检索结果-内蒙古大学图书馆

International Journal of Information and Communication Technology 2024年第2期24卷 145-155页

作者： Wang, Kaiku Huang, Congkuan Yang, Yang Department of Computer Science and Technology Beijing University of Aeronautics and Astronautics Beijing100191 China Department of Electrical Engineering and Automation Hefei University of Technology Hefei230009 China

Aiming at the problem of low precision and large cleaning error in multi-link similar data mining, a multi-link similar data mining cleaning method based on Bayesian algorithm is proposed in this paper. On the basis of extracting multi-link data, the data is preprocessed and the similarity between the data is calculated. The data with high similarity is input into the Bayesian network, and the data cleaning process is completed according to the maximum likelihood value of the data. Experimental results show that the mining accuracy of the proposed method for similar data can reach 98.51%, and the cleaning error is about 1.22%, indicating that the proposed method can more effectively complete the mining and cleaning of similar data in multi-links. Copyright © 2024 Inderscience Enterprises Ltd.

关键词： Directed graphs

来源：评论

学校读者我要写书评

暂无评论

Residual feature decomposition and multi-task learning-based variation-invariant face recognition

引用

Neural Computing and Applications 2024年第32期36卷 20147-20166页

作者： Haider, Abbas Wu, Guanfeng Spence, Ivor Wang, Hui School of Electronics Electrical Engineering and Computer Science Queen’s University Belfast University Rd BelfastBT7 1NN United Kingdom

Facial identity is subject to two primary natural variations: time-dependent (TD) factors such as age, and time-independent (TID) factors including sex and race. This study aims to address a broader problem known as variation-invariant face recognition (VIFR) by exploring the question: "How can identity preservation be maximized in the presence of TD and TID variations?" While existing state-of-the-art (SOTA) methods focus on either age-invariant or race and sex-invariant FR, our approach introduces the first novel deep learning architecture utilizing multi-task learning to tackle VIFR, termed "multi-task learning-based variation-invariant face recognition (MTLVIFR)." We redefine FR by incorporating both TD and TID, decomposing faces into age (TD) and residual features (TID: sex, race, and identity). MTLVIFR outperforms existing methods by 2% in LFW and CALFW benchmarks, 1% in CALFW, and 5% in AgeDB (20 years of protocol) in terms of face verification score. Moreover, it achieves higher face identification scores compared to all SOTA methods. Open source code. © The Author(s) 2024.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Reactive Power Optimization of AC-DC Hybrid System Based on Improved Whale Algorithm

Journal of Network Intelligence

引用

Journal of Network Intelligence 2024年第4期9卷 2084-2098页

作者： Huang, Xin-Yu Liang, Quan Chen, Xian-Fu Zhan, Chuang-Tao School of Electronic Electrical Engineering Physics Fujian University of Technology Fuzhou350118 China School of Computer Science Mathematics Fujian University of Technology Fuzhou350118 China

With the continuous construction of HVDC, it has gradually become dis-tances and large capacity transmission, as well as one of the main technologies of regional power grid interconnection. The scale of AC-DC hybrid grid continues to grow, bringing new challenges to reactive power balance and voltage stability of power grid. An improved whale optimization algorithm is proposed to solve the reactive power optimization problem of AC-DC hybrid systems. By introducing local neighborhood search mechanism, adaptive threshold and adaptive inertia weight, the local search accuracy, global search ability and convergence speed of the algorithm are improved. The reactive power optimization model is established with the total network loss and node voltage offset as the objective function, and the solution steps are given. An IEEE 22-node system with DC transmission lines is used as an example to simulate the proposed algorithm, and compared with the traditional whale optimization algorithm and genetic algorithm, the results show that the proposed algorithm has good convergence and stability, and can obtain better reactive power optimization effect. © 2024, Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Control and Stability of Large-scale Power System with Highly Distributed Renewable Energy Generation:Viewpoints from Six Aspects

引用

CSEE Journal of Power and Energy Systems 2023年第1期9卷 8-14页

作者： Qing-Hua Wu Anjan Bose Chanan Singh Joe H.Chow Gang Mu Yuanzhang Sun Zhaoxi Liu Zhigang Li Yang Liu School of Electric Power Engineering South China University of TechnologyGuangzhou 510640China School of Electrical Engineering&Computer Science Washington State UniversityPullmanWA 99164USA Department of Electrical and Computer Engineering Texas A&M UniversityCollege StationTX 77843USA Department of Electrical Computer and Systems EngineeringRensselaer Polytechnic Institute(RPI)TroyNYUSA Key Laboratory of Modern Power System Simulation and Control&Renewable Energy Technology Ministry of Education(Northeast Electric Power University)Jilin 132012China School of Electrical Engineering and Automation Wuhan UniversityWuhan 430072China

Power systems are moving toward a low-carbon or carbon-neutral future where high penetration of renewables is *** conventional fossil-fueled synchronous generators in the transmission network being replaced by renewable energy generation which is highly distributed across the entire grid,new challenges are emerging to the control and stability of large-scale power *** analysis and control methods are needed for power systems to cope with the ongoing *** the CSEE JPES forum,six leading experts were invited to deliver keynote speeches,and the participating researchers and professionals had extensive exchanges and discussions on the control and stability of power ***,potential changes and challenges of power systems with high penetration of renewable energy generation were introduced and explained,and advanced control methods were proposed and analyzed for the transient stability enhancement of power grids.

