检索结果-内蒙古大学图书馆

An improved grasshopper optimization algorithm based on dynamic dual elite learning and sinusoidal mutation

COMPUTING 2022年第5期104卷 981-1015页

作者： Chen, Lei Tian, Yu Ma, Yunpeng Tianjin Univ Commerce Sch Informat Engn Tianjin Peoples R China Tianjin Univ Commerce Sch Sci Tianjin Peoples R China

Grasshopper optimization algorithm (GOA) is a meta-heuristic algorithm for solving optimization problems by modeling the biological habit and social behavior of grasshopper swarms in nature. Compared with other optimization algorithms, GOA still has room to improve its performance on solving complex problems. Therefore, this paper proposes an improved grasshopper optimization algorithm (EMGOA) based on dynamic dual elite learning and sinusoidal mutation. First of all, dynamic elite learning strategy is adopted to improve the influence of elites on the update process, enabling the algorithm to have a faster convergence speed. Then, sinusoidal function is utilized to guide the mutation of the current global optimal individual during each iteration to avoid the algorithm falling into the local optimum and improve the convergence accuracy of the algorithm. In order to investigate the performance of the proposed EMGOA algorithm, experiments are conducted on 26 benchmark functions and CEC2019 in this paper. The experimental results show that the optimization performance of EMGOA is obviously better than GOA, and EMGOA is competitive with six state-of-the-art meta-heuristic optimization algorithms.

关键词： Grasshopper optimization algorithm Dynamic elite learning Sinusoidal mutation optimization algorithm Meta-heuristic algorithm

来源：评论

学校读者我要写书评

暂无评论

Pairing-Free Identity-Based Digital Signature algorithm for Broadcast Authentication Based on Modified ECC Using Battle Royal optimization algorithm

引用

WIRELESS PERSONAL COMMUNICATIONS 2022年第3期123卷 2341-2365页

作者： Kumar, Vivek Ray, Sangram Natl Inst Technol Sikkim Dept Comp Sci & Engn Sikkim 737139 India

In wireless sensor networks (WSN), broadcast authentication is an important security service that provides secure communication. Several mobile users are allowed by this broadcast authentication service. There are some concerns in the sensor network, which depend on security based on maintaining consumer untracking and privacy for data transmission. To overcome the concern of security issues, an Identity (ID)-based cryptography method is introduced. This paper presented a Pairing-Free Identity-based Digital Signature (PF-IBDS) algorithm based on Modified Elliptic Curve Cryptography (MECC) by using Battle Royal optimization algorithm. The main aim of this paper is to secure the data transmission for message authentication. The proposed protocol is to enhance the speed of authentication, reduce the signature size and speed up the signature verification. Moreover, this paper analyses the security by BAN (Burrows-Abadi-Needham) logic and comparing with the existing protocols. It is verified that the developed protocol is protected and well-organized for peer-to-peer communications. Therefore, the proposed method offers secure key management, fast authentication, and also minimizes the computation overhead. The proposed authentication process is simulated in the Java platform. The performance of this protocol has compared with other existing approaches in terms of key verification time, key generation time and computational time.

关键词： Key generation Authentication WSN optimization algorithm Security Elliptic curve cryptography Identity-based signature Pairing-free

来源：评论

学校读者我要写书评

暂无评论

Improved Reptile Search optimization algorithm Using Chaotic Map and Simulated Annealing for Feature Selection in Medical Field

引用

IEEE ACCESS 2022年 10卷 51428-51446页

作者： Elgamal, Zenab Sabri, Aznul Qalid Md Tubishat, Mohammad Tbaishat, Dina Makhadmeh, Sharif Naser Alomari, Osama Ahmad Univ Malaya Fac Comp Sci & Informat Technol Kuala Lumpur 50603 Malaysia Zayed Univ Coll Technol Innovat Abu Dhabi U Arab Emirates Ajman Univ Coll Engn & Informat Technol Artificial Intelligence Res Ctr AIRC Ajman U Arab Emirates Univ Sharjah MLALP Res Grp Sharjah U Arab Emirates

