检索结果-内蒙古大学图书馆

Toward Democratized Generative AI in Next-Generation Mobile Edge Networks

IEEE Network 2025年

作者： Zhang, Ruichen He, Jiayi Luo, Xiaofeng Niyato, Dusit Kang, Jiawen Xiong, Zehui Li, Yonghui Sikdar, Biplab Nanyang Technological University College of Computing and Data Science Singapore Guangdong University of Technology School of Automation Guangzhou510006 China Singapore University of Technology and Design Pillar of Information Systems Technology and Design Singapore University of Sydney School of Electrical and Information Engineering SydneyNSW2006 Australia National University of Singapore College of Design and Engineering Department of Electrical and Computer Engineering Singapore

The rapid development of generative artificial intelligence (AI) technologies, including large language models (LLMs), has brought transformative changes to various fields. However, deploying such advanced models on mobile and edge devices remains challenging due to their high computational, memory, communication, and energy requirements. To address these challenges, we propose a model-centric framework for democratizing generative AI deployment on mobile and edge networks. First, we comprehensively review key compact model strategies, such as quantization, model pruning, and knowledge distillation, and present key performance metrics to optimize generative AI for mobile deployment. Next, we provide a focused review of mobile and edge networks, emphasizing the specific challenges and requirements of these environments. We further conduct a case study demonstrating the effectiveness of these strategies by deploying LLMs on real mobile edge devices. Experimental results highlight the practicality of democratized LLMs, with significant improvements in generalization accuracy, hallucination rate, accessibility, and resource consumption. Finally, we discuss potential research directions to further advance the deployment of generative AI in resource-constrained environments. © 1986-2012 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

STMAE: Spatial Temporal Masked Auto-Encoder for Traffic Forecasting 27th

STMAE: Spatial Temporal Masked Auto-Encoder for Traffic For...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Wu, Xing Cai, Chengyou Wang, Xiaoxiao Wang, Jianjia Yao, Junfeng Qian, Quan Song, Jun School of Computer Engineering and Science Shanghai University Shanghai China Shanghai Institute for Advanced Communication and Data Science Shanghai University Shanghai China Shanghai Shentong Metro Co. Ltd. Shanghai China School of AI and Advanced Computing XJTLU Entrepreneur College Xi’an Jiaotong-Liverpool University Suzhou China CSSC Seago System Technology Co. Ltd. Shanghai China Department of Geography Hong Kong Baptist University Hong Kong

ISBN: (纸本)9783031781681

The advancement of intelligent transportation systems underscores the importance of data-driven approaches in traffic forecasting, which plays a crucial role in tasks such as traffic signal control and route guidance, among others. However, the inherent uncertainty stemming from regional traffic dynamics, coupled with intricate spatio-temporal correlations, poses formidable challenges to accurate traffic prediction. Moreover, the complexities inherent in sequence forecasting across varying scales further exacerbate the accuracy dilemma. Recognizing the need for integrating information across spatial and temporal dimensions to enhance forecasting precision, a novel solution termed Spatial Temporal Masked Autoencoder (STMAE) is introduced. The STMAE framework addresses these challenges through a two-stage learning process. In the pre-training phase, an autoencoder architecture is employed to extract spatio-temporal features from the data. In the fine-tuning phase, the pre-trained encoder of the STMAE model undergoes further refinement to specifically target traffic forecasting tasks. Extensive evaluations validate the effectiveness of the proposed STMAE model. Notably, STMAE demonstrates competitive performance, achieving 3.32 Vehs MAE for long-term (60 min) traffic forecasting while operating within a reduced computational budget. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

C2AV-TSE: Context and Confidence-aware Audio Visual Target Speaker Extraction

引用

IEEE Journal on Selected Topics in Signal Processing 2025年

作者： Wu, Wenxuan Chen, Xueyuan Wang, Shuai Wang, Jiadong Meng, Lingwei Wu, Xixin Meng, Helen Li, Haizhou The Chinese University of Hong Kong Department of Systems Engineering and Engineering Management Hong Kong Nanjing University School of Intelligence Science and Technology Suzhou215163 China The Chinese University of Hon g Kong Shenzhen Research Institute of Big Data Shenzhen518172 China Technical University of Munich Germany The Chinese University of Hon g Kong Shenzhen Research Institute of Big Data School of Data Science Shenzhen China National University of Singapore Department of Electrical and Computer Engineering 119077 Singapore

