检索结果-内蒙古大学图书馆

Wireless Resource Optimization in Hybrid Semantic/Bit Communication Networks

IEEE Transactions on Communications 2025年第5期73卷 3318-3332页

作者： Xia, Le Sun, Yao Niyato, Dusit Zhang, Lan Ali Imran, Muhammad University of Glasgow James Watt School of Engineering GlasgowG12 8QQ United Kingdom Nanyang Technological University College of Computing and Data Science Jurong West 639798 Singapore Clemson University Department of Electrical and Computer Engineering ClemsonSC29634 United States

Recently, semantic communication (SemCom) has shown great potential in significant resource savings and efficient information exchanges, thus naturally introducing a novel and practical cellular network paradigm where two modes of SemCom and conventional bit communication (BitCom) coexist. Nevertheless, the involved wireless resource management becomes rather complicated and challenging, given the unique background knowledge matching and time-consuming semantic coding requirements in SemCom. To this end, this paper jointly investigates user association (UA), mode selection (MS), and bandwidth allocation (BA) problems in a hybrid semantic/bit communication network (HSB-Net). Concretely, we first identify a unified performance metric of message throughput for both SemCom and BitCom links. Next, we specially develop a knowledge matching-aware two-stage tandem packet queuing model and theoretically derive the average packet loss ratio and queuing latency. Combined with practical constraints, we then formulate a joint optimization problem for UA, MS, and BA to maximize the overall message throughput of HSB-Net. Afterward, we propose an optimal resource management strategy by utilizing a Lagrange primal-dual transformation method and a preference list-based heuristic algorithm with polynomial-time complexity. Numerical results not only demonstrate the accuracy of our analytical queuing model, but also validate the performance superiority of our proposed strategy compared with different benchmarks. © 1972-2012 IEEE.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

Gesture and Body Position Control for Lightweight Drones Using Remote Machine Learning Framework 5th

Gesture and Body Position Control for Lightweight Drones U...

引用

5th International Conference on electrical and Electronics engineering, ICEEE 2024

作者： Hayat, Amna Li, Calvin Huan Prakoso, Nicholas Zheng, Renzheng Wyawahare, Amogh Wu, Jerry Department of Electrical and Computer Engineering University of Maryland College ParkMD20742 United States

ISBN: (纸本)9789819791118

This study explores enhancing drone capabilities in low-light environments using gesture and body pose recognition. Deploying a Crazyflie 2.1 drone integrated with sensors and AI modules, we leverage Google’s MediaPipe for real-time gesture detection and pose estimation under different lighting conditions. Compared to other traditional image-based methods, our approach with MediaPipe’s landmark-based models highlighted significant improvements in accuracy and computational efficiency. Results demonstrate that the landmark-based models not only perform robustly across different lighting conditions but also reduce dependency on high-quality images, making them suitable for real-time applications in challenging visual conditions. The use of these models in the drone’s autonomous navigation system shows potential improvements in how it operates and extends their use in important areas like search and rescue, military surveillance, disaster monitoring, and interactive technologies. This paper proves that landmark-based methods are better than traditional image classification, paving the way for more research into smart, responsive unmanned aerial vehicles for important uses including defense and safety. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Empowering Persian LLMs for Instruction Following: A Novel Dataset and Training Approach 1

Empowering Persian LLMs for Instruction Following: A Novel D...

引用

1st Workshop on Language Models for Low-Resource Languages, LoResLM 2025 - co-located at the 31st International Conference on Computational Linguistics, COLING 2025

作者： Mokhtarabadi, Hojjat Zamani, Ziba Maazallahi, Abbas Manshaei, Mohammad Hossein Department of Electrical and Computer Engineering Isfahan University of Technology Iran Department of Computer Engineering Shahid Bahonar University of Kerman Iran Department of Electrical and Computer Engineering University of Tehran Tehran Iran Department of Computer Science Hunter College City University of New York NY United States

