and salp swarm optimization algorithm-based optimization of multilevel inverters

引用

NEURAL COMPUTING & APPLICATIONS 2021年第6期33卷 1935-1950页

作者： Ceylan, Oguzhan Kadir Has Univ Dept Management Informat Syst Istanbul Turkey

Renewable energy sources are installed into both distribution and transmission grids more and more with the introduction of smart grid concept. Hence, efficient usage of cascaded H-bridge multilevel inverters (MLIs) for power control applications becomes vital for sustainable electricity. Conventionally, selective harmonic elimination equations need to be solved for obtaining optimum switching angles of MLIs. The objective of this study is to obtain switching angles for MLIs to minimize total harmonic distortion. This study contributes to the solution of this problem by utilizing two recently developed intelligent optimization algorithms: multi-verse optimization algorithm and salp swarm algorithm. Moreover, well-known particle swarm optimization is utilized for MLI optimization problem. Seven-level, 11-level and 15-level MLIs are used to minimize total harmonic distortions. Simulation results with different modulation indexes for seven-, 11- and 15-level MLIs are calculated and compared in terms of the accuracy and solution quality. Numerical calculations are verified by using MATLAB/Simulink-based models.

关键词： multilevel inverters Harmonic elimination multi-verse optimization algorithm Salp swarm algorithm Particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

multi-verse optimization algorithm for optimal synthesis of phase-only reconfigurable linear array of mutually coupled parallel half-wavelength dipole antennas placed at finite distances from the ground plane

引用

SCIENTIA IRANICA 2022年第4期29卷 1915-1924页

作者： Jamunaa, D. Mahanti, G. K. Hasoon, F. N. Natl Inst Technol Dept Elect & Commun Engn Durgapur 713209 India NUST Coll Engn Dept Elect & Commun Engn Muscat Oman

In the case of antenna arrays, researchers usually neglect the effect of mutual coupling of antennas placed in proximity to each other. The interchange of electromagnetic energy between an antenna and a far-field point depends on not only the transmitting antenna, but also its neighboring antennas. This effect is referred to as mutual coupling between dipole antenna elements and is considered here in the synthesis of phase-only reconfigurable antenna arrays. The main objective of this work is to produce the desired side lobe level and voltage standing wave ratio, in addition to few other radiation pattern parameters. multi-verse optimization algorithm is employed for the purpose of generating voltage amplitude and discrete phase distributions in the dipole elements to generate flat-top beam/pencil beam patterns. These two patterns share common amplitude distributions and differ in phase distributions. Results of simulations proved that this algorithm accomplished its task successfully and was superior to other algorithms like particle swarm optimization, grey wolf optimization, and imperialist competitive optimization algorithms. (C) 2022 Sharif University of Technology. All rights reserved.

关键词： Reconfigurable linear array antenna multi-verse optimization algorithm Mutual coupling Voltage standing wave ratio Particle swarm optimization Grey wolf optimization Imperialist competitive optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Binary multi-verse optimization algorithm for global optimization and discrete problems

引用

INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS 2019年第12期10卷 3445-3465页

作者： Al-Madi, Nailah Faris, Hossam Mirjalili, Seyedali Princess Sumaya Univ Technol King Hussein Fac Comp Sci Amman Jordan Univ Jordan King Abdullah II Sch Informat Technol Business Informat Technol Dept Amman Jordan Univ Queensland Sch Informat Technol & Elect Engn St Lucia Qld 4072 Australia

multi-verse optimizer is one of the recently proposed nature-inspired algorithms that has proven its efficiency in solving challenging optimization problems. The original version of multi-verse optimizer is able to solve problems with continuous variables. This paper proposes a binary version of this algorithm to solve problems with discrete variables such as feature selection. The proposed Binary multi-verse optimizer is equipped with a V-shaped transfer function to covert continuous values to binary, and update the solutions over the course of optimization. A comparative study is conducted to compare Binary multi-verse optimizer with other binary optimization algorithms such as Binary Bat algorithm, Binary Particle Swarm optimization, Binary Dragon algorithm, and Binary Grey Wolf Optimizer. As case studies, a set of 13 benchmark functions including unimodal and multimodal is employed. In addition, the number of variables of these test functions are changed (5, 10, and 20) to test the proposed algorithm on problems with different number of parameters. The quantitative results show that the proposed algorithm significantly outperforms others on the majority of benchmark functions. Convergence curves qualitatively show that for some functions, proposed algorithm finds the best result at early iterations. To demonstrate the applicability of proposed algorithm, the paper considers solving feature selection and knapsack problems as challenging real-world problems in data mining. Experimental results using seven datasets for feature selection problem show that proposed algorithm tends to provide better accuracy and requires less number of features compared to other algorithms on most of the datasets. For knapsack problem 17 benchmark datasets were used, and the results show that the proposed algorithm achieved higher profit and lower error compared to other algorithms.