The increased volume of medical datasets has produced high dimensional features, negatively affecting machine learning (ML) classifiers. In ML, the feature selection process is fundamental for selecting the most relevant features and reducing redundant and irrelevant ones. The optimization algorithms demonstrate its capability to solve feature selection problems. Reptile Search algorithm (RSA) is a new nature-inspired optimization algorithm that stimulates Crocodiles' encircling and hunting behavior. The unique search of the RSA algorithm obtains promising results compared to other optimization algorithms. However, when applied to high-dimensional feature selection problems, RSA suffers from population diversity and local optima limitations. An improved metaheuristic optimizer, namely the Improved Reptile Search algorithm (IRSA), is proposed to overcome these limitations and adapt the RSA to solve the feature selection problem. Two main improvements adding value to the standard RSA;the first improvement is to apply the chaos theory at the initialization phase of RSA to enhance its exploration capabilities in the search space. The second improvement is to combine the Simulated Annealing (SA) algorithm with the exploitation search to avoid the local optima problem. The IRSA performance was evaluated over 20 medical benchmark datasets from the UCI machine learning repository. Also, IRSA is compared with the standard RSA and state-of-the-art optimization algorithms, including Particle Swarm optimization (PSO), Genetic algorithm (GA), Grasshopper optimization algorithm (GOA) and Slime Mould optimization (SMO). The evaluation metrics include the number of selected features, classification accuracy, fitness value, Wilcoxon statistical test (p-value), and convergence curve. Based on the results obtained, IRSA confirmed its superiority over the original RSA algorithm and other optimized algorithms on the majority of the medical datasets.

关键词： Reptile search algorithm (RSA) feature selection (FS) optimization algorithm chaos theory simulated annealing (SA)

来源：评论

学校读者我要写书评

暂无评论

Research on the Construction of Smart Grid Digital System Based on Big Data Cloud Computing Model optimization algorithm 4

Research on the Construction of Smart Grid Digital System Ba...

引用

4th IEEE International Conference on Power, Electronics and Computer Applications, ICPECA 2024

作者： Li, Zhipeng Liu, Shaobo Zhang, Jianfeng Wang, Jun Shen, Shuo State Grid Gansu Electric Power Company Lanzhou China State Grid Gansu Electric Power Company Digital Division Lanzhou China

ISBN: (纸本)9798350359589

An intelligent power business development method based on digital service information is proposed. At the same time, a complete data mining framework is constructed. Parameters such as distance of adjacent pixels, similarity degree of carrier components and average amplitude were determined by coding and parsing. Then the digital business information resources are extracted. The mining method of data cloud in power system based on time series is established. The correlation degree of each information characteristic of middle station is analyzed based on classification and characteristic identification of power system middle station. Experiments show that the algorithm can effectively improve the distribution of data in the middle station in every minute. The standard deviation of the algorithm is reduced and the mining effect is improved. © 2024 IEEE.

关键词： artificial intelligence digital system optimization algorithm smart grid

来源：评论

学校读者我要写书评

暂无评论

Multi-source Heterogeneous Data Processing and optimization algorithm in Intelligent Distribution Network Planning System 3

Multi-source Heterogeneous Data Processing and Optimization ...

引用

3rd International Conference on Data Analytics, Computing and Artificial Intelligence, ICDACAI 2024

作者： Hu, Xinyu Han, Wei Cao, Xinnan Zhou, Jinfei Jiang, Wangjie State Grid Nantong Power Supply Company Nantong Jiangsu226000 China

ISBN: (纸本)9798331519032

In the process of distribution network planning (DNP), massive heterogeneous data, such as power system operation data, enterprise operation management data, nonelectric energy data, etc., bring challenges to data processing because of their high dimension, large volume and strong coupling. Aiming at these problems, this paper proposes a DNP method combining multi-source heterogeneous data (MHD) processing technology and optimization algorithm. This method fuses multi-source data by Kalman filter (KF) to improve data accuracy, and extracts key features by principal component analysis (PCA) to provide a simplified data set for subsequent optimization. In the aspect of optimization algorithm, the multi-objective optimization algorithm NSGA-II is used to solve the DNP problem, taking into account the objectives of economy and reliability, and satisfying the physical constraints such as power flow balance, voltage limitation and line capacity. The experimental results show that this method is superior to the traditional planning method in terms of total investment cost, operation cost, average power outage time and power supply reliability, which effectively verifies its effectiveness and superiority. The research in this paper provides new ideas and methods for intelligent DNP, which is helpful to improve the safety, stability and economic operation level of power system. © 2024 IEEE.

