检索结果-内蒙古大学图书馆

Accelerating Mobile Edge Generation (MEG) by Constrained Learning

IEEE Transactions on Cognitive Communications and Networking 2025年

作者： Xu, Xiaoxia Liu, Yuanwei Mu, Xidong Xing, Hong Nallanathan, Arumugam Queen Mary University of London School of Electronic Engineering and Computer Science LondonE1 4NS United Kingdom The University of Hong Kong Department of Electrical and Electronic Engineering Hong Kong School of Electronics Electrical Engineering and Computer Science BelfastBT3 9DT United Kingdom The Hong Kong University of Science and Technology IoT Thrust Guangzhou Guangzhou511453 China Hong Kong University of Science and Technology Department of ECE Hong Kong Kyung Hee University Department of Electronic Engineering Gyeonggi-do Yongin-si17104 Korea Republic of

A novel mobile edge generation (MEG) framework is proposed for low-latency image generation on mobile devices. Exploiting a latent diffusion model (LDM) distributed across the edge server (ES) and the user equipment (UE), only low-dimension features need to be transmitted for creating artificial intelligence generative content (AIGC). Two novel modules, namely dynamic diffusion and feature merging, are conceived to compress the diffusion model and transmitted features, respectively. By jointly optimizing compression rates of denoising steps and feature merging, the image quality maximization problem is formulated subject to latency and energy consumption constraints. To address this problem in dynamic channel conditions, a low-complexity compression protocol is developed. First, a backbone LDM architecture is learned by offline distillation to support various compression options. Then, compression rates are predicted in online environment specific to channel and task features. To solve the resultant constrained Markov Decision Process (MDP), a constrained variational policy optimization (CVPO) based MEG algorithm, MEG-CVPO, is further developed to learn constraint-guaranteed optimization. Numerical results demonstrate that: 1) The proposed framework improves image distortions while reducing over 40% latency compared to conventional generation schemes. 2) MEG-CVPO stringently guarantee constraints and realizes a flexible trade-off between generation qualities and overheads. © 2015 IEEE.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Hybrid Machine Learning Approach for Enhanced Vulnerability Detection in Cloud Environments Using NIST and MITRE Frameworks

Hybrid Machine Learning Approach for Enhanced Vulnerability ...

引用

Advanced Research in Computing (ICARC), International Conference on

作者： N W Chanaka Lasantha M W P Maduranga Ruvan Abeysekara Valmik Tilwari Nilotpal Chakraborty Debashree Sharma Faculty of Graduate Studies IIC University of Technology Phnom Penh Cambodia Department of Electrical and Electronic Engineering University of Sri Jayewardenepura Nugegoda Sri Lanka Faculty of Computing BCAS Campus Colombo Sri Lanka Department. of Electronics & Communication Engineering Indian Institute of Information Technology Guwahati India Department of Computer Science Engineering Indian Institute of Information Technology Guwahati India Department of Electronics & Communication Engineering Indian Institute of Information Technology Guwahati India

ISBN: (数字)9798331530983

ISBN: (纸本)9798331530990

Cloud security is challenged by constant adaptive cyber threats and traditional detection methods lack real time adaptability. In this paper, we propose a new hybrid ML approach stitching data from National Institute of Standards and technology (NIST) and MITRE Adversarial Tactics, Techniques and Common Knowledge (ATT&CK) databases together. In contrast to existing methods, this framework combines, in unique and unprecedented fashion, ensemble ML models and Realtime data processing for increased detection accuracy and reduced false positives. This approach addresses specific challenges in the cloud environments and by leveraging standardised frameworks, it offers actionable audiences for efficient and effective vulnerability management process. The framework is validated by the experimental results which prove its robustness to evolution of the cybersecurity demands.

