检索结果-内蒙古大学图书馆

IEEE International Conference on Communications (ICC)

作者： Haoming Ma Xiaojun Yuan Zhi Ding The National Key Lab. of Sci. and Tech. on Commun. Uni. of Electronic Sci. and Tech. of China Chengdu China Department of Electrical and Computer Engineering University of California at Davis Davis United States

ISBN: (数字)9781728190549

ISBN: (纸本)9781728190556

To address limited server coverage in traditional over-the-air federated learning (OA-FL), we introduce the framework of multiple input multiple output (MIMO) cloud radio access network (Cloud-RAN) OA-FL (MIMOCROF). This framework involves a two-step model aggregation method in each training round. Firstly, each base station (BS) aggregates the local updates from its served devices, resulting in an edge update. Secondly, the cloud server (CS) aggregates the edge updates from the BSs. By modeling the second step as a lossy distributed source coding (L-DSC) process, we analyze the performance of MIMOCROF from the perspective of rate-distortion theory, resulting in a unified communication-learning design approach. In the proposed design, we jointly optimize rate resources and beamforming vectors, thereby leveraging the correlation inherent in FL to achieve performance gains. Numerical results show that, by solving the optimization problem, MIMOCROF performs comparably to the error-free bound and significantly outperforms other benchmark schemes.

关键词： Training Federated learning Wireless networks Source coding Aggregates Rate-distortion Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Balancing Human-robot Collaborative Disassembly Line by Using Dingo Optimization Algorithm

Balancing Human-robot Collaborative Disassembly Line by Usin...

引用

IEEE International Conference on Human-Machine Systems

作者： Xiwang Guo Liangbo Zhou Mengchu Zhou Weitian Wang Jiacun Wang Liang Qi Information and Control Engineering Liaoning Petrochemical University Fushun China Information and Control Liaoning Petrochemical University Fushun China Electrical and Computer Engineering New Jersey Institute of Technology Newark NJ USA School of Computing Montclair State University Montclair USA Computer Science and Software Eng. Monmouth University West Long Branch NJ USA Computer Intelligent Sci. and Tech. Shandong University of Sci. and Tech. Qingdao China

ISBN: (数字)9798350315790

ISBN: (纸本)9798350315806

Disassembling and recycling scrapped products play important roles in effectively reducing environmental pollution and improving resource sustainability. A multi-product human-robot collaborative disassembly-line-balancing problem (MHDP) arises from doing so and represents an important yet to be solved in the remanufacturing field. This work explores how to use optimization algorithms to schedule tasks between humans and robots to maximize remanufacturing profit in human-robot collaboration contexts. Specifically, we investigate MHDP and develop a mixed integer programming model considering various system constraints. We propose a dingo optimization algorithm that simulates wild dogs’ social hierarchy and chasing processes to solve MHDP. We compare the proposed algorithm with an exact solution finder, i.e., IBM CPLEX and a well-known intelligent optimization method, i.e., Genetic Algorithm to show its competitive performance in terms of solution accuracy and efficiency.

关键词： Integer programming Schedules Pollution Human-machine systems Collaboration Optimization methods Recycling

来源：评论

学校读者我要写书评

暂无评论

Demystifying Knitr Package: Essential Recipes and Easy Steps for Adding Knit-Engines in R 12

Demystifying Knitr Package: Essential Recipes and Easy Steps...

引用

12th International Symposium on Digital Forensics and Security, ISDFS 2024

作者： Mati, Sagiru Civcir, Irfan Danbatta, Salim Jibrin Varol, Asaf Nasab, Ahad Muhammad, Ahmad Abba, Sani Isa Operational Research Centre in Healthcare Near East University Nicosia99138 Turkey Yusuf Maitama University Department of Economics Kano Nigeria Ankara University Department of Economics Ankara Turkey Uskudar University Software Engineering Department Istanbul Turkey College of Engineering and Comp. Sci. The University of Tennessee at Chattanooga Dept. of Engineering Mgmt. & Tech ChattanoogaTN United States College of Arts and Sciences Qatar University Department. of Physics and Materials Sciences Doha Qatar Interdisciplinary Research Centre for Membrane and Water Security King Fahd University of Petroleum and Minerals Dhahran Saudi Arabia

