检索结果-内蒙古大学图书馆

An Overview and Experimental Study of Learning-Based Optimization Algorithms for the Vehicle Routing Problem

IEEE/CAA Journal of Automatica Sinica 2022年第7期9卷 1115-1138页

作者： Bingjie Li Guohua Wu Yongming He Mingfeng Fan Witold Pedrycz School of Traffic and Transportation Engineering Central South UniversityChangsha 410075China College of Systems Engineering National University of Defense TechnologyChangsha 410073China Department of Electrical and Computer Engineering University of AlbertaEdmontonAB T6G 2V4Canada the Department of Electrical and Computer Engineering Faculty of EngineeringKing Abdulaziz UniversityJeddah 21589Saudi Arabia the Systems Research Institute Polish Academy of SciencesWarsaw 01447Poland IEEE

The vehicle routing problem(VRP)is a typical discrete combinatorial optimization problem,and many models and algorithms have been proposed to solve the VRP and its *** existing approaches have contributed significantly to the development of this field,these approaches either are limited in problem size or need manual intervention in choosing *** solve these difficulties,many studies have considered learning-based optimization(LBO)algorithms to solve the *** paper reviews recent advances in this field and divides relevant approaches into end-to-end approaches and step-by-step *** performed a statistical analysis of the reviewed articles from various aspects and designed three experiments to evaluate the performance of four representative LBO ***,we conclude the applicable types of problems for different LBO algorithms and suggest directions in which researchers can improve LBO algorithms.

关键词： End-to-end approaches learning-based optimization(LBO)algorithms reinforcement learning step-by-step approaches vehicle routing problem(VRP)

来源：评论

学校读者我要写书评

暂无评论

Automatic First Arrival Picking for Seismic Data using Kalman Filter

Automatic First Arrival Picking for Seismic Data using Kalma...

引用

2023 International Symposium on networks, computers and Communications, ISNCC 2023

作者： Esmat, Muhammad Liu, Bo Al-Shaikhi, Ali Hanafy, Sherif Mohandes, Mohamed Fekri, Faramarz Electrical Engineering Department Dhahran31261 Saudi Arabia Geosciences Department Dhahran31261 Saudi Arabia School of Electrical and Computer Engineering Georgia Institute of Technology Atlanta United States

ISBN: (纸本)9798350335590

The first arrival time of seismic waves is a crucial parameter for seismic data analysis, which is used to determine the depth and location of subsurface structures. However, the estimation of first arrival time is often challenging due to the presence of noise and uncertainties in the data. In this study, we propose a novel approach that utilizes the Kalman filter with generalized likelihood ratio (GLR) to estimate the first arrival time in seismic data. First, a discrete time linear system with unknown amplitudes changes occurring at unknown time instants is used to reformulate the convolutional model. Then, to provide residual signals, we apply a Kalman filter based on the no change hypothesis to the linear system. Finally, to estimate the first arrival time, a generalized likelihood ratio (GLR)-based change detection technique is utilized. Using the simulated data, we verified the performance of the proposed approach. Overall, this study presents a promising approach for improving the accuracy of first arrival picking in the presence of different noise levels. © 2023 IEEE.

关键词： Seismic waves

来源：评论

学校读者我要写书评

暂无评论

The Spectral vs. Energy Efficiency Trade-Off in Dynamic User Clustering Aided mmWave NOMA networks

引用

IEEE Transactions on Communications 2024年第6期73卷 4503-4519页

作者： Rai, Sudhakar Sharma, Ekant Jagannatham, Aditya K. Hanzo, Lajos Indian Institute Of Technology Kanpur Department Of Electrical Engineering Kanpur208016 India Indian Institute Of Technology Roorkee Department Of Electronics And Communication Engineering Uttarakhand Roorkee247667 India University Of Southampton School Of Electronics And Computer Science SouthamptonSO17 1BJ United Kingdom