关键词： Adaptation models Accuracy Cloud computing security Scalability NIST Transformers Data models Threat assessment Robustness Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Simultaneous Wireless Information and Power Transfer for STAR-RIS Assisted UAV Networks

引用

IEEE Internet of Things Journal 2025年

作者： Xie, Wenwu Qin, Lijuan Wang, Ji Wu, Weimin Li, Xingwang Xu, Hongbo Yang, Liang Hunan Institute of Science and Technology School of Information Science and Engineering Yueyang414006 China Central China Normal University Department of Electronics and Information Engineering Wuhan430079 China Huazhong University of Science and Technology School of Electronic Information and Communications Wuhan430074 China Henan Polytechnic University School of Physics and Electronic Information Engineering Jiaozuo454003 China Hunan University College of Computer Science and Electronic Engineering Changsha410082 China

This paper explores the benefits of deploying simultaneously transmitting and reflecting reconfigurable intelligence surfaces (STAR-RIS) in unmanned aerial vehicle (UAV) networks with simultaneous wireless information and power transfer. In the proposed system, the UAV utilizes STAR-RIS to radiate energy-carrying information signals (ECISs) to multiple outdoor energy receivers and multiple indoor information receivers without flying over indoor no-fly zone. Based on the UAV propulsion power formula, we successively introduce fly-hover-broadcast (FHB) and path discretization (PD) protocols to minimize the total UAV energy consumption by jointly using the extended penalty function and optimization algorithm based on the expected value of channel status information, where the UAV flight constraints, no-fly constraint, minimized energy or information threshold constraints, and STAR-RIS phase-shift constraints are met. The FHB protocol, which requires the UAV to radiate the ECISs to the users at only a few hovering positions, provides a lower-bound performance of UAV energy consumption, while the PD protocol is used to discuss the general situation of the ECISs during UAV flight. Simulation results demonstrate that the utilization of the STAR-RIS in UAV networks outperforms the traditional RIS in improving energy efficiency and extending UAV flight time. © 2014 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Secure Beamforming for Continuous Aperture Array (CAPA) Systems

arXiv

引用

arXiv 2025年

作者： Sun, Mingjun Ouyang, Chongjun Wang, Zhaolin Wu, Shaochuan Liu, Yuanwei School of Electronics and Information Engineering Harbin Institute of Technology Harbin150001 China School of Electrical and Electronic Engineering UCD College of Engineering and Architecture University College DublinD04 V1W8 Ireland School of Electronic Engineering and Computer Science Queen Mary University of London LondonE1 4NS United Kingdom Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong

Continuous aperture array (CAPA) is considered a promising technology for 6G networks, offering the potential to fully exploit spatial DoFs and achieve the theoretical limits of channel capacity. This paper investigates the performance gain of a CAPA-based downlink secure transmission system, where multiple legitimate user terminals (LUTs) coexist with multiple eavesdroppers (Eves). The system’s secrecy performance is evaluated using a weighted secrecy sum-rate (WSSR) under a power constraint. We then propose two solutions for the secure current pattern design. The first solution is a block coordinate descent (BCD) optimization method based on fractional programming (FP), which introduces a continuous-function inversion theory corresponding to matrix inversion in the discrete domain. This approach derives a closed-form expression for the optimal source current pattern. Based on this, it can be found that the optimal current pattern is essentially a linear combination of the channel spatial responses, thus eliminating the need for complex integration operations during the algorithm’s optimization process. The second solution is a heuristic algorithm based on Zero-Forcing (ZF), which constructs a zero-leakage current pattern using the channel correlation matrix. It further employs a waterfilling approach to design an optimal power allocation scheme that maximizes the WSSR. In high SNR regions, this solution gradually approaches the first solution, ensuring zero leakage while offering lower computational complexity. Simulation results demonstrate that: 1) CAPA-based systems achieve better WSSR compared to discrete multiple-input multiple-output (MIMO) systems. 2) The proposed methods, whether optimization-based or heuristic, provide significant performance improvements over existing state-of-the-art Fourier-based discretization methods, while considerably reducing computational complexity. Copyright © 2025, The Authors. All rights reserved.

