检索结果-内蒙古大学图书馆

GNN-Assisted BiG-AMP: Joint Channel Estimation and Data Detection for Massive MIMO Receiver

IEEE Transactions on Wireless Communications 2025年第6期24卷 4631-4646页

作者： Liu, Zishen Wu, Nan He, Dongxuan Yuan, Weijie Li, Yonghui Quek, Tony Q. S. School of Information and Electronics Beijing Institute of Technology Beijing100081 China School of System Design and Intelligent Manufacturing Shenzhen Key Laboratory of Robotics and Computer Vision Southern University of Science and Technology Shenzhen518055 China School of Electrical and Information Engineering The University of Sydney SydneyNSW2008 Australia Singapore University of Technology and Design 487372 Singapore Department of Electronic Engineering Kyung Hee University Yongin17104 Korea Republic of

In this paper, we develop a graph neural network (GNN)-assisted bilinear inference approach to enhance the receiver performance of the MIMO system through message passing-based joint channel estimation and data detection (JCD). Specifically, based on the bilinear generalized approximate message passing (BiG-AMP) framework and conditional correlation of signal, we propose a GNN-assisted BiG-AMP (GNN-BiGAMP) approach, which integrates a GNN module into the data-detection-loop to compensate the inaccurate marginal likelihood approximation. By leveraging the coupling between the channel and received symbols, a bilinear GNN-assisted BiG-AMP (BiGNN-BiGAMP) JCD receiver is further proposed. This method incorporates two GNNs with similar graph representation into the bilinear posterior estimation loops, which not only compensates for approximation errors but also alleviates performance loss due to premature variance convergence, thereby enhancing the receiver performance significantly. To fully exploit the supervised information from channel estimation and data detection, we propose a multitask learning based training scheme, which coordinates GNNs with different tasks in two loops. Simulation results show that our proposed GNN-assisted JCD receivers significantly outperform other JCD counterparts in terms of both channel estimation and data detection. © 2025 IEEE. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Textile patch antenna using fleece and felt substrates

Textile patch antenna using fleece and felt substrates

引用

2024 Malaysia-Japan Workshop on Radio technology, MJWRT 2024

作者： Azahari, B.A. Kamardin, K. Yamada, Y. Othman, M.S.F. Department of Electronic System Engineering Malaysia-Japan International Institute of Technology Universiti Teknologi Malaysia Kuala Lumpur Malaysia Wireless Communication Centre Universiti Teknologi Malaysia Kuala Lumpur Malaysia

The application of textile patch antennas can be realized by integrating high-gain antennas into clothing, offering innovative solutions for wearable technology. For example, patients clothing where it can transmit the data from the heart monitoring wirelessly. This study explores the main aspects of the textile patch antenna using fleece and felt substrates. The electromagnetic simulation of the calculated parameters for the patch antenna, the fabrication method for fleece and felt substrates using conductive copper paint for both the patch and the ground plane or conductive material part, and the measurement process for the fabricated antennas. Measurements were carried out using a Vector Network Analyzer (VNA) for input impedance and an anechoic chamber for assessing radiation patterns and gain. The results from the electromagnetic simulations and measurements showed good agreement, except for the gain of the felt antenna, which may be attributed to either a faulty felt antenna or measurement error. © 2024 Institute of Physics Publishing. All rights reserved.

关键词： Felt

来源：评论

学校读者我要写书评

暂无评论

Calibration of RGB-D Camera Using Depth Correction Model

Calibration of RGB-D Camera Using Depth Correction Model

引用

2021 International Conference on Robotics automation and Intelligent Control, ICRAIC 2021

作者： Zhou, Yang Chen, Danqing Wu, Jun Huang, Mingyi Weng, Yubin School of Electronic Engineering and Automation Guilin University of Electronic Technology Guangxi Guilin China Department of Infrastructure Construction Guilin University of Electronic Technology Guangxi Guilin China

This paper proposes a calibration method of RGB-D camera, especially its depth camera. First, use a checkerboard calibration board under auxiliary Infrared light source to collect calibration images. Then, the internal and external parameters of the depth camera are calculated by Zhang's calibration method, which improves the accuracy of the internal parameter. Next, the depth correction model is proposed to directly calibrate the distortion of the depth image, which is more intuitive and faster than the disparity distortion correction model. This method is simple, high-precision, and suitable for most depth cameras. © 2022 Institute of Physics Publishing. All rights reserved.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

Robot Hand-eye Calibration Method Incorporating Filtering Techniques 25

Robot Hand-eye Calibration Method Incorporating Filtering Te...