ISBN: (纸本)9798891762152

Instruction-tuned large language models have demonstrated remarkable capabilities in following human instructions across various domains. However, their proficiency remains notably deficient in many low-resource languages. To address this challenge, we begin by introducing FarsInstruct: a comprehensive instruction dataset designed to enhance the instruction-following ability of large language models specifically for the Persian language—a significant yet underrepresented language globally. FarsInstruct encompasses a wide range of task types and datasets, each containing a mix of straightforward to complex manual written instructions, as well as translations from the Public Pool of Prompts, ensuring a rich linguistic and cultural representation. Furthermore, we introduce Co-CoLA, a framework designed to enhance the multi-task adaptability of LoRA-tuned models. Through extensive experimental analyses, our study showcases the effectiveness of the FarsInstruct dataset coupled with training by the Co-CoLA framework, in improving the performance of large language models within the Persian context. As of the current writing, FarsInstruct comprises 197 templates across 21 distinct datasets, and we intend to update it consistently, thus augmenting its applicability. © 2025 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Semi-Blind Channel Estimation and Achievable Rate Analysis for Uplink RIS-Enhanced Multi-User Networks

IEEE Open Journal of Vehicular Technology

引用

IEEE Open Journal of Vehicular Technology 2025年 6卷 1108-1139页

作者： Farghaly, Samar I. Ismail, Mohamed I. Fouda, Mostafa M. Alwakeel, Ahmed S. Tanta University Department of Electronics and Electrical Communications Engineering Faculty of Engineering Tanta31111 Egypt Idaho State University Department of Electrical and Computer Engineering College of Science and Engineering PocatelloID83209 United States Modern Academy for Engineering Department of Electronic Engineering and Communication Technology Cairo Governorate 4411602 Egypt Center for Advanced Energy Studies Idaho FallsID83401 United States Suez University Department of Electrical Engineering Faculty of Engineering Suez43221 Egypt

Future wireless networks could benefit from the energy-efficient, low-latency, and scalable deployments that Reconfigurable Intelligent Surfaces (RISs) offer. However, the creation of an effective low overhead channel estimate technique is a major obstacle in RIS-assisted systems, especially given the high number of RIS components and intrinsic hardware constraints. This research examines the uplink of a RIS-empowered multi-user MIMO communication system and presents a novel semi-blind channel estimate approach. Unlike current approaches, which rely on pilot-based channel estimation, our methodology uses data to estimate channels, considerably enhancing the achievable rate. We provide a closed-form deterministic expression for the uplink achievable rate in actual settings where the channel state information (CSI) must be estimated rather than assumed perfect. The results of the simulations show that the formula obtained is accurate, with a close alignment between the deterministic and actual achievable rates (generally between 2 5% deviations). The proposed approach outperforms traditional approaches, resulting in rate increases of up to 35–40%, especially in instances with more RIS elements. These findings illustrate RIS technology's tremendous potential to improve system capacity and coverage, providing useful insights for optimizing RIS adoption in future wireless networks. © 2020 IEEE.

关键词： Channel state information

来源：评论

学校读者我要写书评

暂无评论

Differential-Inspired Fault Protection for Microgrids

Differential-Inspired Fault Protection for Microgrids

引用

2025 IEEE Texas Power and Energy Conference, TPEC 2025

作者： Cisneros-Saldana, Jorge I. Begovic, Miroslav M. Texas A&M University Department of Electrical and Computer Engineering College Station United States

ISBN: (纸本)9798331541125

AC Microgrids are necessarily important for modern power systems, offering reliability, flexibility, and renewable energy integration. Yet, their dual operational modes - grid-connected and autonomous - present challenges for fault detection and protection. This paper proposes a significant harmonic content fault detection approach using high-pass filtering and transient signal analysis, integrated with differential relaying, to accurately detect and classify faults in microgrids. Unlike conventional traveling-wave-based methods relying on electromagnetic wave propagation, the proposed approach leverages high-frequency transient harmonics and a threshold-based process to isolate fault characteristics. A detailed IEEE 4-bus benchmark model in MATLAB/Simulink evaluates the methodology under diverse fault conditions, including grid-connected and islanded modes, inverter-based sources, and dynamic loads. Fault scenarios include short-circuit types such as line-to-line, line-to-ground, and three-phase faults. Results demonstrate the method's speed, accuracy, and low latency. Key contributions include a high-pass filter-based framework tailored for AC microgrids in both operational modes. This differential-inspired innovative protective approach enhances fault detection robustness, adaptability, and real-time implementation, particularly for systems with high DER penetration using Grid-Forming Inverters. By addressing critical challenges in decentralized and inverter-dominated systems, this work advances microgrid protection schemes' reliability and resilience, offering computationally efficient solutions for advanced microgrid operations. © 2025 IEEE.

