检索结果-内蒙古大学图书馆

Competing leaders grey wolf optimizer and its application for training multi-layer perceptron classifier

EXPERT SYSTEMS WITH APPLICATIONS 2024年 239卷

作者： Yang, Zhenlun Guangzhou Panyu Polytech Sch Informat Engn Guangzhou 511483 Guangdong Peoples R China

The multi-layer perceptron (MLP) is a highly popular artificial neural network used for classification across various applications. swarm intelligence algorithms, such as the grey wolf optimizer, battle royale optimizer, sine cosine algorithm, and their improved variants, have been widely utilized for training MLP classifiers, addressing the challenging optimization problem that covers various difficulties in determining the optimal network parameters to minimize errors while processing datasets. Nevertheless, these prevailing algorithms frequently encounter problems like stagnation in local optima and inefficient search, leading to a deficiency in their ability to deliver efficient and accurate solutions. In order to overcome this challenge and provide a powerful tool for MLP classifier training, the competing leaders grey wolf optimizer (CGWO) is proposed in this study. CGWO benefits from a novel mechanism of competing leaders that provides a flexible wolf pack leadership hierarchy to avoid stagnation in local optima and accelerate convergence speed. In addition, a population diversity-enhanced initiation method is designed to help improve the efficiency of the mechanism of competing leaders. The performance of CGWO in training MLP classifiers is evaluated in an experiment comparing CGWO with nine state-of-the-art algorithms on eleven classification datasets representing a wide range of optimization challenges. CGWO substantially outperforms its competitors regarding optimal fitness, classification accuracy, and convergence speed;and shows competitive performance in computation time comparison.

关键词： Multi-layer perceptron Grey wolf optimizer Competing leaders Neural networks swarm intelligence algorithm

来源：评论

学校读者我要写书评

暂无评论

Hierarchy Strengthened Grey Wolf Optimizer for Numerical Optimization and Feature Selection

引用

IEEE ACCESS 2019年 7卷 78012-78028页

作者： Tu, Qiang Chen, Xuechen Liu, Xingcheng Sun Yat Sen Univ Sch Elect & Informat Technol Guangzhou 510006 Guangdong Peoples R China Sun Yat Sen Univ Xinhua Coll Sch Informat Sci Guangzhou 510520 Guangdong Peoples R China

Grey wolf optimizer (GWO) is an efficient swarm intelligence algorithm for kinds of optimization problems. However, GWO tends to be trapped in local optimum when solving large-scale problems. Social hierarchy is one of the main characteristics of GWO which affect the searching efficiency. Thus, an improved algorithm called hierarchy strengthened GWO (HSGWO) is proposed in this paper. First, the pack of wolves is roughly divided into two categories: dominant wolves and omega wolves. Second, the enhanced elite learning strategy is performed for dominant wolves to prevent the misguidance of low-ranking wolves and improve the collective efficiency. Then, the hybrid GWO and differential evolution (DE) strategy is executed for omega wolves to avoid falling into local optimum. In addition, a new hybrid one-dimensional and total-dimensional selection strategy is designed for omega wolves to balance the exploration and the exploitation during optimization. Finally, a perturbed operator is used to maintain the diversity of the population and further improve the exploration. To make a complete evaluation, the proposed HSGWO is first compared with six representative GWO variants for 50-dimensional problems based on CEC2014 benchmarks. The scalability of HSGWO is further tested by comparing it with eight state-of-the-art non-GWO algorithms for large-scale optimization problems with 100 decision variables. In addition, feature selection problem is used for testing the effectiveness of HSGWO on real-world applications. The experimental results demonstrated that the proposed algorithm outperforms other algorithms in terms of solution quality and convergence rate in most of the experiments.

关键词： swarm intelligence algorithm grey wolf optimizer (GWO) social hierarchy numerical optimization feature selection

来源：评论

学校读者我要写书评

暂无评论

Intelligent Neural Integral Sliding-mode Controller for a space robotic manipulator mounted on a free-floating satellite

引用

ADVANCES IN SPACE RESEARCH 2023年第9期71卷 3734-3747页

作者： Lavin-Delgado, J. E. Chavez-Vazquez, S. Gomez-Aguilar, J. F. Alassafi, Madini O. Alsaadi, Fawaz E. Ahmad, Adil M. Univ Politecn Estado Guerrero UPEG Direcc Ingn Redes & Telecomunicac Carretera Fed Iguala Taxco KM 105 Taxco De Alarcon 40321 Guerrero Mexico Tecnol Nacl Mexico CENIDET Interior Internado Palmira S-N Col Palmira Cuernavaca 62490 Morelos Mexico CONACyT Tecnol Nacl Mex CENIDET Interior Internado Palmira S N Col Palmira Cuernavaca 62490 Morelos Mexico King Abdulaziz Univ Fac Comp & Informat Technol Dept Informat Technol Jeddah Saudi Arabia