关键词： Feature selection optimization multi-verse optimization algorithm Global optimization

来源：评论

学校读者我要写书评

暂无评论

A new chaotic multi-verse optimization algorithm for solving engineering optimization problems

引用

JOURNAL OF EXPERIMENTAL & THEORETICAL ARTIFICIAL INTELLIGENCE 2018年第2期30卷 293-317页

作者： Sayed, Gehad Ismail Darwish, Ashraf Hassanien, Aboul Ella Cairo Univ Fac Comp & Informat Cairo Egypt Helwan Univ Fac Sci Cairo Egypt Sci Res Grp Egypt Cairo Egypt

multi-verse optimization algorithm (MVO) is one of the recent meta-heuristic optimization algorithms. The main inspiration of this algorithm came from multi-verse theory in physics. However, MVO like most optimization algorithms suffers from low convergence rate and entrapment in local optima. In this paper, a new chaotic multi-verse optimization algorithm (CMVO) is proposed to overcome these problems. The proposed CMVO is applied on 13 benchmark functions and 7 well-known design problems in the engineering and mechanical field;namely, three-bar trust, speed reduce design, pressure vessel problem, spring design, welded beam, rolling element-bearing and multiple disc clutch brake. In the current study, a modified feasible-based mechanism is employed to handle constraints. In this mechanism, four rules were used to handle the specific constraint problem through maintaining a balance between feasible and infeasible solutions. Moreover, 10 well-known chaotic maps are used to improve the performance of MVO. The experimental results showed that CMVO outperforms other meta-heuristic optimization algorithms on most of the optimization problems. Also, the results reveal that sine chaotic map is the most appropriate map to significantly boost MVO's performance.

关键词： Nature-inspired algorithm multi-verse optimization algorithm Chaotic theory Constrained optimization problems

来源：评论

学校读者我要写书评

暂无评论

The multi-verse optimization algorithm using a Fuzzy Clustering Technique to Effectively Detect Frauds in Automobile

The Multi-Verse Optimization Algorithm using a Fuzzy Cluster...

引用

2023 International Conference on Integrated Intelligence and Communication Systems, ICIICS 2023

作者： Reddy, R. Archana Ramadan, Ghazi Mohamad Ramesh, Bhookya Sundaram, S. Meenakshi Al-Jawahry, Hassan M. SR University School of Computer Science and Artificial Intelligence Telangana Warangal India Ahl Al Bayt University College of Mlt Karbala Iraq Hyderabad India Nitte Meenakshi Institute of Technology Department of Ai and Ds Bengaluru India The Islamic University Najaf Iraq

ISBN: (纸本)9798350315455

The growing use of the internet, especially in the automotive industry, has resulted in the development of several online services. Globally, the exponential expansion of financial fraud has resulted in huge financial losses for organisations in a variety of industries. This research develops an innovative approach that utilizes a capability of the multi-verse optimization algorithm (MVOA) to improve the performance in fraud detection through fuzzy clustering method. The contributions of MVOA are in the enhancement of model adaptability to ever-changing fraud patterns, the adept handling of imbalanced data through diverse exploration, and the resolution of feature interdependencies. The suggested fuzzy clustering technique improves the majority sample dataset within the Advanced Integrated Fraud Detection System (AIFDS) framework by removing outliers. The dataset utilization is thoroughly evaluated using modern classifiers such as XGBoost, CATBoost, Decision Tree and Random Forest. The AIFDS, enhanced by the MVOA-with fuzzy clustering model achieved better performance in accuracy of 94.32%, Sensitivity of 96.37 and precision of 93.49%, and enhancing fraud detection and lowering the financial risks associated with fraudulent operations. © 2023 IEEE.

关键词： Advanced Integrated Fraud Detection System Automobile Industry Classification Fuzzy clustering technique multi-verse optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Simulation and modeling of an improved multi -verse optimization algorithm for QoS-aware web service composition with service level agreements in the cloud environments

引用

SIMULATION MODELLING PRACTICE AND THEORY 2020年 103卷 102090-102090页

作者： Yaghoubi, Mohamadali Maroosi, Ali Islamic Azad Univ Dept Comp Engn Ferdows Branch Ferdows Iran Univ Torbat Heydarieh Dept Comp Engn Torbat Heydarieh Iran

Cloud computing is a new trend in information technology that provides resources and shares services by web services over the internet for users. Many web services have similar functionality with different quality of service (QoS) in the cloud. Thus, an appropriate service composition method is needed to assign an optimal composition of services to the users. Furthermore, service level agreement (SLA) which is the level of service expected from the service provider should be satisfied by the service composition method that less considered in previous studies. Introducing an appropriate algorithm for web service composition that could achieve high QoS while satisfying SLA constrains is one of the main issues in the cloud computing area. In this study, an improved multi-verse optimization algorithm for web service composition that is called IMVO algorithm is proposed to improve QoS while satisfying SLA. The simulation results show increasing of normalized QoS up to 57% in comparison with the other approaches, especially for service composition problems with SLA.