关键词： Microgrids

来源：评论

学校读者我要写书评

暂无评论

Robust Authentication: Leveraging Hardware Fingerprints and AI to Enhance Security Against Spoofing

引用

IEEE Access 2025年 13卷 86912-86926页

作者： Nimmy, K. Jain, Kurunandan Sachin, S.M. Abekaesh, P.A. Venkitasubramaniam, Parv Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Amritapuri India Amrita Vishwa Vidyapeetham Center for Cybersecurity Systems and Networks Amritapuri India Lehigh University Department of Electrical & Computer Engineering United States

Fingerprint authentication blends biometric precision with user convenience, leveraging unique ridge patterns for fast, reliable, and tamper-resistant identity verification. However, it remains vulnerable to spoofing attacks, where adversaries create synthetic fingerprints using materials like gelatin. To mitigate this, multi-factor authentication (MFA) enhances security by verifying both the fingerprint and the user’s device, restricting access to authorized hardware and complicating attacks. Although Photo Response Non-Uniformity (PRNU) has been explored for device authentication, its reliability diminishes under varying lighting conditions. To address this, we propose an AI-driven approach to generate robust hardware fingerprints from fingerprint scanners, enabling high-accuracy device identification. Our method, trained on 2,000 fingerprint images from 10 scanners, achieves an impressive 98% accuracy in identifying the source scanner. By integrating fingerprint biometrics, hardware fingerprints, and passwords, our novel MFA protocol significantly enhances security against spoofing and forgery attacks. Through security analysis, we demonstrate its effectiveness in preventing unauthorized access. Finally, we validate our authentication framework using an AI-powered binary classifier model, showcasing its practicality for real-world security applications. © 2013 IEEE.

关键词： AI-based classification hardware fingerprint multifactor authentication (MFA) mutual authentication protocol photo-response non-uniformity (PRNU)

来源：评论

学校读者我要写书评

暂无评论

QRAG: Using Learnable Graph Queries for Retrieval Augmented Generation 15

QRAG: Using Learnable Graph Queries for Retrieval Augmented ...

引用

15th IEEE Annual computing and Communication Workshop and Conference, CCWC 2025

作者： Barghi, Alexandria University of Maryland Department of Electrical & Computer Engineering College ParkMD20742 United States

ISBN: (纸本)9798331507695

Retrieval-augmented generation (RAG) is a critical feature of most LLM pipelines, ensuring the model produces precise, up-to-date, and hallucination-free results. However, traditional RAG, which is based on vector similarity, often fails to capture the whole context needed to respond to a user's prompt. This is especially true in 'multi-hop' prompts, where the information needed is in at least one other document that does not match the prompt embedding. Graph-based RAG provides a solution to this problem, but is hindered by the current graph processing ecosystem, and can be complicated to implement. As a response, we introduce QRAG, built on the BitGraph framework, which delivers a scalable, tunable solution for graph-based RAG. QRAG also introduces support for prize-aware graph traversals, which enable faster and more accurate subgraph extraction, possibly eliminating the need for further subgraph refinement. © 2025 IEEE.

关键词： Graph embeddings

来源：评论

学校读者我要写书评

暂无评论

Innovative Video Classification Method based on Deep Learning Approach

引用

Recent Patents on engineering 2025年第2期19卷 95-107页

作者： Hemamalini, V. Jayasutha, D. Vinothini, V.R. Devi, R. Manjula Kumar, A. Anitha, E. Department of Networking and Communications School of Computing SRM Institute of Science and Technology Chennai India Department of Computer Science and Engineering Arjun College of Technology Coimbatore Thamaraikulam India Department of Mathematics Bannari Amman Institute of Technology Sathyamangalam Erode638401 India Department of Computer Science and Design Kongu Engineering College Perundurai Erode638060 India Department of Civil Engineering University Institute of Engineering & Technology Maharshi Dayanand University Rohtak124001 India Department of Artificial Intelligence and Data Science Sri Eshwar College of Engineering Coimbatore641202 India

