检索结果-内蒙古大学图书馆

54th IEEE Frontiers in Education Conference, FIE 2024

作者： Reynolds, Sarah Ochoa, Omar Towhidnejad, Massood Pembridge, James J. Babiceanu, Radu Embry-Riddle Aeronautical University Department of Electrical Engineering and Computer Science Daytona Beach United States Embry-Riddle Aeronautical University Daytona Beach United States

ISBN: (纸本)9798350351507

This innovative practice full paper describes the integration of Ph.D. students into departmental operations using Agile approaches, i.e., Serum, Serum is an agile framework originally developed for managing software development projects, but in recent years has been adapted into a framework used in classroom experiences and a management technique for non-engineering project-based work. In this work, Serum was adapted at the department operations level to enhance the efficacy of department projects and processes. A Ph.D. student acted as the Scrum Master for one of the teams. This provided the Ph.D. student with a unique experiential learning opportunity to apply theoretical knowledge in a practical setting, significantly enhancing their learning experience. The benefits for the Ph.D. student included the development of soft skills that made them a more well-rounded Ph.D. student and the creation of meaningful relationships with the faculty members on their team which increased their sense of belonging within the department. Additionally, the Ph.D. student gained insight into the intricacies of university operations, which is valuable training for a student who seeks a career in academia. This paper aligns with a desire to improve the experience of engineering and computing education of graduate students outside of the typical classroom and research domains. © 2024 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Resilient, Federated Large Language Models over Wireless Networks: Why the PHY Matters

Resilient, Federated Large Language Models over Wireless Net...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Andrei, Vlad C. Djuhera, Aladin Li, Xinyang Mönich, Ullrich J. Saad, Walid Boche, Holger Virginia Tech Electrical and Computer Engineering Department ArlingtonVA United States Technical University of Munich Munich Germany Munich Center for Quantum Science and Technology Germany

ISBN: (纸本)9798350351255

In this paper, the problem of training large language models (LLMs) in split federated learning over real-world wireless networks is investigated. In the considered system, the embedding layers of an LLM are first computed at a client and then trans-mitted over a wireless MIMO-OFDM link to a server instance for further processing, continuing the forward- and initiating the backpropagation of the training to the originating client. Due to channel impairments and adversarial attacks, the server needs to compute the model losses and gradients using corrupted parameters such as embeddings in LLMs. The computation of the corresponding model losses is rigorously characterized using such perturbed embeddings and a direct connection to the communication mean-squared error (MSE) for models beyond simple neural networks is established. Subsequently, the communication errors are modeled as part of the training process, and a method to design beamforming, scheduling and power allocation is proposed, ensuring high task performance and model convergence even in the case of worst-case jamming. Results on two natural language processing tasks using different LLM architectures confirm the validity of the theoretical analysis and prove the effectiveness of the proposed wireless system design in terms of accuracy and F1 score. © 2024 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

FedCal: Achieving Local and Global Calibration in Federated Learning via Aggregated Parameterized Scaler 41

FedCal: Achieving Local and Global Calibration in Federated ...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Peng, Hongyi Yu, Han Tang, Xiaoli Li, Xiaoxiao College of Computing and Data Science Nanyang Technological University Singapore Department of Electrical and Computer Engineering The University of British Columbia VancouverBC Canada Vector Institute Canada

Federated learning (FL) enables collaborative machine learning across distributed data owners. However, this approach poses a significant challenge for model calibration due to data heterogeneity. While prior work focused on improving accuracy for non-iid data, calibration remains under-explored. This study reveals existing FL aggregation approaches lead to sub-optimal calibration, and theoretical analysis shows despite constraining variance in clients' label distributions, global calibration error is still asymptotically lower bounded. To address this, we propose a novel Federated Calibration (FedCal) approach, emphasizing both local and global calibration. It leverages client-specific scalers for local calibration to effectively correct output misalignment without sacrificing prediction accuracy. These scalers are then aggregated via weight averaging to generate a global scaler, minimizing the global calibration error. Extensive experiments demonstrate that FedCal significantly outperforms the best-performing baseline, reducing global calibration error by 47.66% on average. Copyright 2024 by the author(s)

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A Local Time-Stepping Discontinuous Galerkin Time-Domain Scheme for Simulation of Electromagnetic Problems Involving Resistive Boundary Condition

A Local Time-Stepping Discontinuous Galerkin Time-Domain Sch...