关键词： Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

An improved end-to-end micro-expression recognition system for real-world videos via dual-input CNN architecture

引用

Expert Systems with Applications 2025年 286卷

作者： Gan, Y.S. Liu, Kun-Hong Wu, Min-Huan Liong, Gen-Bing Liong, Sze-Teng School of Architecture Feng Chia University Taichung40724 Taiwan Department of Digital Media Technology School of Film Xiamen University Xiamen China Bachelor of Science in Senior Wellness and Sport Science Tunghai University Taiwan Faculty of Computer Science & Information Technology University of Malaya Kuala Lumpur50603 Malaysia Department of Electronic Engineering Feng Chia University Taichung40724 Taiwan

Micro-expression (ME) recognition reveals nonverbal emotions through subtle, involuntary facial muscle movements. However, the development and commercialization of ME recognition systems have been hindered by the lack of databases that accurately reflect real-world conditions. This study addresses this challenge by proposing a robust end-to-end system designed to operate effectively in unconstrained environments. Existing methods typically rely on a single apex frame, which may be unreliable due to noise, occlusions, or lighting variations. To address these issues, a 3D facial reconstruction technique is applied as a pre-processing step to normalize pose and lighting. A novel dual-peak frame detection strategy is then introduced to extract two expressive optical flow frames, reducing the impact of noise from any single frame. Finally, a Shallow and Small-size Dual-input (SSD) CNN architecture is designed to jointly process the two frames for improved emotion classification. The proposed system achieves strong performance on the challenging in-the-wild MEVIEW dataset, with accuracy and F1-score of 75 % and 77.68 %, respectively. Comprehensive evaluations further validate the effectiveness of the pipeline, highlighting its potential for real-world ME recognition applications. © 2025 Elsevier Ltd

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

Energy Efficient Transmitter Creation by Consuming Free Energy in Molecular Communication

引用

IEEE Transactions on Molecular, Biological, and Multi-Scale Communications 2025年

作者： Jing, Dongliang Li, Linjuan Cheng, Zhen Lin, Lin Eckford, Andrew W. Northwest A and F University College of Mechanical and Electronic Engineering Yangling China Ministry of Agriculture and Rural Affairs Key Laboratory of Agricultural Internet of Things Yangling China Zhejiang University of Technology School of Computer Science and Technology Hangzhou310023 China Tongji University College of Electronics and Information Engineering Shanghai China York University Department of Electrical Engineering and Computer Science TorontoON Canada

Information molecules play a crucial role in molecular communication (MC), acting as carriers for information transfer. A common approach to get information molecules in MC involves harvesting them from the environment;however, the harvested molecules are often a mixture of various environmental molecules, and the initial concentration ratios in the reservoirs are identical, which hampers high-fidelity transmission techniques such as molecular shift keying (MoSK). This paper presents a transmitter design that harvests molecules from the surrounding environment and stores them in two reservoirs. To separate the mixed molecules, energy is consumed to transfer them between reservoirs. Given limited energy resources, this work explores energy-efficient strategies to optimize transmitter performance. Through theoretical analysis and simulations, we investigate different methods for moving molecules between reservoirs. The results demonstrate that transferring higher initial concentration molecules enhances transmitter performance, while using fewer molecules per transfer further improves efficiency. These findings provide valuable insights for optimizing MC systems through energy-efficient molecule transfer techniques. © 2015 IEEE.

关键词： Transmitters

来源：评论

学校读者我要写书评

暂无评论

Intelligent control algorithms for industrial automation systems

Intelligent control algorithms for industrial automation sys...

引用

IEEE Students' Conference on Electrical, electronics and computer Science (SCEECS)

作者： Sarathkumar D Anil. A. R J Sivadasan T. Jayakumar Murugesan Manivel Anandhakumar C Department of Electrical and Electronics Engineering Kongu Engineering College Tamil Nadu India Department of Computer Science &Engineering Sree Buddha College of Engineering Pattoor Alappuzha Kerala India Department of Electronics and Communication Engineering PSR Engineering College Sivakasi Tamil Nadu India Department of Electrical and Electronics Engineering Nandha Engineering College Tamil Nadu India Department of Electrical and Electronics Engineering Karpagam Institute of Technology Coimbatore Tamilnadu India Department of Electrical and Electronic Engineering Sri Ramakrishna Institute of Technology Coimbatore Tamil Nadu India