ISBN: (纸本)9798350330366

The knitr package provides an avenue for incorporating programming languages and statistical applications into R Markdown and Quarto document for the sake of reproducibility. However, deep technical knowledge of R programming is required to achieve this task. In addition to this, the existing literature does not provide a guide on how to add econometric/statistical programs such as EViews, gretl, and Dynare. This paper develops and explains four easy steps for adding econometric/statistical applications by taking into account their peculiarities. The recipes provided in this paper can be useful in enhancing the reproducibility, accuracy, and reliability of econometric/statistical computations. The recipes can also be used in cooking new knit-engines or modifying the existing ones. © 2024 IEEE.

关键词： Engines

来源：评论

学校读者我要写书评

暂无评论

AI-based Approach for Radio Frequency Jamming Attack Detection in Unmanned Aerial Vehicles

AI-based Approach for Radio Frequency Jamming Attack Detecti...

引用

Asia-Pacific Conference on Communications

作者： Jetani Harshil Harikrushna Goti Nikunjkumar Mahida Rajesh Gupta Sudeep Tanwar Geetika Bhardwaj N.Z Jhanjhi Sayan Kumar Ray Department of Comp. Sci. & Engg Institute of Technology Nirma University Ahmedabad India Department of Comp. Sci. & Engg Guru Nanak Dev Engineering College Ludhiana Punjab India School of Computer Science Taylor’s University Subang Jaya Malaysia

ISBN: (数字)9798331517816

ISBN: (纸本)9798331517823

Unmanned Aerial Vehicles (UAV) are highly versatile systems with applications expanding in various fields, for instance, Surveillance, Reconnaissance, Disaster Response, Agriculture, and many more. Although UAVs have many important advantages over conventional manned aircraft, such as cheaper operating costs and a lower risk for human pilots, their vulnerability to Radio Frequency (RF)-jamming poses a substantial risk to navigation and communication systems by disrupting signals. UAVs depend on remote control and autonomous operations. These attacks are concerning in many application areas. Communication and navigation play crucial roles in these autonomous systems. This paper aims to explore different deep-learning algorithms for the detection of RF-jamming attacks in UAVs. A comparison analysis is conducted to evaluate five distinct architectures using conventional evaluation metrics criteria comprising accuracy, precision, recall, confusion matrices, and the area under the ROC curve. These comparative analyses helped in selecting an accurate architecture for the definition, RNN architecture gave an impressive accuracy of 93% and demonstrated a superior performance than other architectures. This paper aims to strengthen RF-jamming detection systems in UAVs to enhance their safety and operational reliability in several scenarios.

关键词： Training Resistance Analytical models Accuracy Surveillance Radio navigation Autonomous aerial vehicles Data models Aircraft navigation Jamming

来源：评论

学校读者我要写书评

暂无评论

Metaphor Detection with Additional Auxiliary Context

Metaphor Detection with Additional Auxiliary Context

引用

IIAI International Conference on Advanced Applied Informatics (IIAIAAI)

作者： Takuya Hayashi Minoru Sasaki Major in Computer and Information Sciences Graduate School of Sci. and Eng. Ibaraki Univ. Hitachi Japan Department of Computer and Information Sciences College of Engineering Ibaraki Univ. Hitachi Japan

ISBN: (数字)9798350377903

ISBN: (纸本)9798350377910

‘Metaphor detection’ refers to the detection of figurative expressions and metaphors in sentences and text data. Metaphor expressions are expressions that cannot be interpreted literally and their meaning needs to be inferred. Traditionally, linguistic features such as word classes have been used as input for specific machine learning models to infer Metaphor content. In previous studies, detection has been performed on a single input sentence, which has the problem that the context before and after the sentence cannot be properly captured. Therefore, in order to perform effective Metaphor detection for sentences with little context information, this study proposes a method to generate and add sentences that complement the context using ChatGPT. Using this method, we compared the predictions made by the Metaphor detection model for both the dataset to which the complementary sentences were added and the original dataset. The results show that adding supplementary context to the dataset improves the accuracy of Metaphor detection.