引用

USNC-URSI Radio science Meeting (Joint with AP-S Symposium)

作者： Ruitao Sun Ming Dong Liang Chen Hakan Bagci Electrical and Computer Engineering (ECE) Program Computer Electrical and Mathematical Science and Engineering (CEMSE) Division King Abdullah University of Science and Technology (KAUST) Thuwal Saudi Arabia

ISBN: (数字)9789463968119

ISBN: (纸本)9798350359497

Thin layers with high conductivity values, such as metal sheets, conductive paint, graphene, and other two-dimensional (2D) materials, are commonly used in various electromagnetic applications. One of the fundamental challenges in numerical modeling of these thin conductive layers is the requirement for an extremely fine mesh that can accurately capture field variations and account for the intricate geometrical features of the structure (H. Chen, A. J. Taylor and N. Yu, Rep. Prog. Phy., 79,10-35,2016). A dense mesh translates into high computational cost since the number of unknowns is increased and the time step size must be reduced for an explicit time marching scheme (to ensure that the Courant-Friedrichs-Lewy (CFL) condition is satisfied). One can replace the thin conductive layer with an infinitesimally thin sheet on which the resistive boundary condition (RBC) is enforced (T. B. A. Senior and J. L. Volakis, London, UK: IET, 1995). This approach completely avoids the dense mesh and the high computational cost that comes with it. However, RBC has to be incorporated into the electromagnetic solver.

关键词： Two-dimensional displays Graphene Metals Boundary conditions Computational efficiency Numerical models Electromagnetics

来源：评论

学校读者我要写书评

暂无评论

Designing an Advanced Situational Awareness Platform Using Intelligent Multi-Drones for Smart Farming Towards Agriculture 5.0 11

Designing an Advanced Situational Awareness Platform Using I...

引用

11th International Conference on ICT for Smart Society, ICISS 2024

作者： Hermanus, Davy Ronald Supangkat, Suhono Harso Hidayat, Fadhil Bina Nusantara University Research Interest Group in Educational Technology Computer Science Department Indonesia School of Electrical Engineering and Informatics Institut Teknologi Bandung Bandung Indonesia

ISBN: (纸本)9798350389654

With regard to Agriculture 5.0, the goal of this research is to create an intelligent platform for multi-drone collaboration that will improve situational awareness. This study examines the crucial phases in the Sensing, Understanding, and Action processes by fusing cutting-edge drone technology with creative coordination methods. Creating the architecture and foundation for drone collaboration, utilizing artificial intelligence for real-time data processing, and creating user interfaces that work are all part of the study technique. Area coverage, data quality, processing speed, and decision-making effectiveness are some of the performance evaluation measures. The goal of the research is to identify strategies for enhancing large-scale farming methods' resource management and operational effectiveness. The results will greatly enhance Agriculture 5.0 technologies and create avenues for the deployment of multi-drone collaboration platforms in a variety of high-situational awareness businesses. © 2024 IEEE.

关键词： Data quality

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Impact of Security Measures on Wi-Fi Quality of Service 2

Analyzing the Impact of Security Measures on Wi-Fi Quality o...