关键词： Distributed energy resources high converter penetration power system control renewable energy generation stability control transient stability

来源：评论

学校读者我要写书评

暂无评论

Create a Crowd Emotion Detection Framework With Ecological Validity

引用

IEEE Transactions on Affective Computing 2025年第2期16卷 1087-1103页

作者： Chen, Xiao Liu, Zhen Liu, Tingting Xiao, Jiangjian Ningbo University Faculty of Electrical Engineering and Computer Science Ningbo315211 China Ningbo University College of Science and Technology Cixi Ningbo315300 China Chinese Academy of Sciences Ningbo Institute of Materials Technology and Engineering Ningbo315201 China

Ecological validity remains essential for generalizing scientific research into real-world applications. However, current methods for crowd emotion detection lack ecological validity due to limited diversity samples in datasets. This paper proposes a crowd emotion detection framework that improves the ecological validity of models from both dataset and methodological perspectives. Firstly, we develop an Emotional Crowd Generator script within Grand Theft Auto V to generate a large-scale and diverse synthetic emotional crowd dataset, named Emotional-GTA (E-GTA). Secondly, we utilize prior features to enhance the model's generalization ability, especially for rare samples. Building on this, we introduce a dual-driven Graph-based Prior Feature and Image Fusion Network (GPIFN), which further strengthens our model's ecological validity from a methodological perspective. We propose a graphical representation that effectively constructs the Crowd Image Graph (CIG) and the Crowd Prior Features Graph (CPG). The CIG represents crowds from the perspective of the image features, while the CPG represents them from the perspective of prior features. We then design a dual-stream network GPIFN that extracts image features from the CIG and prior features from the CPG. Additionally, we design an Image and Prior Features Fusion Module (IPFM) that efficiently merges image and prior features while maintaining the original stream features. Our experiments demonstrate that both E-GTA and GPIFN greatly enhance ecological validity in real-world scenarios. Our framework achieves state-of-the-art results on real-world datasets: UMN and Violent-Flows. © 2010-2012 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Multi-agent Simulation for Mass School Shootings

Multi-agent Simulation for Mass School Shootings

引用

2024 IEEE International Conference on Big Data, BigData 2024

作者： Dai, Wei Singh, Yash Pratap Zhang, Rui Purdue University Northwest Department of Computer Science HammondIN United States Purdue University Northwest Department of Electrical and Computer Engineering HammondIN United States

ISBN: (纸本)9798350362480

The increasing frequency of school shootings in the United States has been raised as a critical concern. Active shooters kill innocent students and educators in schools. These incidents highlight the urgent need for effective strategies to minimize casualties. This study aims to address the challenge of simulating and assessing potential mitigation measures by developing a multi-agent simulation model. Our model is designed to estimate casualty rates and evacuation efficiency during active shooter scenarios within school buildings. The simulation evaluates the impact of a gun detection system on safety outcomes. By simulating school shooting incidents with and without this system, we observe a significant improvement in evacuation rates, which increased from 16.6% to 66.6%. Furthermore, the Gun Detection System reduced the average casualty rate from 24.0% to 12.2% within a period of six minutes, based on a simulated environment with 100 students. We conducted a total of 48 simulations across three different floor layouts, varying the number of students and time intervals to assess the system's adaptability. We anticipate that the research will provide a starting point for demonstrating that a gunshot detection system can significantly improve both evacuation rates and casualty reduction. © 2024 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Joint Device and Training Scheduling for Wireless Federated Learning

引用

IEEE Internet of Things Journal 2025年第12期12卷 18806-18819页

作者： Chen, Xiaobing Zhou, Xiangwei Zhang, Hongchao Sun, Mingxuan Zhao, Taibiao Louisiana State University Division of Electrical and Computer Engineering Baton RougeLA70803 United States Louisiana State University Department of Mathematics Baton RougeLA70803 United States Louisiana State University Division of Computer Science and Engineering Baton RougeLA70803 United States