关键词： Accuracy Machine learning Predictive models Linguistics Chatbots Informatics

来源：评论

学校读者我要写书评

暂无评论

Utilizing RL and Web-Enhanced Commuting for Traffic Congestion Mitigation and Public Transportation Enhancement

Utilizing RL and Web-Enhanced Commuting for Traffic Congesti...

引用

International conference of Electronics, Communication and Aerospace Technology (ICECA)

作者： Jenefa A Jerusha Miraclin Dulcie B Carolin Joanna Sheryl K Esswari S Sandra Jeslena W Bessy M Kuriakose Division of CSE Karunya Institute of Tech. and Sci. Coimbatore India Department of Computer Science and Engineering Malla Reddy Engineering College for Women India

In the face of escalating urban traffic congestion and inadequate public transportation efficiency, this study introduces a pioneering solution by merging Reinforcement Learning (RL) with web-enhanced commuting strategies. The central goal is to create a real-time adaptive system capable of optimizing traffic control and enhancing public transit management. The urgency of the problem lies in the elongated commute times and ecological ramifications caused by congested roads, underscoring the necessity for innovative and sustainable urban mobility solutions. Through the innovative combination of RL techniques and web-enhanced approaches, the study proposes a dynamic framework that can potentially alleviate congestion and augment public transportation efficiency through on-the-fly adjustments. Preliminary experimental results highlight encouraging advancements in both traffic flow management and public transportation efficiency, affirming the efficacy of the RL-augmented system. This integration of cutting-edge technology and commuter-focused strategies presents an avenue for reshaping urban mobility paradigms, mitigating traffic congestion, and optimizing public transportation systems, thereby paving the way for a more sustainable urban future.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Channel Attention HalfU-Net for Skin Lesion Segmentation

Channel Attention HalfU-Net for Skin Lesion Segmentation

引用

Advanced engineering and Technologies (ICONNIC), International Conference on

作者： Heri Prasetyo Abid Ammar Mahdy Abrar Dwi Fairuz Nadhif Jing-Ming Guo Chih-Hsien Hsia Department of Informatics Universitas Sebelas Maret (UNS) Surakarta Indonesia Department of Electrical Engineering National Taiwan Univ. Sci. Technolgy Taipei Taiwan Dept. Computer Sci. Infor. Engineering National Ilan University Yilan Taiwan

U-shaped architecture have gain popularity in the image segmentation task, especially for biomedical image. Regardless of its good performance, U-shaped architecture generally has huge number of parameters. Considering the resource constraint in actual medical environment, the needs lightweight model is essential. In order to overcome this problem, we propose Channel Attention HalfU-Net. The proposed method implement the existing medical image segmentation model named HalfU-Net. HalfU-Net can reduce the computational cost by simplify the decoder part of the UNet. Channel attention is assigned between ghost model for every stage in encoder part to capture more relevant feature. This leads to performance improvement in skin lesion segmentation problem. Despite that our model achieve state-ofthe-arts performance by surpassing U-Net in aspects of DSC and IoU metrics by 0.86% and 3.48% respectively, the number of parameter of our proposed method is more than 200 times less then U-Net.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Load Frequency Control Strategies: PID, Fuzzy Logic, and Model Predictive Control (MPC) 4

Comparative Analysis of Load Frequency Control Strategies: P...

