检索结果-内蒙古大学图书馆

A Comprehensive Survey on Intelligent Reflecting Surfaces and Unmanned Aerial Vehicles Integration for Enhanced Communication in Massive Networks 11

A Comprehensive Survey on Intelligent Reflecting Surfaces an...

引用

11th International Conference on Mechatronics and Robotics Engineering, ICMRE 2025

作者： Attar, Hani Ababneh, Jafar Hafez, Mohamed Rachini, Ali Solyman, Ahmed Bahy, Ramy M. Zarqa University Faculty of Engineering Zarqa Jordan College of Engineering University of Business and Technology Jeddah21448 Saudi Arabia Zarqa University Faculty of Information Technology Cyber Security Department Zarqa Jordan INTI-IU-University Nilai Faculty of Engineering Feqs Malaysia Department of Computer Science and Information Technology Jounieh Lebanon School of Computing Engineering and Built Environment Glasgow Caledonian University Glasgow United Kingdom Technical Research Center Cairo Egypt

ISBN: (纸本)9798331509293

Intelligent Reflecting Surfaces (IRSs) offer a revolutionary approach to wireless communication by dynamically controlling the properties of electromagnetic waves. By manipulating wavefronts without requiring radio frequency links, IRSs can enhance spectrum and energy efficiency, reduce costs, and improve overall system performance. Unmanned Aerial Vehicles (UAVs) have garnered significant attention due to their mobility and adaptability. However, real-time data transmission between UAVs can be hindered by obstacles and security risks. By combining IRSs and UAVs, we can create unparalleled opportunities in demanding environments. Through coordinated movements and intelligent wave reflection, both systems can optimize wireless signal propagation. This paper provides a comprehensive review of IRS-assisted UAV communications. We explore existing research, introduce novel technologies and applications, and highlight potential research directions for developing low-cost and energy-efficient wireless systems. Additionally, we address current challenges and outline promising areas for future study. © 2025 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Back to the Future: Challenges of Sparse and Irregular Medical Image Time Series

Back to the Future: Challenges of Sparse and Irregular M...

引用

Workshop on Longitudinal Disease Tracking and Modeling with Medical Images and Data, LDTM 2024, 5th International Workshop on Multiscale Multimodal Medical Imaging, MMMI 2024, 1st Workshop on Machine Learning for Multimodal/-sensor Healthcare Data, ML4MHD2024 and Workshop on Multimodal Learning and Fusion Across Scales for Clinical Decision Support, ML-CDS 2024 held in conjunction with the 27th International Conference on Medical Image computing and computer Assisted Intervention, MICCAI 2024

作者： Disch, Nico Albert Peretzke, Robin Roy, Saikat Ulrich, Constantin Zimmerer, David Stiefelhagen, Rainer Kleesiek, Jens Maier-Hein, Klaus Division of Medical Image Computing German Cancer Research Center Heidelberg Germany HIDSS4Health - Helmholtz Information and Data Science School for Health Karlsruhe Heidelberg Germany Faculty of Mathematics and Computer Science University of Heidelberg Heidelberg Germany Pattern Analysis and Learning Group Department of Radiation Oncology Heidelberg University Hospital Heidelberg Germany Karlsruhe Institute of Technology Karlsruhe Germany University Hospital Essen Essen Germany University Hospital Essen West German Cancer Center Essen Essen Germany Medical Faculty Heidelberg University of Heidelberg Heidelberg Germany

ISBN: (纸本)9783031845246

In longitudinal medical image analysis, most work focuses on regularly sampled images, or on tasks like regression or classification. However, in the clinical context, images are frequently generated irregularly due to factors such as cost constraints. This work tackles the problem of irregularly sampled longitudinal medical imaging by evaluating methods in segmentation and reconstruction tasks. We examine the reconstruction for real-life MRI from patients with Alzheimer’s Disease (AD), where the model predicts future MRI scans from an arbitrary number of input images sampled at irregular intervals. However, experiments show that most models cannot surpass the performance of using an image from the same patient at a different time point as a baseline. Therefore, we conducted experiments on a synthetic dataset to better isolate effects in temporal learning. These experiments offer insights into model behavior and serve as a benchmark for validating models’ longitudinal learning capability, thus providing a straightforward method to assess temporal understanding in a controlled environment. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

QNN-QRL: Quantum Neural Network Integrated with Quantum Reinforcement Learning for Quantum Key Distribution

arXiv

引用

arXiv 2025年

作者： Behera, Bikash K. Al-Kuwari, Saif Farouk, Ahmed Pvt. Ltd. WB Mohanpur741246 India Qatar Center for Quantum Computing College of Science and Engineering Hamad Bin Khalifa University Doha Qatar Department of Computer Science Faculty of Computers and Artificial Intelligence Hurghada University Hurghada Egypt