引用

25th IEEE International Conference on Industrial technology, ICIT 2024

作者： Guo, Peng Si, Weiyong Yang, Chenguang School Of Automation Science And Engineering South China University Of Technology Guangzhou China School Of Computer Science And Electronic Engineering University Of Essex Colchester United Kingdom University Of Liverpool Department Of Computer Science Liverpool United Kingdom

ISBN: (纸本)9798350340266

Hand-eye calibration is the foundation of visual servo for robotic tasks, aiming to determine the rigid transfor-mation matrix between the robot and the vision system. The accuracy of hand-eye calibration affects the robot's ability to accurately perform tasks. The classical form of the hand-eye calibration is to solve the equation 'AX = XB'. The algorithms for solving this problem mainly divided into two categorie: step-wise and simultaneous solutions for the rotation and translation components. Due to the noise in the collected data, the calculation accuracy is inevitably affected. In this paper, we introduce a filtering approach for hand-eye calibration. First, we design the movement path of the robot arm end effector, then summarize the variation patterns of parameters, and finally use these patterns to filter the actually collected data. Experimental results on our custom dataset and the robot arm platform demonstrate that our proposed method can reduce reprojection error and improve the accuracy of hand-eye calibration. © 2024 IEEE.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

Study on influence factors of dilation uniformity in pulse-dilation framing camera 8

Study on influence factors of dilation uniformity in pulse-d...

引用

8th Symposium on Novel Photoelectronic Detection technology and Applications

作者： Wu, Siqi Bai, Yanli Zhong, Si Guilin University of Electronic Technology School of Electronic Engineering and Automation Guilin541004 China Guilin University of Electronic Technology Teaching Practice Department Guilin541004 China

ISBN: (数字)9781510653122

ISBN: (纸本)9781510653115

The pulse-dilation framing camera is modeled and the cause of its dilation non-uniformity is introduced, the influence factors of dilation uniformity is studied and the non-uniformity is quantitatively analyzed using relative errors. The research results show that the dilation uniformity along the photocathode(PC) is gradually get worse by decreasing acceleration energy, increasing gradient of dilation pulse and enlarging drift length. Especially, the most and minimal serious effects are the gradient and the drift length, respectively. When the length of the PC is 80 mm, the PC voltage is -2 kV and drift length is 0.4 m, with increasing the gradient from 1 V/ps to 5 V/ps, the dilating relative errors is increased from 20.9% to 620.2%. When the PC voltage is -2 kV and gradient is 4 V/ps, with increasing drift length from 0.4 m to 0.8 m, the relative errors is increased from 261.5% to 269.6%. The research is discussed the deficiency of temporal performance in the pulse-dilation framing camera with large PC. © 2022 SPIE

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

Large circuit models: opportunities and challenges

引用

Science China(Information Sciences) 2024年第10期67卷 25-66页

作者： Lei CHEN Yiqi CHEN Zhufei CHU Wenji FANG Tsung-Yi HO Ru HUANG Yu HUANG Sadaf KHAN Min LI Xingquan LI Yu LI Yun LIANG Jinwei LIU Yi LIU Yibo LIN Guojie LUO Hongyang PAN Zhengyuan SHI Guangyu SUN Dimitrios TSARAS Runsheng WANG Ziyi WANG Xinming WEI Zhiyao XIE Qiang XU Chenhao XUE Junchi YAN Jun YANG Bei YU Mingxuan YUAN Evangeline F.Y.YOUNG Xuan ZENG Haoyi ZHANG Zuodong ZHANG Yuxiang ZHAO Hui-Ling ZHEN Ziyang ZHENG Binwu ZHU Keren ZHU Sunan ZOU Huawei Noah’s Ark Lab School of Integrated Circuits Peking University Faculty of Electrical Engineering and Computer Science Ningbo University Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Department of Computer Science and Engineering The Chinese University of Hong Kong School of Integrated Circuits Southeast University Huawei HiSilicon Peng Cheng Laboratory School of Computer Science Peking University School of Microelectronics State Key Laboratory of Integrated Chips and System Fudan University School of Artificial Intelligence Shanghai Jiao Tong University