In this paper, a fractional neural integral sliding-mode controller based on the Caputo-Fabrizio derivative and Riemann-Liouville integral for a robot manipulator mounted on a free-floating satellite is proposed and developed. The mathematical model is obtained by using the Euler-Lagrange formalism and generalized through the Caputo-Fabrizio derivative. The conventional neural integral sliding-mode controller reported in the literature were also developed to make a comparative analysis between both controllers. The con-trollers are tuned using a swarm intelligence algorithm. External disturbances are also considered. Simulation results show the superiority and robustness of the proposed control system for trajectory tracking tasks through the root-mean-square error. Additionally, two addi-tional reference trajectories were considered. In this sense, the numerical simulations were done by using the same orders and gains, showing the robustness of our fractional-order control strategy under different operating conditions. Further, the proposed controller uses the fractional derivative in the sense of Caputo-Fabrizio which has not been used enough in the area of robotics, so this is a start to analyse the contributions that arise when using said derivative in this robotic.(c) 2022 COSPAR. Published by Elsevier B.V. All rights reserved.

关键词： Robot manipulator Fractional calculus Neural network controller Artificial intelligence Big Data Analytics Decision Making Aerospace systems swarm intelligence algorithm

来源：评论

学校读者我要写书评

暂无评论

Improved African Vulture Optimization algorithm Based on Quasi-Oppositional Differential Evolution Operator

引用

IEEE ACCESS 2022年 10卷 95197-95218页

作者： Liu, Renju Wang, Tianlei Zhou, Jing Hao, Xiaoxi Xu, Ying Qiu, Jiongzhi Wuyi Univ Dept Intelligent Mfg Jiangmen 529020 Peoples R China

In this study, an improved African vulture optimization algorithm (IAVOA) that combines the African vulture optimization algorithm (AVOA) with both quasi-oppositional learning and differential evolution is proposed to address specific drawbacks of the AVOA, including low population diversity, bad development capability, and unbalanced exploration and development capabilities. The improved algorithm has three parts. First, quasi-oppositional learning is introduced in the population initialization and exploration stages to improve population diversity. Second, a differential evolution operator is introduced in the local search position update of each population to improve exploration capability. Third, adaptive parameters are introduced to the differential evolution operator, thus balancing the algorithm exploration and development. A numerical simulation experiment based on 36 different types of benchmark functions showed that while the IAVOA can enhance the convergence speed and solution accuracy of the basic AVOA and two variants of AVOA, IAVOA outperforms the other 7 swarm intelligence algorithms in the mean and best values of 33 benchmark functions.

关键词： Statistics Sociology Mathematical models Particle swarm optimization Metaheuristics Convergence Benchmark testing African vulture optimization algorithm benchmark function differential evolution quasi-oppositional learning swarm intelligence algorithm

来源：评论

学校读者我要写书评

暂无评论

Cooperative Networking Strategy of UAV Cluster for Large-Scale WSNs

引用

IEEE SENSORS JOURNAL 2022年第22期22卷 22276-22290页

作者： Chen, Yidi Liu, Hao Guo, Jiapeng Wang, Yujie Liu, Fei Ding, Shanshan Chen, Renwen Nanjing Univ Aeronaut & Astronaut State Key Lab Mech & Control Mech Struct Nanjing 210016 Peoples R China

To solve the shortcomings of wireless sensor networks (WSNs) in data collection in a wide range, long distance, and other complex environments, such as high networking cost, short network life cycle, and difficult data collection, a data collection strategy based on the unmanned aerial vehicle (UAV) cluster collaborative networking is proposed. First, the node structure and deployment application of WSNs are analyzed, and the architecture of UAV collaborative data collection is designed. Second, the related models of communication energy consumption between WSNs' network and UAV cluster, UAV cluster task allocation, and path planning are established successively. Then, a simple but efficient task planning strategy considering UAV forward and return distances is proposed. Finally, for the problem of model solving, the solution strategy of the heuristic swarm intelligence algorithm is proposed. The simulation results verify that the strategy reduces the overall network energy consumption by 42.16% and the total range of UAV by 9.7% and realizes the relative minimization of WSNs energy consumption and UAV flight cost on the premise of ensuring the full coverage of WSNs' nodes.