ISBN: (数字)9798331529833

ISBN: (纸本)9798331529840

Industrial automation has become a cornerstone of modern manufacturing, enhancing efficiency, reliability, and scalability. The integration of intelligent control algorithms, such as fuzzy logic, neural networks, genetic algorithms, and model predictive control, has revolutionized traditional automation systems, enabling more adaptive, efficient, and robust operations. This paper explores the application and impact of these intelligent control techniques in industrial settings. It highlights how machine learning algorithms can predict equipment failures, optimize processes, and enhance decision-making in real-time. Case studies are presented to illustrate the benefits and challenges of deploying these algorithms across various automated systems, such as robotic assembly lines, process control in chemical plants, and smart warehousing. Furthermore, the paper discusses the integration of these algorithms with industrial IoT (IIoT) platforms, facilitating seamless communication and data exchange between machines and control systems. The research also addresses the challenges of implementing intelligent control, such as computational complexity, security concerns, and the need for real-time processing. Finally, this study evaluates future trends, emphasizing the potential of combining artificial intelligence and deep learning techniques with industrial automation for a more adaptive and autonomous manufacturing ecosystem.

关键词： Fuzzy logic Automation Machine learning algorithms Neural networks Prediction algorithms Real-time systems Optimization Intelligent control Industrial Internet of Things Predictive control

来源：评论

学校读者我要写书评

暂无评论

Integrated Sensing, Identification, and Backscatter Communication System Utilizing Inverse Scattering Approach

引用

IEEE Transactions on Antennas and Propagation 2025年

作者： Ma, Dingfei Shen, Shanpu Zhou, Hongxin Zhang, Chi Zhang, Qingfeng Murch, Ross Guangdong University of Technology School of Information Engineering Guangzhou510006 China University of Liverpool Department of Electrical Engineering and Electronics LiverpoolL69 3GJ United Kingdom Southern University of Science and Technology Department of Electronics and Electrical Engineering Guangdong Shenzhen518055 China University Key Laboratory of Advanced Wireless Communications of Guangdong Province Guangdong China Peng Cheng Laboratory Shenzhen518055 China University of Hong Kong Science and Technology Department of Electronic and Computer Engineering Hong Kong

This paper presents a novel integrated sensing, identification, and backscatter communication system that incorporates techniques based on inverse scattering. The proposed system enables simultaneous localization, identification and backscatter communication of tags in cluttered environments. We formulate the backscatter in terms of the tag’s structural and antenna modes and clutter scatterers. By modulating the tags with opencircuit and short-circuit states, we extract the structural and antenna mode components separately. Utilizing the structural mode component, we sense both the tag and clutter scatterers and perform tag identification using the antenna mode component. To conduct sensing and identification both inverse scattering and compressive sensing (CS) algorithms are employed. This enables recovery of high-dimensional imaging information but also significantly reduces the number of transceivers required. In addition, channel state information (CSI) can be acquired by utilizing the antenna mode during the sensing and identification stage, and the backscatter communication performance is evaluated using the bit error rate (BER) based on the maximum ratio combining (MRC) technique. A proof-of-principle illustrative system is developed based on one transmit and one receive array equipped with 3×3 uniform linear antennas (ULA) configuration. Results of sensing, identification and backscatter communication are provided to verify that the proposed system with inverse scattering can accurately locate and identify the tags separately or in combination, while maintaining data communications in challenging cluttered environments. © 1963-2012 IEEE.

关键词： Bit error rate

来源：评论

学校读者我要写书评

暂无评论

A Hybrid GAN-CNN Framework for Low-Light Image Enhancement Combining Structural Noise Reduction and Perceptual Quality

A Hybrid GAN-CNN Framework for Low-Light Image Enhancement C...