The advent of ubiquitous computing devices in the Internet of Things (IoT) has resulted in an explosion of data. Traditional centralized machine learning models face challenges including limited bandwidth in wireless environments and privacy concerns due to their data aggregation approach. Federated learning addresses these challenges via decentralizing model training across numerous devices, leveraging model updates to enhance privacy and reduce communication overhead. To improve its cost efficiency, current research focuses on minimizing either time or energy costs but rarely both, and does not jointly optimize the parameters of device and training scheduling in the presence of system and data heterogeneity inherent in IoT networks. In our paper, we first introduce a multi-group transmission scheme and propose a comprehensive device scheduling framework, Group Scheduling on Orthogonal Frequency-Division Multiple Access (GS-OFDMA), to address time bottlenecks. Then we formulate a joint optimization problem for device and training scheduling that minimizes the total cost of training while ensuring model convergence. To tackle the resulting mixed integer nonlinear programming problem, we develop an iterative algorithm. Experimental results show that our approach significantly reduces the total cost by at least 35% across various real-world datasets and data distributions in comparison with random participant selection. The proposed GS-OFDMA protocol also exhibits higher time efficiency over other device scheduling schemes. © 2014 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Farmbot: An IoT-Based Wireless Agricultural Robot for Smart Cultivation 26

Farmbot: An IoT-Based Wireless Agricultural Robot for Smart ...

引用

26th International Conference on computer and Information Technology, ICCIT 2023

作者： Kar, Sudipto Mohammad, Ragib Zaman, Meem Tasfia Reza, Sayed Maher Talukder, Ovi Hasan, Mehadi North South University Department of Electrical and Computer Engineering Dhaka Bangladesh Sylhet Engineering College Department of Computer Science and Engineering Sylhet Bangladesh

ISBN: (纸本)9798350359015

Smart technologies have significantly transformed various sectors, and agriculture is no exception. This paper aims to introduce a robot called "Farmbot"to revolutionize traditional farming techniques and enhance crop production. The construction of a radio frequency remote-controlled robot using Arduino microcontrollers and ultrasonic sensors is programmed to navigate by the farmer on the ground. The Farmbot aims to aid farmers by delivering valuable data through a smartphone app on moisture levels, soil's potential of hydrogen, temperature, humidity, and the presence of flammable gasses across distinct farm zones, all through a single set of sensors. It provides comprehensive insights into the overall land condition, enabling informed decisions regarding irrigation, fertilization, and the crucial steps required for optimal growth. To further enhance its utility and application, features such as fertilizer and insecticide dispersion and optional plowing functionality are incorporated into the robot to enhance agricultural efficiency, ensuring optimal crop health and pest control and saving labor. The experimental results will demonstrate the effectiveness of the Farmbot in assisting farmers with irrigation management, fertilization management, and automated farming tasks. © 2023 IEEE.

关键词： agriculture air quality humidity micro-controller moisture radio frequency robot sensors temperature

来源：评论

学校读者我要写书评

暂无评论

Electric Vehicle Charging System Controller Analysis and Synthesis

Electric Vehicle Charging System Controller Analysis and Syn...

引用

2025 IEEE Green Technologies Conference, GreenTech 2025

作者： Perez, Agustin Omar Yilmaz, Muhittin Texas A&M University-Kingsville Electrical Engineering Computer Science Department KingsvilleTX United States

ISBN: (纸本)9798331520182

This research investigates a type of converter and charging system in terms of closed-loop design for a potentially superior charging system for electric vehicle, resulting in better battery life and energy efficiency. A recent rectifier-charging system is analyzed in terms of the controller and given controller types. A baseline with the existing design was implemented and different controller combinations, as part of the proportional-integral-derivative controller, were investigated about their effects on the charging circuit operations and related battery performance levels. Simulation results imply that different controllers result in different output characteristics, and potential controller optimizations, in addition to the circuit operations, are likely to yield superior charging operations. © 2025 IEEE.

关键词： Two term control systems

来源：评论

学校读者我要写书评

暂无评论

Trends in Transfer Learning on Reinforcement Learning for Mobility Control 15

Trends in Transfer Learning on Reinforcement Learning for Mo...

引用

15th International Conference on Information and Communication Technology Convergence, ICTC 2024

作者： Lee, Sungjoon Park, Soohyun Kim, Joongheon Korea University Department of Electrical and Computer Engineering Seoul Korea Republic of Sookmyung Women's University Division of Computer Science Seoul Korea Republic of

ISBN: (纸本)9798350364637

This paper provides an in-depth analysis of recent trends and advancements in applying Transfer Learning (TL) techniques to RL for vehicle control. We particularly focus on applications in autonomous driving and unmanned systems. The integration of TL with RL has demonstrated significant potential in overcoming key challenges such as Sim2Real transfer, multi-agent collaboration, and scalability in real-time applications. © 2024 IEEE.

关键词： Reinforcement learning

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：