关键词： Wireless sensor networks Sensors Optimization Data collection Autonomous aerial vehicles Energy consumption Heuristic algorithms Collaborative perception data collection swarm intelligence algorithm unmanned aerial vehicle (UAV) wireless sensor networks (WSNs)

来源：评论

学校读者我要写书评

暂无评论

Coordinated control strategy for braking and shifting for electric vehicle with two-speed automatic transmission

引用

ETRANSPORTATION 2022年 13卷

作者： Liu, Yonggang Gao, Dekun Zhai, Kening Huang, Qi Chen, Zheng Zhang, Yi Chongqing Univ State Key Lab Mech Transmiss Chongqing 400044 Peoples R China Chongqing Univ Coll Mech & Vehicle Engn Chongqing 400044 Peoples R China Dongfeng Liuzhou Automobile Co Ltd Passenger Car Technol Ctr Liuzhou 545005 Guangxi Peoples R China Chongqing Univ Sci & Technol Sch Mech & Power Engn Chongqing 401331 Peoples R China Kunming Univ Sci & Technol Fac Transportat Engn Kunming 650500 Yunnan Peoples R China Univ Michigan Dearborn Dept Mech Engn Dearborn MI 48128 USA

This paper presents a coordinated control strategy for braking and shifting of electric vehicles that are equipped with a two-speed automatic transmission. The coordinated control strategy mainly includes braking force distribution and synthetic shifting regulation for braking operations. Firstly, the vehicle model is established for investigation of the shift process during braking. Then, the braking force distribution considering energy efficiency is presented, and the regenerative braking force is calculated. With the target of maximizing energy recovery and ensuring driving comfort, an optimal shift schedule during regenerative braking is advanced based on the multi-objective cuckoo search algorithm. Due to the interaction of regenerative braking force in torque releasing and restoring process, an adaptive braking mode switching control is proposed to improve the shifting smoothness. The detailed simulations and hardware-in-the-loop validations are conducted to verify the anticipated performance of the proposed strategy. (C) 2022 Elsevier B.V. All rights reserved.

关键词： Electric vehicle Regenerative braking Multi-objective cuckoo search swarm intelligence algorithm

来源：评论

学校读者我要写书评

暂无评论

RWFOA: a random walk-based fruit fly optimization algorithm

引用

SOFT COMPUTING 2020年第16期24卷 12681-12690页

作者： Chen, Chong Shandong Polytech Jinan Peoples R China

As one kind of the classic swarm intelligence (SI) algorithms, fruit fly optimization algorithm has been widely used in many aspects, such as multiple objective optimization and service computing. However, due to the limitation that introduced by the initial population location, its global optimization ability is limited. Therefore, we propose a random walk-based fruit fly optimization algorithm, namely RWFOA, to enhance its global optimization ability. RWFOA employs the random walk mechanism to dynamically adjust the position of the fruit fly population, which can reduce the impact of the initial population location and thus enhance the global optimization ability. We conduct a comprehensive experimental evaluation of RWFOA by comparing it with three representative algorithms, i.e., the OFOA, CFOA and IFFO, over 29 widely used benchmark functions published in CEC 2015. Experimental results demonstrate that RWFOA can find better solutions in most of the selected benchmark functions.

关键词： Fruit fly optimization algorithm Random work Probability graph Roulette scheme swarm intelligence algorithm

来源：评论

学校读者我要写书评

暂无评论

Soft computing applied to the build of textile defects inspection system

引用

IET COMPUTER VISION 2013年第5期7卷 373-381页

作者： Darwish, Saad Mohamed Univ Alexandria Dept Informat Technol Inst Grad Studies & Res Alexandria 21526 Egypt

The inspection of textile defects is challenging because of the large number of defects categories that are characterised by their imprecision and uncertainty. In this study, novel interval type-2 fuzzy system is proposed for resolving defects recognition problem of textile industries. The proposed system mixes interval type-2 fuzzy reasoning and swarm optimisation algorithm together in order to enhance the defects classification capabilities. Interval type-2 fuzzy logic is powerful in handling high level of indecisions in the human decision making process, including uncertainties in measurements of textile features and data used to calibrate the examination's parameters. swarm intelligence algorithm is used to optimise parameters of the membership functions to increase the accuracy of fuzzy controller. Besides, the problem of fuzzy linguistic rules learning has been tackled by utilising ant colony meta-heuristic method to reduce the complexity of the inspection system. Excellent recogniser results on real textile samples, using this system, are demonstrated.