Audio-Visual Target Speaker Extraction (AV-TSE) aims to mimic the human ability to enhance auditory perception using visual cues. Although numerous models have been proposed recently, most of them estimate target signals by primarily relying on local dependencies within acoustic features, underutilizing the human-like capacity to infer unclear parts of speech through contextual information. This limitation results in not only suboptimal performance but also inconsistent extraction quality across the utterance, with some segments exhibiting poor quality or inadequate suppression of interfering speakers. To close this gap, we propose a model-agnostic strategy called the Mask-And-Recover (MAR). It integrates both inter- and intra-modality contextual correlations to enable global inference within extraction modules. Additionally, to better target challenging parts within each sample, we introduce a Fine-grained Confidence Score (FCS) model to assess extraction quality and guide extraction modules to emphasize improvement on low-quality segments. To validate the effectiveness of our proposed model-agnostic training paradigm, six popular AV-TSE backbones were adopted for evaluation on the VoxCeleb2 dataset, demonstrating consistent performance improvements across various metrics. © 2025 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Continual Reinforcement Learning for Digital Twin Synchronization Optimization

引用

IEEE Transactions on Mobile computing 2025年

作者： Tong, Haonan Chen, Mingzhe Zhao, Jun Hu, Ye Yang, Zhaohui Liu, Yuchen Yin, Changchuan Beijing University of Posts and Telecommunications Beijing Key Laboratory of Network System Architecture and Convergence Beijing Advanced Information Network Laboratory Beijing China College of Computing and Data Science Singapore University of Miami Department of Electrical and Computer Engineering Frost Institute for Data Science and Computing Coral Gables33146 United States University of Miami Department of Industrial and Systems Engineering Coral Gables33146 United States Zhejiang University College of Information Science and Electronic Engineering Hangzhou310027 China North Carolina State University Department of Computer Science RaleighNC27695 United States Beijing Key Laboratory of Network System Architecture and Convergence China Beijing University of Posts and Telecommunications Beijing Advanced Information Network Laboratory Beijing100876 China

This article investigates the adaptive resource allocation scheme for digital twin (DT) synchronization optimization over dynamic wireless networks. In our considered model, a base station (BS) continuously collects factory physical object state data from wireless devices to build a real-time virtual DT system for factory event analysis. Due to continuous data transmission, maintaining DT synchronization must use extensive wireless resources. To address this issue, a subset of devices is selected to transmit their sensing data, and resource block (RB) allocation is optimized. This problem is formulated as a constrained Markov process (CMDP) problem that minimizes the long-term mismatch between the physical and virtual systems. To solve this CMDP, we first transform the problem into a dual problem that refines RB constraint impacts on device scheduling strategies. We then propose a continual reinforcement learning (CRL) algorithm to solve the dual problem. The CRL algorithm learns a stable policy across historical experiences for quick adaptation to dynamics in physical states and network capacity. Simulation results show that the CRL can adapt quickly to network capacity changes and reduce normalized root mean square error (NRMSE) between physical and virtual states by up to 55.2%, using the same RB number as traditional methods. © 2025 IEEE. All rights reserved.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Full-Space Wireless Sensing Enabled by Multi-Sector Intelligent Surfaces

引用

IEEE Transactions on Wireless Communications 2025年

作者： Zhang, Yumeng Shao, Xiaodan Li, Hongyu Clerckx, Bruno Zhang, Rui Hong Kong University of Science and Technology Electronic and Computing Engineering Hong Kong Hong Kong University of Waterloo Department of Electrical and Computer Engineering WaterlooONN2L 3G1 Canada Internet of Things Thrust Guangdong Guangzhou511400 China Imperial College London Department of Electrical and Electronic Engineering LondonSW7 2AZ United Kingdom Kyung Hee University Seoul Korea Republic of The Chinese University of HongKong School of Science and Engineering Shenzhen Research Institute of Big Data Guangdong Shenzhen518172 China National University of Singapore Department of Electrical and Computer Engineering Singapore117583 Singapore