Within the electronic design automation(EDA) domain, artificial intelligence(AI)-driven solutions have emerged as formidable tools, yet they typically augment rather than redefine existing methodologies. These solutions often repurpose deep learning models from other domains, such as vision, text, and graph analytics, applying them to circuit design without tailoring to the unique complexities of electronic circuits. Such an “AI4EDA” approach falls short of achieving a holistic design synthesis and understanding,overlooking the intricate interplay of electrical, logical, and physical facets of circuit data. This study argues for a paradigm shift from AI4EDA towards AI-rooted EDA from the ground up, integrating AI at the core of the design process. Pivotal to this vision is the development of a multimodal circuit representation learning technique, poised to provide a comprehensive understanding by harmonizing and extracting insights from varied data sources, such as functional specifications, register-transfer level(RTL) designs, circuit netlists,and physical layouts. We champion the creation of large circuit models(LCMs) that are inherently multimodal, crafted to decode and express the rich semantics and structures of circuit data, thus fostering more resilient, efficient, and inventive design methodologies. Embracing this AI-rooted philosophy, we foresee a trajectory that transcends the current innovation plateau in EDA, igniting a profound “shift-left” in electronic design methodology. The envisioned advancements herald not just an evolution of existing EDA tools but a revolution, giving rise to novel instruments of design-tools that promise to radically enhance design productivity and inaugurate a new epoch where the optimization of circuit performance, power, and area(PPA) is achieved not incrementally, but through leaps that redefine the benchmarks of electronic systems' capabilities.

关键词： AI-rooted EDA large circuit models (LCMs) multimodal circuit representation learning circuit optimization

来源：评论

学校读者我要写书评

暂无评论

Online Ortho-rectification and Mosaic of UAV aerial imagery for emergency remote sensing 7

Online Ortho-rectification and Mosaic of UAV aerial imagery ...

引用

2022 7th International Conference on electronic technology and Information Science, ICETIS 2022

作者： Wu, Jun Pan, Shuting Luo, Ying Chen, Danqing School of Electronic Engineering and Automation Guilin University of Electronic Technology Guangxi Guilin China Department of Infrastructure Construction Guilin University of Electronic Technology Guangxi Guilin China

ISBN: (纸本)9783800757794

Toward timely response to natural disasters, an photogrametry processing system based on ARM+GPU architecture of the HiSilicon embedded platform is established, so as to Ortho-rectify and mosaic UAV images online. More Specifically, ARM is responsible for data reception and storage, and GPU is responsible for data processing. By making full use of the GPU parallel structure and adopting the optimization of execution configuration, the processing efficiency of UAV images is greatly improved. The experimental results show that, for UAV image with a GSD of 0.05 meters and resolution of 6000*4000 pixels, the cost time of orthorectification can reach less than 0.1 seconds per image. Established photogrametry processing system also has obvious advantages in terms of volume, power consumption, real-time performance, and system stability. © VDE VERLAG GMBH ∙ Berlin ∙ Offenbach.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Empowering Local Differential Privacy: A 5718 TOPS/W Analog PUF-Based In-Memory Encryption Macro for Dynamic Edge Security

Empowering Local Differential Privacy: A 5718 TOPS/W Analog ...

引用

2024 IEEE Symposium on VLSI technology and Circuits, VLSI technology and Circuits 2024

作者： Lin, Chih-Sheng Chiou, Bo-Cheng Yang, Yin-Jia Su, Jian-Wei Tseng, Kuo-Hua Ho, Yun-Ting Lai, Chih-Ming Li, Sih-Han Chang, Tian-Sheuan Chang, Shan-Ming Sheu, Shyh-Shyuan Lo, Wei-Chung Chang, Shih-Chieh Hou, Tuo-Hung Industrial Technology Research Institute Electronic and Optoelectronic System Research Laboratories Hsinchu Taiwan Institute of Electronics National Yang Ming Chiao Tung University Department of Electrical Engineering Hsinchu Taiwan