引用

2nd International Conference on Artificial Intelligence, Blockchain, and Internet of Things, AIBThings 2024

作者： Kopcho, Thomas J. Fouda, Mostafa M. Krome, Cameron J. Quach, Anna T. Olaveson, Israel G. Idaho State University Department of Computer Science PocatelloID United States Idaho State University Department of Electrical and Computer Engineering PocatelloID United States Ai Data & Visualization Idaho National Laboratory Idaho FallsID United States

ISBN: (纸本)9798331529529

This study examines the relationship between Quality of Service (QoS) and security in Wi-Fi networks. Using a detailed dataset consisting of QoS metrics of file transfers under various security configurations, we analyze the impact of these settings on network performance. Our findings provide a quantification to accurately show that different encryption protocols, such as TKIP and CCMP, significantly affect QoS, with disabling security generally improving performance. The study provides a framework for optimizing security settings to enhance both security and QoS in future wireless networks. © 2024 IEEE.

关键词： Wireless local area networks (WLAN)

来源：评论

学校读者我要写书评

暂无评论

An adaptive observer-based SOC estimation method for lithium-ion batteries against sensor measurement uncertainties 38

An adaptive observer-based SOC estimation method for lithium...

引用

38th Youth Academic Annual Conference of Chinese Association of Automation, YAC 2023

作者： Xu, Xiaoyi Luo, Hao Chow, Mo-Yuen Huang, Cong-Sheng Jiang, Yuchen Harbin Institute of Technology Department of Control Science and Engineering Harbin China North Carolina State University Department of Electrical and Computer Engineering RaleighNC United States

ISBN: (纸本)9798350303636

Accurate estimation of battery state of charge (SOC) is critical for efficient and safe battery applications. The measurement uncertainties of sensors, including measurement noises and sensor bias will affect the estimation accuracy inevitably. Therefore, quantifying the relationship between the sensor measurement uncertainties and the SOC estimation errors and seeking better SOC estimation methods has been a hot topic of research. In this paper, model errors and SOC estimation errors under measurement noise and sensor bias are derived. The resulting analyses can be used to assess the robustness of the SOC estimates. In addition, an adaptive observer-based SOC estimation method for lithium-ion batteries is proposed to cope with the measurement uncertainty. Simulation experiments demonstrate the effectiveness of the proposed method. © 2023 IEEE.

关键词： adaptive observer lithium-ion battery sensor bias sensor noises State-of-Charge (SOC) estimation

来源：评论

学校读者我要写书评

暂无评论

Building Bridges: A Holistic Approach to Web Development Education Through Community Engaged Learning and Social Justice Initiatives

Building Bridges: A Holistic Approach to Web Development Edu...

引用

Frontiers in Education (FIE) Conference

作者： Amalia Rusu Adrian Rusu Aarushi Vijay Department of Computer Science and Engineering Fairfield University Fairfield USA Department of Electrical & Computer Engineering and Computer Science University of New Haven New Haven USA

ISBN: (数字)9798350351507

ISBN: (纸本)9798350363067

This innovative practice full paper describes an innovative pedagogical framework that integrates community engaged learning and social justice principles into a traditional web development course, fostering a holistic approach to education that goes beyond programming languages and algorithms, and aiming to redefine the educational landscape by encouraging socially responsible and community-driven web development practices. The community engaged learning component of the course is structured around partnerships with local non-profit organizations, community groups, or socially impactful initiatives. Through these partnerships, students engaged in real-world projects, applying their technical expertise to develop impactful solutions that contribute to social justice causes. The web development course framework is presented and sample projects are provided with student and community partner reflections and benefits. We explored the effect of the community engaged learning and social justice initiatives on technical proficiency, critical thinking, teamwork, and ethical reasoning. Results indicate a positive correlation between community engaged learning experiences and increased student motivation, teamwork, and a heightened awareness of the societal implications of their work. Furthermore, the paper discusses the challenges encountered during the implementation process and proposes strategies for overcoming potential barriers. The findings of this research contribute to the ongoing discourse on the evolution of computer science and engineering education, advocating for a holistic approach that not only equips students with technical skills but also instills a sense of social responsibility.