The spectral efficiency (SE) and global energy efficiency (GEE) trade-off encountered in the design of millimeter-wave (mmWave)-based massive multi-input multi-output (MIMO) non-orthogonal multiple access (NOMA) networks is investigated with a particular focus on user clustering. By exploiting the similarity among user channels a pair of spectral and energy-efficient user clustering algorithms are proposed for dynamically selecting both the number of clusters and the number of users in each cluster. Subsequently, a joint analog precoder/combiner and user clustering technique is developed, followed by a multi-objective optimization (MOO) framework for flexibly balancing the GEE and SE objectives in a mmWave NOMA network subject to specific constraints. The MOO objective is initially transformed to a weighted sum rate maximization problem, followed by a quadratic-transform (QT)-based approach conceived for maximizing the non-convex objective by approximating it as a concave-convex function. Our simulation results demonstrate that the user clustering techniques designed attain a 85% performance gain over random clustering technique and demonstrating the benefits of the algorithm designed for mmWave NOMA networks. © 1972-2012 IEEE.

关键词： Spectrum efficiency

来源：评论

学校读者我要写书评

暂无评论

Multiple Gain Adaptations for Improved Neural networks Training 14

Multiple Gain Adaptations for Improved Neural Networks Train...

引用

2024 IEEE 14th Annual Computing and Communication Workshop and Conference, CCWC 2024

作者： Challagundla, Jeshwanth Tyagi, Kanishka Chugh, Tushar Manry, Michael The University of Texas at Arlington Department of Electrical Engineering ArlingtonTX United States Carnegie Mellon University School of Computer Science Pittsburgh United States

ISBN: (纸本)9798350360134

A two stage algorithm developed called Multiple Gain Adaptations for Improved networks (MGAIN) is presented. MAGAIN alternatively finds output weights and uses several gain factors to update the input weights in a Multi-Layer Perceptron. The gain factors are computed using Newtons method. Our method dynamically adjusts the quantity of gain factors calculated to maximize the reduction in loss with each epoch. The results demonstrate that our approach outperforms existing second order algorithms across the majority of diverse datasets. © 2024 IEEE.

关键词： Backpropagation

来源：评论

学校读者我要写书评

暂无评论

Design Optimization and Performance Analysis of Rectangular Structured Moving Magnet Linear Actuator 4

Design Optimization and Performance Analysis of Rectangular ...

引用

4th International Conference on Computing, Mathematics and engineering Technologies, iCoMET 2023

作者： Ahmad, Hussain Jawad, Muhammad Ahmad, Zahoor Ahmad, Aftab Sarhad University of Science & Information Technology Dept. Electrical Engineering Peshawar Pakistan School of Electrical Engineering Southeast University Nanjing China Comsats University Islamabad Abbottabad Campus Dept. of Electrical and Computer Engineering Abbottabad Pakistan School of Electrical Engineering Inner Mongolia University of Technology Hohhot China

ISBN: (纸本)9798350335316

This article examines a new linear oscillating actuator (LOA) design that uses rectangular-shaped core materials and permanent magnets (PMs). The paper's primary objective is to examine a novel LOA topology with a rectangular-shaped core and PMs as an alternative to the tubular LOA. A Static core material is housed between the mover's components, and two stator cores with two coils each are placed on either side of the mover. The dimensions of all the parameters are swept for optimization, and the optimal parameter dimension is chosen based on the optimal value of the electromagnetic (EM) force. An analysis is done for output parameters like EM force and stroke. EM force per PM mass of the investigated design of LOA is 67 percent higher than of conventional rectangular-shaped LOA. Additionally, the proposed design's EM force density is 23.8 percent higher than that of the conventional design of LOA. Furthermore, the stroke of the proposed LOA is also feasible and more than most of the designs of the LOA. Additionally, the proposed design of the LOA is simple structure, low-cost, and feasible for fabrication. © 2023 IEEE.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Permutation Sum-Capacity of Binary Adder Multiple-Access Channels

Permutation Sum-Capacity of Binary Adder Multiple-Access Cha...