关键词： decision making fuzzy logic fuzzy reasoning heuristic programming inspection learning (artificial intelligence) particle swarm optimisation production engineering computing textile industry ant colony optimisation soft computing textile defect inspection system defects recognition problem textile industries interval type-2 fuzzy reasoning system particle swarm optimisation algorithm defects classification capability interval type-2 fuzzy logic human decision making process examination parameter calibration swarm intelligence algorithm membership functions fuzzy controller fuzzy linguistic rules learning ant colony metaheuristic method

来源：评论

学校读者我要写书评

暂无评论

A modified hybrid rice optimization algorithm for solving 0-1 knapsack problem

引用

APPLIED intelligence 2022年第5期52卷 5751-5769页

作者： Shu, Zhe Ye, Zhiwei Zong, Xinlu Liu, Shiqin Zhang, Daode Wang, Chunzhi Wang, Mingwei Hubei Univ Technol Sch Comp Sci Wuhan Peoples R China Hubei Univ Technol Sch Mech Engn Wuhan Peoples R China

The 0-1 knapsack problem (KP) is a classic NP-hard problem and could be handled by swarm intelligence algorithms. However, most of these algorithms might be trapped in the local optima as the scale increases. Hybrid rice optimization (HRO) is a novel swarm intelligence algorithm inspired by the breeding process of Chinese three-line hybrid rice, its population is classified into three types such as the maintainer, restorer and sterile line and several stages including hybridization, selfing and renewal are implemented. In this paper, a modified HRO algorithm is proposed for the complicated large-scale 0-1 KP. A dynamic step is introduced in the renewal stage to balance the exploration and exploitation phases. Moreover, HRO is combined with binary ant colony optimization (BACO) algorithm to compose the parallel model and serial model for enhancing the convergence speed and search efficiency. In the parallel model, HRO and BACO are independently implemented on two subpopulations and communicate during each iteration. In the serial model, BACO is embedded in HRO as an operator to update the maintainer line. The experimental results on 0-1 KPs of different scales and correlations demonstrate the outperformance of the parallel model and serial model.

关键词： 0-1 knapsack problem swarm intelligence algorithm Hybrid rice optimization algorithm Binary ant colony optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Intelligent proportional-integral-derivate controller using metaheuristic approach via crow search algorithm for vibration suppression of flexible plate structure

引用

JOURNAL OF LOW FREQUENCY NOISE VIBRATION AND ACTIVE CONTROL 2024年第1期43卷 560-574页

作者： Shaari, Aida Nur Syafiqah Hadi, Muhamad Sukri Wahab, Abdul Malek Abdul Ab Talib, Mat Hussin Yatim, Hanim Mohd Darus, Intan Zaurah Mat Tokhi, M. Osman Univ Teknol MARA Coll Engn Sch Mech Engn Shah Alam Malaysia Univ Teknol Malaysia Sch Mech Engn Johor Baharu Malaysia London South Bank Univ Sch Engn London England Univ Teknol MARA Coll Engn Sch Mech Engn Shah Alam 40450 Malaysia

Proportional-integral-derivate (PID) controller has gained popularity since the advancement of smart devices especially in suppressing the vibration on flexible structures using different approaches. Such structures required accurate and reliable responses to prevent system failures. swarm intelligence algorithm (SIA) is one of the optimization methods based on nature that managed to solve real-world problems. Crow search is a well-known algorithm from the SIA group that can discover optimum solutions in both local and global searches by utilizing fewer tuning parameters compared to other methods. Hence, this study aimed to simulate a PID controller tuned by SIA via crow search for vibration cancellation of horizontal flexible plate structures. Prior to that, an accurate model structure is developed as a prerequisite for PID controller development. After the best model is achieved, the proportional-integral-derivative-crow-search (PID-CS) performance was compared to a traditional tuning approach known as the Ziegler Nichols (ZN) to validate its robustness. The result revealed the PID-CS outperformed the proportional-integral-derivative-Ziegler Nichols (PID-ZN) with attenuation values of 44.75 and 42.74 dB in the first mode of vibration for single sinusoidal and real disturbances, respectively. In addition, the value of mean squared error (MSE) for PID-ZN and PID-CS for single sinusoidal disturbance are 0.0167 and 0.0081, respectively. Meanwhile, PID-ZN and PID-CS achieved 2.3981 x 10-4 and 2.3737 x 10-4 when they were exerted with real disturbance. This proves that the PID-CS is more accurate compared to the PID-ZN as it achieved the lowest MSE value.

关键词： Crow search proportional-integral-derivate controller swarm intelligence algorithm flexible structure active vibration control

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：