关键词： distribution network planning system Kalman filtering Multi-source heterogeneous data optimization algorithm principal component analysis

来源：评论

学校读者我要写书评

暂无评论

RL based hyper-parameters optimization algorithm (ROA) for convolutional neural network

引用

JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING 2022年第10期14卷 13349-13359页

作者： Talaat, Fatma M. Gamel, Samah A. Kafrelsheikh Univ Fac Artificial Intelligence Kafrelsheikh Egypt Mansoura Univ Fac Engn Dept Comp Engn & Syst Mansoura Egypt

Many real-world applications necessitate optimization in dynamic situations, where the difficulty is to locate and follow the optima of a time-dependent objective function. To solve dynamic optimization problems (DOPs), many evolutionary techniques have been created. However, more efficient solutions are still required. Recently, a new intriguing trend in dealing with optimization in dynamic environments has developed, with new reinforcement learning (RL) algorithms predicted to breathe fresh life into the DOPs community. In this paper, a new Q-learning RL-based optimization algorithm (ROA) for CNN hyperparameter optimization is proposed. Two datasets were used to test the proposed RL model (MNIST dataset, and CIFAR-10 dataset). Due to the use of RL for hyperparameter optimization, very competitive results and good performance were produced. From the experimental results, it is observed that the CNN optimized by ROA has higher accuracy than CNN without optimization. When using the MNIST dataset, it is shown that the accuracy of the CNN optimized by ROA when learning 5 epoch is 98.97%, which is greater than the 97.62% of the CNN without optimization. When using the CIFAR-10 dataset, it is shown that the accuracy of the CNN optimized by ROA when learning 10 epoch is 73.40 percent, which is greater than 71.73% of the CNN without optimization.

关键词： optimization algorithm Deep learning Deep convolutional neural networks Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

An adaptive hydrologic cycle optimization algorithm for numerical optimization and data clustering

引用

INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS 2022年第9期37卷 6123-6151页

作者： Yan, Xiaohui Niu, Ben Chai, Yujuan Zhang, Zhicong Zhang, Liangwei Dongguan Univ Technol Sch Mech Engn Dongguan Peoples R China Shenzhen Univ Coll Management Shenzhen Peoples R China Shenzhen Univ Hlth Sci Ctr Sch Biomed Engn Shenzhen 518060 Peoples R China

The circulation and convergence of water in the hydrologic cycle process inspired us to design a new optimization algorithm, the Hydrologic Cycle optimization (HCO) algorithm. In this study, a comprehensive demonstration of the HCO was presented. First, a simplified model of the hydrological cycle phenomenon was established. Then, the framework of HCO and its operators were discussed and verified in detail. Several experiments were done to test the optimization ability of the HCO algorithm. In the first experiment, the parameter settings were tested, and an adaptive version of the algorithm was proposed. Then the HCO was tested on 20 numeric optimization benchmark functions and eight data clustering sets, respectively, and compared with other algorithms. The experimental results showed that the HCO is superior to the compared algorithms, indicating that it is a competitive approach for numerical and engineering optimization problems.

关键词： computational intelligence evolutionary computation hydrologic cycle optimization optimization algorithm swarm intelligence

来源：评论

学校读者我要写书评

暂无评论

Coyote optimization algorithm-Based PV Planning Strategy for Maximizing Hosting Capacity in A Distribution System

Coyote Optimization Algorithm-Based PV Planning Strategy for...

引用

IEEE Asia Meeting on Environment and Electrical Engineering (IEEE-AM)

作者： Nguyen Cong Chinh Nguyen Nhat Tung Nguyen Quang Thuan Thuyloi Univ Fac Elect & Elect Engn Hanoi Vietnam

ISBN: (纸本)9798350381061

This paper declares a Coyote optimization algorithm (COA)-based method of determining both optimal PV locations and sizes simultaneously in a distribution system with the largest hosting capacity (HC) of solar photovoltaic (PV) generation and minimizing system voltage deviation. The objective function includes PV hosting capacity (PVHC) and voltage deviation amplitude at each bus. The RMS bus voltage, the maximum size of each PV placement at an installed bus, the total active power losses, and reverse power flow at the substation are constraints to be met. The problem is solved using the Coyote optimization algorithm (COA). The IEEE 123-bus system is applied to test the proposed method. Results are compared with those obtained by other metaheuristic methods, including Genetic algorithm and Particle Swarm optimization. Test results show that the COA method yields exceptional solutions compare to GA and PSO methods in both optimality and convergence.