引用

2023 IEEE International Symposium on Information Theory, ISIT 2023

作者： Lu, William Makur, Anuran Purdue University Department of Computer Science West LafayetteIN47907 United States Purdue University School of Electrical and Computer Engineering West LafayetteIN47907 United States

ISBN: (纸本)9781665475549

Propelled by recent advances in the study of point-to-point permutation channels, which stem from communication networks and biological communications applications, we analyze the permutation binary adder multiple-access channel (PAMAC) in this work. The PAMAC network model consists of d senders communicating with a single receiver through a standard binary adder multiple-access channel followed by a random permutation block that shuffles the output codeword of the multiple-access channel. We formally define an appropriate notion of permutation sum-capacity Cpsum for this model, and then establish that Cpsum = d/2. To derive an achievability bound we construct d randomized encoders where input codewords are i.i.d. samples from Bernoulli distributions with carefully chosen parameters. These parameters can be perceived as roots of the probability generating function of the distribution over the output alphabet after the PAMAC's addition operation. Our achievability proof crucially uses eigenvalue perturbation results to provide quantitative estimates on the stability of the roots, which allows us to analyze decoding performance. This argument also yields an inner bound on the permutation capacity region of the PAMAC model. Finally, we also obtain a converse bound on Cpsum matching our achievability result. © 2023 IEEE.

关键词： Adders

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Virtual Impedance Control Techniques for Improved Stability in DC Microgrids

引用

IEEE Access 2025年 13卷 99077-99091页

作者： Moura, Beatriz Cristina Rodrigues, Danillo Borges Guimaraes, Erico Chagas Lima, Gustavo Brito de Silveira, Joao Pedro Carvalho Freitas, Luiz Carlos Gomes Neto, Pedro Jose Dos Santos State University of Campinas Department of Integrated Systems Campinas São Paulo 13083860 Brazil Federal University of Triângulo Mineiro Faculty of Electrical Engineering Minas Gerais 38025180 Brazil Federal University of Uberlândia Faculty of Electrical Engineering Minas Gerais 38400902 Brazil State University of Campinas Electrical and Computer Engineering School São Paulo 13083852 Brazil

DC microgrids (DCMGs) have been extensively studied using various control techniques, with droop control and its variants being the most widely adopted. Virtual impedance control (VIC), a technique commonly used in AC microgrids, can be adapted for DCMGs. VIC employs virtual resistance as the droop constant and incorporates a dynamic element, such as a virtual inductor, to enhance microgrid stability. This study compares four approaches to implementing VIC to determine the most effective method for reducing voltage oscillations during transient conditions, which enhances overall DCMG stability. In this paper, the analyzed DCMG consists of two units of energy storage system (ESS), electronic loads, and a renewable energy source (RES), each connected via a dedicated power electronic converter. Parametric analyses are conducted to define the VIC parameter range, and a stability analysis is performed to evaluate the different methods of implementation. The techniques under analysis are tested using a controller hardware-in-the-loop (C-HIL). The results establish the operating range for each VIC strategy, the stability limitations, and identifying the control approach that achieves optimal damping performance and stability in the studied microgrid. © 2013 IEEE.