引用

Multi-Agent Systems for Collaborative Intelligence (ICMSCI), International Conference on

作者： R. Gobinath R Boopathi Vijayalakshmi S D. Anu Disney P. Nirmala Priyadharshini K. Maheshwari Artificial intelligence and Data science E.G.S. Pillay Engineering College Nagapattinam Department of Electrical and Electronic Engineering Karpaga Vinayaga College of Engineering and Technology Tamilnadu Department of Electronics and communication Engineering Sona College of Technology Salem Tamilnadu Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai Department of Information Technology Adithya Institute of Technology Coimbatore Department of Artificial Intelligence and Data Science Sir Issac Newton College of Engineering and Technology Nagapattinam

ISBN: (数字)9798331509828

ISBN: (纸本)9798331509835

Low light region is one of the difficult scenarios for surveillance system, especially noisy, low-quality images may lead to poor object detection and scene analysis. To tackle this problem, we introduce a hybrid GAN - CNN framework for low light image denoising and quality enhancement. We develop a framework that combines the strengths of Generative Adversarial Networks (GANs) for photorealistic image generation and Convolutional Neural Networks (CNNs) for robust noise reduction. First denoising and feature extraction is done by the CNN module, and the GAN part further refines the denoised output to improve the perceptual quality of the generated images. We train and validate the proposed model in standard low light image dataset and show superior PSNR, SSIM, and visual clarity compared to state of art methods. We show that the hybrid GAN-CNN model successfully trades between image denoising accuracy and visual realism, thereby providing a viable alternative for enhancing surveillance performance in lowlight conditions. Keywords: Image denoising, GAN-CNN hybrid, low-light enhancement, PSNR, SSIM, surveillance systems.

关键词： Visualization Accuracy Surveillance Noise reduction Noise Generative adversarial networks Feature extraction Convolutional neural networks Image enhancement Image denoising

来源：评论

学校读者我要写书评

暂无评论

Compact Millimeter Wave Massive MIMO System Utilizing ESPAR

引用

IEEE Transactions on Communications 2025年

作者： Zhang, Chi Shen, Shanpu Li, Hongyu Ma, Dingfei Han, Zixiang Qian, Jun Clerckx, Bruno Murch, Ross Peng Cheng Laboratory Department of Broadband Communication Shenzhen518055 China University of Liverpool Department of Electrical Engineering and Electronics LiverpoolL69 3GJ United Kingdom Guangzhou511400 China Guangdong University of Technology College of Information Engineering Guangzhou China China Mobile Research Institute Future Research Lab Beijing100053 China The Hong Kong University of Science and Technology Department of Electronic and Computer Engineering Clear Water Bay Kowloon Hong Kong Imperial College London Department of Electrical and Electronic Engineering LondonSW7 2AZ United Kingdom The Hong Kong University of Science and Technology Department of Electronic and Computer Engineering Institute for Advanced Study Clear Water Bay Kowloon Hong Kong

In this work, we propose a compact millimeter wave (mmWave) massive multiple-input multiple-output (MIMO) system utilizing electronically steerable parasitic array radiator (ESPAR). We analyze the system and channel models for the compact mmWave massive MIMO system using a beamspace formulation and demonstrate that we can optimize the spectral efficiency of the compact mmWave massive MIMO system by jointly adjusting the variable reactive loads in the ESPAR with a digital beamformer. We formulate the compact mmWave massive MIMO system optimization problem to maximize spectral efficiency and propose an unconstrained optimization based algorithm with an initialization method. The spectral and energy efficiencies of the compact mmWave massive MIMO system are evaluated in comparison to conventional mmWave massive MIMO systems of the same antenna size using full-digital, fully-connected hybrid, and partially-connected hybrid beamforming. The results show that the compact mmWave massive MIMO system provides higher spectral efficiency than partially-connected hybrid beamforming. On top of this, it can provide higher energy efficiencies of around 3.21, 2.88, and 1.22 times compared to full-digital, fully-connected hybrid, and partially-connected hybrid beamforming but with lower hardware complexity and lower cost. Therefore, compact mmWave massive MIMO systems are a promising and effective alternative to conventional massive MIMO systems in millimeter wave (mmWave) communications. © 1972-2012 IEEE.

关键词： Beamforming

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：