关键词： PV generation optimization algorithm Hosting capacity Smart inverter Reverse power flow.

来源：评论

学校读者我要写书评

暂无评论

A Group Teaching optimization algorithm for Priority-Based Resource Allocation in Wireless Networks

引用

WIRELESS PERSONAL COMMUNICATIONS 2022年第3期123卷 2449-2472页

作者： Sreethar, S. Nandhagopal, N. Karuppusamy, S. Anbu Dharmalingam, M. Excel Engn Coll Dept Comp Sci & Engn Namakkal Tamil Nadu India Excel Engn Coll Dept ECE Namakkal India Kongunadu Coll Engn & Technol Dept ECE Thottiam 621215 Tamil Nadu India

In wireless networks, resource allocation (RA) is considered as a very important and it is used to enhance the wireless and communication networks performances. D2D (Device-to-device) communication based RA is expressed as a MINLP (mixed integer nonlinear programming) issue. Existing strategies based on RA cannot offer integrative consideration to spectrum efficiency, QoS (Quality of Service) for networks with mixed traffic. When multiple users with various priorities utilize the similar network resource, then it is necessary to utilize the resource on priority basis. In this work, priority based RA is introduced using the GTOA (group teaching optimization algorithm) by combining spectrum resources from unlicensed and licensed spectrum bands to the D2D users in the mixed traffic scenarios. The GTOA optimization framework maximizes all the D2D pair's utility functions by reducing the whole energy utilization. The network contains the two types of users such as QoS services and BE (best effort) services. Along with several traffics, the function of utility is described for users. The priorities are assigned to the QoS services by the developed GTOA based RA mechanism for performing the resource allotment. As related to other current approaches, the GTOA procedure devours lessor complexity. For the real-time traffic, the developed GTOA can spontaneously assurance the QoS constraint and also owing to the utility function the developed GTOA system create the balance among fairness and throughput for BE traffic users. As a result, by executing RA, the resources and a user can be deliberated. The priority based RA is performed using MATLAB. Simulation outcomes show that the developed GTOA is most appropriate for the priority based RA to the D2D users in the mixed traffic scenarios.

关键词： Priority optimization algorithm Mixed traffic D2D communication Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Direct Torque Control With Variable Flux for an SRM Based on Hybrid optimization algorithm

引用

IEEE TRANSACTIONS ON POWER ELECTRONICS 2022年第6期37卷 6688-6697页

作者： Feng, Liyun Sun, Xiaodong Tian, Xiang Diao, Kaikai Jiangsu Univ Automot Engn Res Inst Zhenjiang 212013 Jiangsu Peoples R China

This article presents an optimal direct torque control (DTC) strategy with variable flux for a switched reluctance motor using the improved linear active disturbance rejection control (LADRC) plus the hybrid optimization algorithm (HOA). First, the constant flux amplitude is substituted by the variable flux DTC (VF-DTC) to reduce the torque ripple. Then, the LADRC with the improved extended state observer applied in speed controller is utilized instead of the conventional PI control to improve the speed of the observer, antidisturbance ability, and robustness. Moreover, the HOA is employed to search for the optimal control parameters and acquire satisfactory dynamic performances. Finally, the optimal VF-DTC system is implemented on a 12/8 SRM. Simulation and experimental results are carried out to compare the performances of the conventional DTC, the VF-DTC with LADRC, the VF-DTC with PI using HOA, and the proposed optimal VF-DTC using HOA. The results show that the proposed control method has a faster speed response, superior antidisturbance ability, and lower torque ripples.

关键词： Torque Reluctance motors optimization Control systems Couplings Observers Tuning Active disturbance rejection control (ADRC) direct torque control (DTC) optimization algorithm switched reluctance motor (SRM) variable flux

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：