Quantum key distribution (QKD) has emerged as a critical component of secure communication in the quantum era, ensuring information-theoretic security. Despite its potential, there are issues in optimizing key generation rates, enhancing security, and incorporating QKD into practical implementations. This research introduces a unique framework for incorporating quantum machine learning (QML) algorithms, notably quantum reinforcement learning (QRL) and quantum neural networks (QNN), into QKD protocols to improve key generation performance. Here, we present two novel QRL-based algorithms, QRL-V.1 and QRL-V.2, and propose the standard BB84 and B92 protocols by integrating QNN algorithms to form QNN-BB84 and QNN-B92. Furthermore, we combine QNN with the above QRL-based algorithms to produce QNN-QRL-V.1 and QNN-QRL-V.2. These unique algorithms and established protocols are compared using evaluation metrics such as accuracy, precision, recall, F1 score, confusion matrices, and ROC curves. The results from the QNN-based proposed algorithms show considerable improvements in key generation quality. The existing and proposed models are investigated in the presence of different noisy channels to check their robustness. The proposed integration of QML algorithms into QKD protocols and their noisy analysis create a new paradigm for efficient key generation, which advances the practical implementation of QKD systems. © 2025, CC BY.

关键词： Quantum cryptography

来源：评论

学校读者我要写书评

暂无评论

Towards Cost-Optimal Policies for DAGs to Utilize IaaS Clouds with Online Learning

引用

IEEE Transactions on Services computing 2025年

作者： Wu, Xiaohu Yu, Han Casale, Giuliano Gao, Guanyu Beijing University of Posts and Telecommunications National Engineering Research Center of Mobile Network Technologies Beijing China Nanyang Technological University WeBank-NTU Joint Research Centre on Fintech Singapore Singapore Nanyang Technological University School of Computer Science and Engineering Singapore Singapore Imperial College London Department of Computing London United Kingdom Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing China

Premier cloud service providers (CSPs) offer on-demand and spot instances (i.e., virtual machines) with time-varying features in availability and price. While interacting with a CSP, what concerns users is the process of cost-effectively utilizing these instances, possibly in addition to self-owned instances. A job in data-intensive applications is represented by a directed acyclic graph (DAG) whose nodes represent tasks and the DAG can further be transformed into a chain of tasks. The key to achieving cost efficiency is determining the allocation of a specific deadline to each task, as well as the allocation of different types of instances to the task. In this paper, we make some mild assumptions on the usage of various instances and give an analytical understanding of the expected behaviors while utilizing instances. Based on this, we propose informed heuristic policies to determine the allocation of deadlines and instances. The policies are parametric to support the usage of online learning to infer the optimal values against the dynamics of cloud markets. Finally, intuitive greedy policies are used as baselines to validate the effectiveness of the proposed analytical solutions. The cost improvement is up to 23.58% when spot and on-demand instances are considered and up to 50.08% when self-owned instances are also considered. © 2008-2012 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Instructing the Architecture Search for Spatial-temporal Sequence Forecasting with LLM

arXiv

引用

arXiv 2025年

作者： Xue, Xin Zhou, Haoyi Chen, Tianyu Zhang, Shuai Long, Yizhou Li, Jianxin Department of Computer Science Beihang University Beijing100191 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beijing100191 China Department of Software Beihang University Beijing100191 China Zhongguancun Laboratory Beijing100190 China

Spatial-temporal sequence forecasting (STSF) is a long-standing research problem with widespread real-world applications. Neural architecture search (NAS), which automates the neural network design, has been shown effective in tackling the STSF problem. However, the existing NAS methods for STSF focus on generating architectures in a time-consuming data-driven fashion, which heavily limits their ability to use background knowledge and explore the complicated search trajectory. Large language models (LLMs) have shown remarkable ability in decision-making with comprehensive internal world knowledge, but how it could benefit NAS for STSF remains unexplored. In this paper, we propose a novel NAS method for STSF based on LLM. Instead of directly generate architectures with LLM, We inspire the LLM’s capability with a multi-level enhancement mechanism. Specifically, on the step-level, we decompose the generation task into decision steps with powerful prompt engineering and inspire LLM to serve as instructor for architecture search based on its internal knowledge. On the instance-level, we utilize a one-step tuning framework to quickly evaluate the architecture instance and a memory bank to cumulate knowledge to improve LLM’s search ability. On the task-level, we propose a two-stage architecture search, balancing the exploration stage and optimization stage, to reduce the possibility of being trapped in local optima. Extensive experimental results demonstrate that our method can achieve competitive effectiveness with superior efficiency against existing NAS methods for STSF. © 2025, CC BY-NC-ND.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