The multi-sector intelligent surface (IS), benefiting from a smarter wave manipulation capability, has been shown to enhance channel gain and offer full-space coverage in communications. However, the benefits of multi-sector IS in wireless sensing remain unexplored. This paper introduces the application ofmulti-sector IS for wireless sensing/localization. Specifically, we propose a new self-sensing system, where an active source controller uses the multi-sector IS geometry to reflect/scatter the emitted signals towards the entire space, thereby achieving full-space coverage for wireless sensing. Additionally, dedicated sensors are installed aligned with the IS elements at each sector, which collect echo signals fromthe target and cooperate to sense the target angle. In this context, we develop a maximum likelihood estimator of the target angle for the proposed multi-sector IS self-sensing system, along with the corresponding theoretical limits defined by the Craḿer-Rao Bound. The analysis reveals that the advantages of the multi-sector IS self-sensing system stem from two aspects: enhancing the probing power on targets (thereby improving power efficiency) and increasing the rate of target angle (thereby enhancing the transceiver's sensitivity to target angles). Finally, our analysis and simulations confirm that the multi-sector IS self-sensing system, particularly the 4-sector architecture, achieves full-space sensing capability beyond the single-sector IS configuration. Furthermore, similarly to communications, employing directive antenna patterns on each sector's IS elements and sensors significantly enhances sensing capabilities. This enhancement originates from both aspects of improved power efficiency and target angle sensitivity, with the former also being observed in communications while the latter being unique in sensing. © 2002-2012 IEEE.

关键词： Directive antennas

来源：评论

学校读者我要写书评

暂无评论

Tensor Network Structure Search Using Program Synthesis

arXiv

引用

arXiv 2025年

作者： Guo, Zheng Deshpande, Aditya Kiedrowski, Brian Wang, Xinyu Gorodetsky, Alex Michigan Institute for Data & AI in Society University of Michigan United States Electrical Engineering and Computer Science Department University of Michigan United States Aerospace Engineering Department University of Michigan United States Neuclear Engineering & Radiological Sciences Department University of Michigan United States

Tensor networks provide a powerful framework for compressing multi-dimensional data. The optimal tensor network structure for a given data tensor depends on both the inherent data properties and the specific optimality criteria, making tensor network structure search a crucial research problem. Existing solutions typically involve sampling and validating numerous candidate structures;this is computationally expensive, limiting their practical applications. We address this challenge by formulating tensor network structure search as a program synthesis problem and proposing a highly efficient validation method that is based on constraint solving. Specifically, we design a domain specific language: it builds the correspondence between programs and network structures, and uses a novel idea of output-directed splits to compress the search space without hindering the expressiveness. We then propose a synthesis algorithm that can prioritize promising candidates through constraint solving. Experimental results show that our approach improves search speed by 10× and achieves compression ratios by 1.5× to 3× better than state-of-the-art. Notably, our approach scales to larger tensors that are out of reach by prior work. Finally, we demonstrate that the discovered topologies generalize to data from the same source, achieving compression ratios up to 2.4× better than hierarchical Tuckers while maintaining the runtime around 110 seconds. © 2025, CC BY.

关键词： data compression ratio

来源：评论

学校读者我要写书评

暂无评论

Lightweight Authenticated Task Offloading in 6G-Cloud Vehicular Twin Networks

Lightweight Authenticated Task Offloading in 6G-Cloud Vehicu...

引用

IEEE Conference on Wireless Communications and Networking

作者： Sarah Al–Shareeda Fusun Ozguner Keith Redmill Trung Q. Duong Berk Canberk Electrical and Computer Engineering Department Center for Automotive Research (CAR) The Ohio State University USA BTS Group Turkey Department of AI and Data Engineering Istanbul Technical University Turkey School of Electronics Electrical Engineering and Computer Science Queen's University Belfast UK Faculty of Engineering and Applied Science Memorial University of Newfoundland St. John's NL Canada School of Computing Engineering and The Built Environment Edinburgh Napier University UK