关键词： computer science Ethics computer languages Correlation Buildings Organizations Reflection Cognition Teamwork engineering education

来源：评论

学校读者我要写书评

暂无评论

Internet of Things routing protocol with mobility awareness and energy efficiency 3

Internet of Things routing protocol with mobility awareness ...

引用

3rd International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2023

作者： Chauhan, Birendra Kumar Banupriya, M. Venkatagurunatham, K. Sungheetha, Akey Kumari, Ch D V P Karthick, L. Iimt University School of Basic Sciences and Technology Uttar Pradesh Meerut250001 India Hindustan Institute of Technology Department of Computer Science and Engineering Coimbatore India Andhrapradesh Guntur522019 India Adama Science and Technology University School of Electrical Engineering and Computing Department of Computer Science and Engineering Nazareth1888 Ethiopia Aditya College of Engineering Department of Computer Science and Engineering Andhra Pradesh Surampalem533437 India Hindusthan College of Engineering and Technology Department of Mechanical Engineering Coimbatore641032 India

ISBN: (纸本)9798350399264

Internet of things enabled devices are considered one of the technologies for the future and at the same time, the mass use of IoT devices has revolutionised the way of using modern technology. Hence, with the mass implication creating energy-efficient systems without compromising on the data ratio has become mandatory. Thus, the study collected secondary data and conducted a thematic analysis. Such methods of study have emperors the researchers to collect reliable data and with the discussion create a reliable result. For a better understanding, this study has discussed bout different kinds of routing and helps o create an energy-efficient system with better mobility. The discussion is based on different bandwidths of data along with their use at the same time problem of the system is mentioned at the end. Such a critical discussion allows a reader to prepare their own opinion about a system creation which have an energy-efficient topology and that has improved data packet ratio. © 2023 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

An Enhancement of Object Detection Using YOLO V8 and Mobile Net in Challenging Conditions

引用

SN computer science 2025年第4期6卷 1-20页

作者： Pasupuleti, Shailaja Ramalakshmi, K. Gunasekaran, Hemalatha Arokiaraj, Rex Macedo Debnath, Saswati Jebaseeli, T. Jemima Department of Computer Science and Engineering Alliance University Karnataka Anekal Bangalore India AU-Centre of Excellence Department of Computer Vision Alliance University Karnataka Anekal Bangalore India College of Computing and Information Sciences University of Technology and Applied Sciences Ibri Oman Department of Information Technology College of Computing and Information Sciences University of Technology and Applied Sciences Ibri Oman Department of Computer Science and Engineering Alliance University Karnataka Bangalore India Division of Artificial Intelligence and Machine Learning Karunya Institute of Technology and Sciences Coimbatore India

Autonomous drones and deep learning neural networks are becoming popular tools to revolutionize aircraft operations by partially automating visual inspection processes in aircraft maintenance. The research aims to provide a trustworthy method for locating and classifying surface flaws on aircraft, such as dents, fractures, corrosion, and a few other anomalies. To assess the model performance with and without a lightweight network integration, the implementation merges YOLOv8 and Mobile Net architectures, using dropout regularization and data augmentation approaches. To guarantee the model's performance in low-light situations, the dataset has been carefully selected to contain images replicating such settings. Annotation, environment setup, model training, and online dataset scraping are all covered by the thorough technique. A web-scraped dataset is used to train and validate two popular semantic segmentation algorithms, YOLOv8 and Mobile Net, which show enough performance for segmenting and grading aircraft surface problems in practical settings. The results show that precision and recall values are improved using a hybrid technique that ensembles trained Mobile Net and YOLOv8 models. Using COCO metrics, in the proposed approach an assessment of Ensemble WBF, Mobile Net-YOLO, and YOLOv8 outcomes on test and validation sets, guaranteed reliable object recognition and classification abilities. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Aircraft Classification Mobile-Net Object detection Weighted Box Fusion YOLOv8

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：