关键词： Cloud computing multi-verse optimization algorithm Quality of Service (QoS) Web service composition

来源：评论

学校读者我要写书评

暂无评论

Prediction and minimization of blasting flyrock distance, using deep neural networks and gravitational search algorithm, JAYA, and multi-verse optimization algorithms

引用

Heliyon 2024年第19期10卷 e37876页

作者： Ghojoghi, Eslam Ebrahimi Farsangi, Mohamad Ali Mansouri, Hamid Rashedi, Esmat Mining Engineering Department of Mining Engineering Shahid Bahonar University of Kerman Iran Communication Engineering Faculty of Electrical and Computer Engineering Graduate University of Advanced Technology Kerman Iran

Flyrock represents a significant and fundamental challenge in surface mine blasting, carrying inherent risks to humans and the environment. Consequently, accurate prediction, minimization, and identification of the factors influencing flyrock distance are imperative for effective control and mitigation of its destructive consequences. Machine learning and artificial intelligence methodologies have emerged as viable means to predict and simulate in different scientific fields. This study employs Deep Neural Network in conjunction with three optimization algorithms including the JAYA algorithm, multi-verse optimization algorithm, and Gravitational Search algorithm to predict blasting flyrock distance. The developed model consists of a combination of seven input parameters, encompassing both blasting design parameters and rock geomechanical properties. The output of the Deep Neural Networks model is the flyrock distance. For the training and testing of the model, a dataset comprising of 245 blasting records, collected from Songun copper mine, Iran, was utilized. The DNN model yielded an R2 value of 0.96 and an MSE value of 34.11. These results demonstrate the high accuracy and predictive capability of the model. Furthermore, the application of three optimization algorithms resulted in similar optimized parameter values, which minimized flyrock distances. © 2024 The Authors

关键词： Blasting Deep neural Network Flyrock distance Gravitational search algorithm JAYA algorithm multi-verse optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

The Harris hawks, grasshopper and multi-verse optimization algorithms for the selection of optimal machining parameters in manufacturing operations

引用

MATERIALS TESTING 2019年第8期61卷 725-733页

作者： Yildiz, Ali Riza Yildiz, Betul Sultan Sait, Sadiq M. Li, Xinyu Uludag Univ Dept Automot Engn Gorukle Bursa Turkey Univ Michigan Ann Arbor MI 48109 USA Mississippi State Univ Ctr Adv Vehicular Syst NSF & DOE Funded Res Projects Starkville MS USA KFUPM Comp Engn Dhahran Saudi Arabia KFUPM Ctr Commun & IT Res Dhahran Saudi Arabia Huazhong Univ Sci & Technol Dept Ind & Mfg Syst Engn Huazhong Peoples R China

In this research, the Harris hawks optimization algorithm (HHO), the grasshopper optimization algorithm (GOA) and the multi-verse optimization algorithm (MVO) have been used in solving manufacturing optimization problems. This paper is the first research study for the optimization of processing parameters for manufacturing processes using the HHO, the GOA, and the MVO in the literature, and in particular, for grinding operations. A well-known grinding optimization problem is solved to prove how effective the HHO, the GOA and the MVO are in solving manufacturing problems and to demonstrate superiority over other algorithms. The results of the HHO, the GOA and the MVO are compared with other methods such as the genetic algorithm, the ant colony algorithm, the scatter search, the differential evolution algorithm, the particle swarm optimization algorithm, simulated annealing, the artificial bee colony, harmony search, improved differential evolution, the hybrid particle swarm algorithm, teaching learning-based optimization algorithms, the cuckoo search, and the fractal search algorithm. The results show that the HHO, the GOA, and the MVO are efficient optimization approaches for obtaining optimal manufacturing variables in manufacturing operations.

关键词： Harris hawks optimization algorithm grasshopper optimization algorithm multi-verse optimization algorithm manufacturing grinding design

来源：评论

学校读者我要写书评

暂无评论

A performance analysis of a hybrid golden section search methodology and a nature-inspired algorithm for MPPT in a solar PV system

引用

ARCHIVES OF ELECTRICAL ENGINEERING 2019年第3期68卷 611-627页

作者： Mostafa, Hazem H. Ibrahim, Amr M. Anis, Wagdi R. Egyptian Chinese Univ Fac Engn Energy & Renewable Energy Dept Cairo 11724 Egypt Ain Shams Univ Elect Power & Machines Dept Fac Engn Cairo Egypt Ain Shams Univ Fac Engn Elect & Commun Dept Cairo Egypt

This research presents a comparative study for maximum power point tracking (MPPT) methodologies for a photovoltaic (PV) system. A novel hybrid algorithm golden section search assisted perturb and observe (GSS-PO) is proposed to solve the problems of the conventional PO (CPO). The aim of this new methodology is to boost the efficiency of the CPO. The new algorithm has a very low convergence time and a very high efficiency. GSS-PO is compared with the intelligent nature-inspired multi-verse optimization (MVO) algorithm by a simulation validation. The simulation study reveals that the novel GSS-PO outperforms MVO under uniform irradiance conditions and under a sudden change in irradiance.

关键词： hybrid optimization golden sections search multi-verse optimization algorithm maximum power point tracking perturb and observe photovoltaic (PV)

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：