引用

4th IEEE International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2024

作者： Pal, Ritu Sati, Madan Mohan Pal, Tarun Singh, Akhilesh Vijay, Sandip Goyal, Shweta Tula's Institute Deptt. of Computer Sci. & Engg. Dehradun India Graphic Era Hill University Deptt. of Mathematics Bhimtal263136 India Shoolini University Faculty of Applied Sciences & Biotechnology Himachal Pardesh 173229 India Uttarakhand Technical University Campus Institute Department of Electrical Engineering Pithoragarh India Tula's Institute Department of Ece & Eee Dehradun India Graphic Era Deemed to Be University Department of Electrical Engineering Dehradun248002 India

ISBN: (纸本)9798350360165

An effective power system operation must have load frequency control abilities. An essential part of the system is a reliable power source and a stable system. We need to keep the production and consumption of energy under check if we want to reach this goal. There is an in-depth analysis and review of twoarea power system Load Frequency Control (LFC) methods offered. Fuzzy control, PID, and MPC were among the many methods we explored. Determine which of the three choices is optimal;that is the goal of this assignment. Many factors are considered when assessing a control plan. It is crucial to consider about the transient reaction. Among the most important considerations are complex processing, robustness, and steadystate error. We may evaluate several control methods for a multiarea power grid and how well they handle demand fluctuations using MATLAB/Simulink models. © 2024 IEEE.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

A non linear system controlling by using artificial neural network

A non linear system controlling by using artificial neural n...

引用

2024 IEEE International Conference on Communication, Computing and Signal Processing, IICCCS 2024

作者： Vidyarthi, Vrij Mohan Manu, Mehul Pundhir, Shivali Prajapati, Meenu Kharayat, Pushpendra Singh Rayal, Ashish Tula's Institute Department of Eee U.K. Dehradun India Graphic Era Hill University Dept of Allied Sciences India Tula's Institute Deptt. of Computer Sci. & Engg. U.K. Dehradun India Uttaranchal University School of Applied and Life Sciences Department of Mathematics Dehradun248007 India Graphic Era Deemed to be University Department of Electrical Engineering Dehradun248002 India

ISBN: (纸本)9798350390759

This article describes using artificial neural networks (ANNs) to control nonlinear systems. A third-order function is used to represent the nonlinear system. Using back propagation delay, the ANN has been utilized to train the nonlinear system's unknown variable. The fact that the non-linear system is non-converging indicates that it is an unstable, non-bounded system. Enhancement of the performance parameters is possible if the third-order system's objective function incorporates the limitations limits. ANN is used to train the third order non-linear system with restrictions. The nonlinear system is rapidly convergent to a bounded value in the stable area following the use of ANN. © 2024 IEEE.

关键词： ANN Bounded Converge Nonlinear Third order

来源：评论

学校读者我要写书评

暂无评论

Perspective Transition of Large Language Models for Solving Subjective Tasks

arXiv

引用

arXiv 2025年

作者： Wang, Xiaolong Zhang, Yuanchi Wang, Ziyue Xu, Yuzhuang Luo, Fuwen Wang, Yile Li, Peng Liu, Yang Dept. of Comp. Sci. & Tech. Institute for AI Tsinghua University Beijing China Tsinghua University Beijing China Gansu China Harbin Institute of Technology Harbin China College of Computer Science and Software Engineering Shenzhen University Shenzhen China

Large language models (LLMs) have revolutionized the field of natural language processing, enabling remarkable progress in various tasks. Different from objective tasks such as commonsense reasoning and arithmetic question-answering, the performance of LLMs on subjective tasks is still limited, where the perspective on the specific problem plays crucial roles for better interpreting the context and giving proper response. For example, in certain scenarios, LLMs may perform better when answering from an expert role perspective, potentially eliciting their relevant domain knowledge. In contrast, in some scenarios, LLMs may provide more accurate responses when answering from a third-person standpoint, enabling a more comprehensive understanding of the problem and potentially mitigating inherent biases. In this paper, we propose Reasoning through Perspective Transition (RPT), a method based on in-context learning that enables LLMs to dynamically select among direct, role, and third-person perspectives for the best way to solve corresponding subjective problem. Through extensive experiments on totally 12 subjective tasks by using both closed-source and open-source LLMs including GPT-4, GPT-3.5, Llama-3, and Qwen-2, our method outperforms widely used single fixed perspective based methods such as chain-of-thought prompting and expert prompting, highlights the intricate ways that LLMs can adapt their perspectives to provide nuanced and contextually appropriate responses for different problems. © 2025, CC BY.

关键词： Open systems

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：