A hybrid flow shop scheduling optimization using puma optimizer: Addressing energy efficiency and workforce restrictions

引用

Alexandria Engineering Journal 2025年 128卷 340-365页

作者： Sang-Woong Lee Jawad Tanveer Amir Masoud Rahmani Farhad Soleimanian Gharehchopogh Benyamin Abdollahzadeh Hamid Rokny Thantrira Porntaveetus Jan Lansky Mehdi Hosseinzadeh Pattern Recognition and Machine Learning Lab School of Computing Gachon University Seongnam 13120 Republic of Korea Department of Computer Science and Engineering Sejong University Seoul 05006 Republic of Korea Future Technology Research Center National Yunlin University of Science and Technology Yunlin Taiwan Department of Computer Engineering Ur. C. Islamic Azad University Urmia Iran Center of Excellence in Precision Medicine and Digital Health Department of Physiology Faculty of Dentistry Chulalongkorn University Bangkok 10330 Thailand Department of Computer Science and Mathematics Faculty of Economic Studies University of Finance and Administration Prague Czech Republic School of Computer Science Duy Tan University Da Nang Vietnam Centre for Research Impact & Outcome Chitkara University Institute of Engineering and Technology Chitkara University Rajpura 140401 Punjab India

The Hybrid Flow Shop Scheduling Problem (HFSP) is a complex challenge in production and manufacturing, requiring efficient scheduling solutions that optimize productivity while considering real-world constraints. This study proposes an advanced optimization framework utilizing the Puma Optimizer, a metaheuristic algorithm enhanced with an adaptive control mechanism for intelligently selecting phases and operators. This feature makes it well-suited for discrete optimization problems such as HFSP. Our approach integrates heuristic decoding and adaptive local search, balancing exploration and exploitation to generate high-quality schedules. The proposed mathematical model optimizes makespan and total tardiness while energy consumption is incorporated as a constraint to enhance sustainability. Extensive computational experiments demonstrate the superior performance of the proposed algorithm compared to traditional methods, achieving shorter makespan and lower tardiness while ensuring workforce feasibility. These results highlight the Puma Optimizer’s adaptability and potential to set new benchmarks for HFSP, offering a scalable and effective solution for modern production systems.

关键词： Hybrid Flow Shop Scheduling Problem (HFSP) Puma optimizer Energy efficiency Worker constraints Metaheuristic optimization

来源：评论

学校读者我要写书评

暂无评论

Multi-agent Collaboration for Vehicular Task Offloading Using Federated Deep Reinforcement Learning

引用

IEEE Transactions on Mobile computing 2025年

作者： Chen, Xing Xiao, Bohuai Lin, Xinyu Chen, Zheyi Min, Geyong Fuzhou University College of Computer and Data Science Fuzhou350116 China Ministry of Education Engineering Research Center of Big Data Intelligence Fuzhou350002 China Fuzhou University Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou350116 China University of Exeter Department of Computer Science ExeterEX4 4QF United Kingdom

Mobile Edge computing (MEC) distributes resources such as computing, storage, and bandwidth to the side close to users, which can provide low-latency services to in-vehicle users, thus promising a more efficient and safer driving environment. However, due to the dynamic scale of vehicle and the variability of resource requirements, it is a significant challenge to quickly obtain effective task offloading in large-scale vehicle scenarios. The existing studies generally adopt the centralized decision-making method, with long decision-making time and high computational overhead, which cannot effectively achieve good offloading decisions in large-scale scenarios. To address these problems, we propose a Multi-agent Collaborative Method for vehicular task offloading using Federated Deep Reinforcement Learning called MCM-FDRL. First, each vehicle as an agent, independently makes offloading decisions based on local information. Next, the offloading decision model of each vehicle is obtained through federated reinforcement learning training. At runtime, an effective vehicle offloading plan can be gradually developed through multi-agent collaboration. Using two real-world datasets, experiments show that the MCM-FDRL has good adaptability and scalability. Moreover, compared to the state-of-the-art methods, the task's average response time of the MCM-FDRL is reduced by 9.75%-64.90%, respectively. © 2002-2012 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Augmented reality for area measurement reasoning of elementary students

引用

Educational Technology Research and Development 2025年 1-35页

作者： Flavin, Eunhye Chung, Moon Hwang, Sunghwan Flavin, Matthew T. Center for Education Integrating Science Mathematics and Computing Georgia Institute of Technology 505 10th St NW Atlanta 30332 GA United States Department of Education Studies Stonehill College 320 Washington Street North Easton 02322 MA United States Department of Mathematics Education Chuncheon National University of Education 126 Gongji-ro Gangwon-do Chuncheon-si South Korea School of Electrical and Computer Engineering Georgia Institute of Technology 777 Atlantic Dr NW Atlanta 30309 GA United States