关键词： Controller hardware-in-the-loop (C-HIL) dc microgrids (DCMGs) droop control virtual impedance control (VIC)

来源：评论

学校读者我要写书评

暂无评论

Distributed Fault-Tolerant Consensus Tracking of Multi-Agent Systems Under Cyber-Attacks

引用

IEEE/CAA Journal of Automatica Sinica 2022年第6期9卷 1037-1048页

作者： Chun Liu Bin Jiang Xiaofan Wang Huiliao Yang Shaorong Xie School of Mechatronic Engineering and Automation Shanghai UniversityShanghai 200444 School of Artificial Intelligence Shanghai UniversityShanghai 200444China IEEE College of Automation Engineering Nanjing University of Aeronautics and AstronauticsNanjing 210016China College of Energy and Electrical Engineering Hohai UniversityNanjing 210016China School of Computer Engineering and Science Shanghai UniversityShanghai 200444China

This paper investigates the distributed fault-tolerant consensus tracking problem of nonlinear multi-agent systems with general incipient and abrupt time-varying actuator faults under ***,a decentralized unknown input observer is established to estimate relative states and actuator ***,the estimated and output neighboring information is combined with distributed fault-tolerant consensus tracking *** of reaching leader-following exponential consensus tracking of multi-agent systems under both connectivity-maintained and connectivity-mixed attacks are derived with average dwelling time,attack frequency,and attack activation rate technique,*** example verifies the effectiveness of the fault-tolerant consensus tracking algorithm.

关键词： Cyberattacks fault-tolerant consensus tracking incipient and abrupt actuator faults nonlinear multi-agent systems unknown input observer

来源：评论

学校读者我要写书评

暂无评论

New Experimental-Based Modelling of Traction Motor Stator Poles and Windings for Impedance Spectroscopy Analysis

引用

IEEE Transactions on Industry Applications 2025年

作者： Ravanis, N. Douvaras, A. Gyftakis, K.N. Technical University of Crete School of Electrical and Computer Engineering Chania73100 Greece

Permanent magnet motors are subjected to a variety of stresses that depend on the application requirements. Those stresses may lead to progressive degradation of the motor components until a failure appears. However, it is to be noted that the inherent manufacturing tolerances have a strong role to play in the ageing mechanism because the various stresses will have a stronger impact on them. Stator faults are among the most serious faults in all electric motors due to their fast evolution to a catastrophic breakdown. Stator faults are linked with the degradation and failure of the insulation system. This paper will aim to provide a detailed equivalent circuit of a permanent magnet motor's stator poles with mounted armature coils for impedance spectroscopy purposes. The experimentally derived model is a sensitive map to manufacturing weaknesses in the insulating materials and can be used for identifying different defects, as well as their form and location, thus improving the quality inspection procedure before the assembly of the motor. This procedure will exclude poles with weak insulation and therefore significantly increase the longevity and reliability of the motors. © 1972-2012 IEEE.

关键词： Stators

来源：评论

学校读者我要写书评

暂无评论

Machine Learning based Comparative Analysis of Cervical Cancer Risk Classifications Algorithms 2

Machine Learning based Comparative Analysis of Cervical Canc...

引用

2nd IEEE International Conference on Advances in Computing, Communication and Applied Informatics, ACCAI 2023

作者： Ganguly, Tania Pati, Peeta Basa Deepa, K. Singh, Tripty Ozer, Tolga Amrita School of Computing Department of Computer Science and Engineering Bengaluru India Amrita School of Engineering Department of Electrical and Electronics Engineering Bengaluru India Afyon Kocatepe University Technology Faculty Electric Electronic Engineering Afyonkarahisar Turkey

ISBN: (纸本)9798350315905

Cervical cancer is a major health concern for women worldwide, and early detection is essential for successful treatment. Since symptoms often do not appear until later stages, early screening is necessary. Machine learning can help classify cervical cancer risk by analyzing patient datasets and identifying the important factors that predict the likelihood of emerging cervical cancer. This paper evaluates six different machine-learning approaches for analyzing risk factors associated with cervical cancer using a dataset of 838 instances with 36 features. Results show that the SVM classifier performs the best, with an accuracy of 99.60% which emphasize the possibility of utilizing machine learning to enhance the precision of cervical cancer risk assessment. This can result in the development of better screening and prevention techniques for cervical cancer, which can be more effective in identifying and managing this disease. © 2023 IEEE.

关键词： Logistic regression

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：