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 artif...
详细信息
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.
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) f...
详细信息
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 optimizationalgorithms: 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.
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 poin...
详细信息
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 optimizationalgorithms. (C) 2022 Sharif University of Technology. All rights reserved.
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...
详细信息
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 so...
详细信息
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 optimizationalgorithms 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.
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 ...
详细信息
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.
multi-verse optimization algorithm (MVO) is one of the recent meta-heuristic optimizationalgorithms. The main inspiration of this algorithm came from multi-verse theory in physics. However, MVO like most optimization...
详细信息
multi-verse optimization algorithm (MVO) is one of the recent meta-heuristic optimizationalgorithms. The main inspiration of this algorithm came from multi-verse theory in physics. However, MVO like most optimizationalgorithms 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 optimizationalgorithms 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.
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 fa...
详细信息
In this research, the Harris hawks optimizationalgorithm (HHO), the grasshopper optimizationalgorithm (GOA) and the multi-verse optimization algorithm (MVO) have been used in solving manufacturing optimization probl...
详细信息
In this research, the Harris hawks optimizationalgorithm (HHO), the grasshopper optimizationalgorithm (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 optimizationalgorithm, simulated annealing, the artificial bee colony, harmony search, improved differential evolution, the hybrid particle swarm algorithm, teaching learning-based optimizationalgorithms, 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.
This research offers a fast and accurate method for measuring the biogas production rate throughout biogas production. An agricultural biogas plant's measurement of eight process variables served as the source of ...
详细信息
This research offers a fast and accurate method for measuring the biogas production rate throughout biogas production. An agricultural biogas plant's measurement of eight process variables served as the source of experimental data used to create the models. Biomass type, reactor/feeding, volatile solids, pH, organic load rate, hydraulic retention time, temperature, and reactor volume were utilized in this context. Artificial neural networks (ANN) were developed to evaluate the biogas production rate. The variable selection was carried out using the cuckoo optimizationalgorithm (COA), multi-verse optimization algorithm (MVO), leagues championship algorithm (LCA), evaporation-rate water cycle algorithm (ERWCA), stochastic fractal search (SFS), and teaching-learning-based optimization (TLBO). In this study, the model's size decreased, the important process variables were highlighted, and the ANN models' potential was enhanced for prediction. The proposed COA, MVO, LCA, ERWCA, SFS, and TLBO and ensembles are the outcome of using the abovementioned approaches to synthesize the multi-layer perceptron (MLP). To evaluate the effectiveness of the used models, we have developed a scoring system in addition to employing mean absolute error, mean square error, and coefficient of determination as accuracy criteria. Implementing the COA, MVO, LCA, ERWCA, SFS, and TLBO algorithms enhances the accuracy of the MLP. It is found that some of the used hybrid techniques could provide better prediction outputs than traditional MLP rankings. Additional investigation indicated that the ERWCA is better than the three other algorithms. The biogas production rate was estimated with the greatest precision with R2 = 0.9314 and 0.9302, RMSE of 0.1969 and 0.24925, and MAE of 0.1307 and 0.19591.
暂无评论