ISBN: (数字)9798350368369

ISBN: (纸本)9798350368376

Task offloading management in 6G vehicular net-works is crucial for maintaining network efficiency, particularly as vehicles generate substantial data. Integrating secure communication through authentication introduces additional computational and communication overhead, significantly impacting offloading efficiency and latency. This paper presents a unified framework incorporating lightweight Identity-Based Cryptographic (IBC) authentication into task offloading within cloud-based 6G Vehicular Twin Networks (VTNs). Utilizing Proximal Policy Optimization (PPO) in Deep Reinforcement Learning (DRL), our approach optimizes authenticated offloading decisions to minimize latency and enhance resource allocation. Performance evaluation under varying network sizes, task sizes, and data rates reveals that IBC authentication can reduce offloading efficiency by up to 50 % due to the added overhead. Besides, increasing network size and task size can further reduce offloading efficiency by up to 91.7%. As a countermeasure, increasing the transmission data rate can improve the offloading performance by as much as 63%, even in the presence of authentication overhead. The code for the simulations and experiments detailed in this paper is available on GitHub for further reference and reproducibility [1].

关键词： 6G mobile communication Performance evaluation Identity-based encryption Authentication Deep reinforcement learning Reproducibility of results Resource management Cryptography Optimization Software development management

来源：评论

学校读者我要写书评

暂无评论

AI-Assisted Fine-Grained Plant Disease Diagnosis from Smartphone Images

AI-Assisted Fine-Grained Plant Disease Diagnosis from Smartp...

引用

Cognitive computing in engineering, Communications, sciences and Biomedical Health Informatics (IC3ECSBHI), International Conference on

作者： Anandhi R J D Sreenivasulu Alok Jain V Arun Fatimah Dhari Jabbar Bhasker Boddu Kanan Divetia Department of Information Science Engineering New Horizon College of Engineering Bangalore India Computer Science and Engineering (Data Science) Institute of Aeronautical Engineering Hyderabad India Lovely Professional University Phagwara India Department of Electrical & Electronics Engineering IILM University Greater Noida India Radiology Techniques Department College of Medical Technology The Islamic University Najaf Iraq Department of Computer Science and Engineering MLR Institute of Technology Hyderabad Telangana India Lloyd Law College Greater Noida Uttar Pradesh India

ISBN: (数字)9798331518523

ISBN: (纸本)9798331518530

Disease detection at an early stage in plants is very important in order to check serious losses to crop production. This research presents novel, lightweight, and easily portable AI model that is best suited for real-time plant disease detection through mobile technology. The model is a combination of MobileNet and EfficientNet, and the Model is trained from the PlantVillage dataset. One of the main objectives of the study is to enhance the ability to distinguish between visually similar diseases, a universal problem of plant pathology. Lack of data is then solved by using transfer learning from pre-trained networks as well as further image augmentation. Further, optimization techniques are employed in work to get faster inference and minimal device usage on mobile platform but keeping the diagnostic accuracy high. Thus, the proposed approach helps to bring ideas of AI to practicle field usage and supports further progress in such industries as precision farming and food safety.

关键词： Precision agriculture Plant diseases Accuracy Quantization (signal) Computational modeling Plants (biology) Transfer learning Production Real-time systems Image augmentation

来源：评论

学校读者我要写书评

暂无评论

Detecting and Monitoring Bias for Subgroups in Breast Cancer Detection AI

arXiv

引用

arXiv 2025年

作者： Kundu, Amit Kumar Doo, Florence X. Patil, Vaishnavi Varshney, Amitabh Jaja, Joseph Department of Electrical and Computer Engineering University of Maryland United States Department of Diagnostic Radiology and Nuclear Medicine University of Maryland School of Medicine United States Department of Computer Science University of Maryland United States Institute for Health Computing University of Maryland United States University of Maryland Institute for Advanced Computer Studies United States

Automated mammography screening plays an important role in early breast cancer detection. However, current machine learning models, developed on some training datasets, may exhibit performance degradation and bias when deployed in real-world settings. In this paper, we analyze the performance of high-performing AI models on two mammography datasets—the Emory Breast Imaging dataset (EMBED) and the RSNA 2022 challenge dataset. Specifically, we evaluate how these models perform across different subgroups, defined by six attributes, to detect potential biases using a range of classification metrics. Our analysis identifies certain subgroups that demonstrate notable underperformance, highlighting the need for ongoing monitoring of these subgroups’ performance. To address this, we adopt a monitoring method designed to detect performance drifts over time. Upon identifying a drift, this method issues an alert, which can enable timely interventions. This approach not only provides a tool for tracking the performance but also helps ensure that AI models continue to perform effectively across diverse populations. © 2025, CC BY.

关键词： Mammography

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

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：