Area measurement is a foundational component across STEM fields. The area formula offers limited insight for children trying to develop their area measurement reasoning skills, particularly when dealing with composite shapes. Spatial structuring, where children explore structural units of a 2D space, is an alternative approach. However, poor manipulation of physical units can reinforce misconceptions about area measurement. To address this issue, we developed MeoGeo, an augmented reality (AR) smartphone application. MeoGeo allows children to readily create virtual structural arrays with units of varying sizes, superimposing them on their surroundings in real-time. We conducted an exploratory multiple-case study over a 7-week program to examine the effect of AR activities. Data included written responses from three elementary students on paper-and-pencil tests, along with in situ videos recordings. Our findings indicate that engagement in AR activities facilitated reasoning skills in area measurement for both basic and composite shapes. Furthermore, students maintained their reasoning skills beyond the intervention period. Our study underscores the importance of developing AR systems that align explicitly with the developmental progression of each child, and it highlights the critical role of the instructor in effective execution of AR activities. © The Author(s) 2025.

关键词： Area measurement Augmented reality Elementary education Intelligent system Mathematics education Mathematics reasoning

来源：评论

学校读者我要写书评

暂无评论

An Architecture of Adaptive Cognitive Digital Twins for Resilient Healthcare Infrastructures and Services 2nd

An Architecture of Adaptive Cognitive Digital Twins for Re...

引用

2nd International Workshop on Secure and Resilient Digital Transformation of Healthcare, SUNRISE 2024

作者： Xu, Shouhuai Pirbhulal, Sandeep Abie, Habtamu Department of Computer Science University of Colorado Colorado Springs Colorado SpringsCO80918 United States Norwegian Computing Center/Norsk Regnesentral P.O. Box 114 Blindern OsloN-0314 Norway

ISBN: (纸本)9783031855573

Modern healthcare infrastructures and services are dependent on advanced data analytics, sensing and communication technologies that include 5G/6G networks, Artificial intelligence (AI), Internet of Medical Things (IoMT), Information Technology (IT), and Operational Technology (OT). This integration incurs a large vulnerability surface and cyber attackers can exploit those vulnerabilities to wage successful attacks against modern healthcare infrastructures and services. Therefore, identifying potential vulnerabilities in healthcare infrastructures and services and securing end-to-end monitoring of sensitive healthcare infrastructures and services are crucial for achieving resilient healthcare infrastructures and services. In this paper, we propose an architecture designed to enhance the resilience of healthcare infrastructures and services. This architecture is centered around the concept of Adaptive Cognitive Digital Twins (ACDTs), which are capable of orchestrating adaptive defenses to proactively respond to anticipated cyber attacks. Our architecture has seven layers. We detail the functions at each layer of the architecture to guide the design and development of mechanisms that can be employed at each layer. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

STPNet: Scale-aware Text Prompt Network for Medical Image Segmentation

引用

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society 2025年 PP卷 PP页

作者： Dandan Shan Zihan Li Yunxiang Li Qingde Li Jie Tian Qingqi Hong Institute of Artificial Intelligence Xiamen University Xiamen China Department of Bioengineering University of Washington Seattle WA USA Department of Radiation Oncology UT Southwestern Medical Center Dallas TX USA Department of Computer Science University of Hull Hull U.K. Chinese Academy of Sciences Institute of Automation Beijing China Center for Digital Media Computing School of Film the National Institute for Data Science in Health and Medicine and the Institute of Artificial Intelligence Xiamen University Xiamen China

Accurate segmentation of lesions plays a critical role in medical image analysis and diagnosis. Traditional segmentation approaches that rely solely on visual features often struggle with the inherent uncertainty in lesion distribution and size. To address these issues, we propose STPNet, a Scale-aware Text Prompt Network that leverages vision-language modeling to enhance medical image segmentation. Our approach utilizes multi-scale textual descriptions to guide lesion localization and employs retrieval-segmentation joint learning to bridge the semantic gap between visual and linguistic modalities. Crucially, STPNet retrieves relevant textual information from a specialized medical text repository during training, eliminating the need for text input during inference while retaining the benefits of cross-modal learning. We evaluate STPNet on three datasets: COVID-Xray, COVID-CT, and Kvasir-SEG. Experimental results show that our vision-language approach outperforms state-of-the-art segmentation methods, demonstrating the effectiveness of incorporating textual semantic knowledge into medical image analysis. The code has been made publicly on https://***/HUANGLIZI/STPNet.

关键词： Image segmentation Lesions Feature extraction Accuracy visualization Medical diagnostic imaging Training Lungs Transformers COVID-19

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：