ISBN: (纸本)9798350361469

In the realm of artificial intelligence (AI), data privacy is crucial. This study demonstrates the first In-Memory Encryption (IME) macro utilizing analog Physical Unclonable Function (aPUF) for efficient local differential privacy (LDP). The hardware utilizes a highly parallel 22-nm SRAM 4b/4b/5b (I/W/O) analog in-memory computation (aIMC) macro. Sense amplifier (SA) variation and a time-based confusion (TBC) circuit generate time-varying noise, enhancing dynamic LDP protecting strength to 4.2. Furthermore, the energy efficiency of 5718 TOPS/W underscores significant advancements in robust protection without compromising high energy efficiency, particularly benefiting edge LDP security. © 2024 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CareGenic: AI/ML Based Interactive Medicines Prescription system

CareGenic: AI/ML Based Interactive Medicines Prescription Sy...

引用

Electrical Power engineering, Communication and Computing technology(ODICON), Odisha International Conference on

作者： Syed Ammar Ahmed Shaikh Umair Ritesh Prasad Shashank Kumar Singh Anirban J. Hati Department of Electronic System Engineering National Institute of Electronics and Information technology Aurangabad India Sr. Technical Assistant Department of Electronic System Engineering National Institute of Electronics and Information technology Aurangabad India Scientist B Department of Electronic System Engineering National Institute of Electronics and Information technology Aurangabad India Scientist C Department of Electronic System Engineering National Institute of Electronics and Information technology Aurangabad India

ISBN: (数字)9798350354379

ISBN: (纸本)9798350354386

CareGenic leverages Artificial Intelligence (AI) and Machine Learning (ML) to develop a robust system for predicting illnesses based on symptoms and recommending appropriate medications. This study addresses the growing need for intelligent healthcare solutions that can assist medical professionals and improving patient outcomes. The system utilizes a Random Forest algorithm trained on extensive healthcare datasets to predict illnesses accurately. Furthermore, it recommends medications based on the predicted illnesses, ensuring a holistic approach to patient care. Implemented on a Raspberry Pi 3 with an interactive LCD display interface, CareGenic provides an accessible and efficient tool for healthcare environments. The system's performance was evaluated using metrics such as accuracy, precision, and recall, achieving 95%, 93%, and 92%, respectively. These results demonstrate the efficacy of CareGenic in real-world scenarios. Compared to existing systems like IBM Watson Health and Google Health, CareGenic offers a more integrated approach by combining symptom-based predictions with medication recommendations. Future work will focus on enhancing the model's accuracy and expanding its capabilities to cover a broader range of illnesses and medications. This paper provides detailed insights into the system's architecture, methodology, implementation, and evaluation, highlighting the significant potential of AI and ML in revolutionizing healthcare.

关键词： Technological innovation Power engineering Accuracy system performance Medical services Prediction algorithms Liquid crystal displays Internet Medical diagnostic imaging Random forests

来源：评论

学校读者我要写书评

暂无评论

Perturbation Event Oriented Dynamic Task Scheduling Algorithm for Parallel Testing of Control systems

Perturbation Event Oriented Dynamic Task Scheduling Algorith...

引用

2024 IEEE International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2024

作者： Chen, Jingyi Wang, Shenhang Tong, Xiaoxuan Xiang, Gang Yu, Yang Zhan, Ziyuan School of Electronic and Information Engineeer Harbin Institute of Technology Harbin China Beijing Aerospace Automatic Control Institute System Design Department Beijing China Beijing Aerospace Automatic Control Institute Beijing China Beijing Aerospace Automatic Control Institute Department of System Engineering Beijing China

ISBN: (纸本)9798350388855

Task scheduling algorithms are key to research and practice in parallel testing techniques, especially in control system applications. The complexity of control system testing requires higher scheduling efficiency. However, perturbation events caused by test equipment problems, data transmission obstacles, or task changes are almost unavoidable and may reduce the scheduling effectiveness or even lead to system crashes. Therefore, in this paper, based on the analysis of the dynamic test scheduling model, a disturbance factor is designed to judge the urgency of disturbance events for evaluating the dynamic scheduling cycle. On this basis, based on the comprehensive rescheduling index, a suitable adjustment strategy is selected to formulate the dynamic test scheduling scheme. The experimental results show that the algorithm proposed in this paper can achieve fast response capability for different disturbance events and exhibit good adaptivity. © 2024 IEEE.

关键词： Scheduling algorithms

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：