Background: The automated classification of videos through artificial neural networks is addressed in this work. To explore the concepts and measure the results, the data set UCF101 is used, consisting of video clips taken from YouTube to recognize actions. The study is carried out with the authors' resources to determine the feasibility of independent research in the area. Methods: This work was developed in the Python programming language using the Keras library with Tensorflow as the back-end. The objective is to develop a network that presents performance compatible with the state of the art in terms of classifying videos according to the actions taken. Results: Given the hardware limitations, there is considerable distance between the implementation possibilities in this work and what is known as the state-of-the-art. Conclusion: Throughout the work, some aspects in which this limitation influenced the development are presented, but it is shown that this realization is feasible and that obtaining expressive results is possible 98.6% accuracy is obtained in the UCF101 data set, compared to the 98 percentage points of the best result ever reported, using, however, considerably fewer resources. In addition, the importance of transfer learning in achieving expressive results as well as the different performances of each architecture are reviewed. Thus, this work may open doors to carry patent-based outcomes. © 2025 Bentham Science Publishers.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Extensive Numerical Analysis of PDF Parameters for Wind Energy in Brazil: A Study Across 27 Cities for 60 Years Wind Speed

引用

IEEE Access 2025年 13卷 84555-84568页

作者： Badawi, Ahmed Souza, Amaury Elzein, I.M. Ali, Hassan Zyoud, Alhareth College of Engineering Technology University of Doha for Science and Technology Qatar Federal University of Mato Grosso do Sul Brazil Birzeit University Faculty of Engineering Department of Electrical and Computer Engineering Birzeit Ramallah Palestine

This research conducts a comprehensive numerical assessment of wind energy potential across Brazil, leveraging six decades of wind speed data collected from 27 cities to analyze Probability Density Function (PDF) parameters and enhance wind resource mapping. The study employs the Weibull distribution, defined by its shape factor k and scale factor c, to represent variations in wind speed. A total of nine numerical practices and methods including the Maximum Likelihood Method (MLM), Method of Moments (MM), Empirical Method (EM), Standard Deviation Method (STDM), Modified Maximum Likelihood Method (MMLM), Second Modified Maximum Likelihood Method (SMMLM), Graphical Method (GM), Least Mean Square Method (LSM), and Energy Pattern Factor Method (EPF) were utilized to achieve optimal parameter estimation. Statistical analysis was performed using various metrics such as the Index of Agreement (IA), Root Mean Square Error (RMSE), Chi-square test (X2), Mean Absolute Percentage Error (MAPE), and Relative Root Mean Square Error (RRMSE). The findings indicated that MLM was the most precise method, followed by STDM, EM, MM, and EPF, while GM and LSM demonstrated lower effectiveness. The analysis determined a scale factor range of 2.17-2.36 m/s and a shape factor of 2.5-2.78, resulting in a bell-shaped Gaussian PDF. The Mean Wind Speed (MWS) was recorded at 2.06 m/s, which, despite being categorized as low, indicates the potential for effective deployment of small-scale wind turbines for energy production. This study offers significant insights for wind energy development in Brazil, presenting a methodological approach for optimizing the placement of wind turbines and minimizing electricity generation costs. © 2013 IEEE.

关键词： Weibull distribution

来源：评论

学校读者我要写书评

暂无评论

The NavINST Dataset for Multi-Sensor Autonomous Navigation

引用

IEEE Access 2025年 13卷 84659-84674页

作者： Araujo, Paulo Ricardo Marques De Mounier, Eslam Bader, Qamar Dawson, Emma Kaoud Abdelaziz, Shaza I. Zekry, Ahmed Elhabiby, Mohamed Noureldin, Aboelmagd Queen’s University Department of Electrical and Computer Engineering KingstonON Canada Ain Shams University Cairo Egypt Micro Engineering Tech. Inc CalgaryAB Canada Royal Military College of Canada Department of Electrical and Computer Engineering KingstonON Canada

The Navigation and Instrumentation (NavINST) Laboratory has developed a comprehensive multisensory dataset from various road-test trajectories in urban environments, featuring diverse lighting conditions, including indoor garage scenarios with dense 3D maps. This dataset includes multiple commercial-grade IMUs and a high-end tactical-grade IMU. Additionally, it contains a wide array of perception-based sensors, such as a solid-state LiDAR—making it one of the first datasets to do so—a mechanical LiDAR, four electronically scanning RADARs, a monocular camera, and two stereo cameras. The dataset also includes forward speed measurements derived from the vehicle’s odometer, along with accurately post-processed high-end GNSS/IMU data, providing precise ground truth positioning and navigation information. The NavINST dataset is designed to support advanced research in high-precision positioning, navigation, mapping, computer vision, and multisensory fusion. It offers rich, multi-sensor data ideal for developing and validating robust algorithms for autonomous vehicles. Finally, it is fully integrated with the robot operating system (ROS), ensuring ease of use and accessibility for the research community. © 2013 IEEE.

关键词： Robot Operating System

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：