检索结果-内蒙古大学图书馆

IEEE Symposium on High-Performance computer Architecture

作者： Wenju Zhao Pengcheng Yao Dan Chen Long Zheng Xiaofei Liao Qinggang Wang Shaobo Ma Yu Li Haifeng Liu Wenjing Xiao Yufei Sun Bing Zhu Hai Jin Jingling Xue National Engineering Research Center for Big Data Technology and System/Services Computing Technology and System Lab/Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China School of Computing National University of Singapore Singapore School of Computer Electronics and Information Guangxi University NanNing China School of Computer Science and Engineering University of New South Wales Sydney NSW Australia

ISBN: (数字)9798331506476

ISBN: (纸本)9798331506483

Hypergraph Neural Networks (HGNNs) are increasingly utilized to analyze complex inter-entity relationships. Traditional HGNN systems, based on a hyperedge-centric dataflow model, independently process aggregation tasks for hyperedges and vertices, leading to significant computational redundancy. This redundancy arises from recalculating shared information across different tasks. For the first time, we identify and harness implicit dataflows (i.e., dependencies) within HGNNs, introducing the microedge concept to effectively capture and reuse intricate shared information among aggregation tasks, thereby minimizing redundant computations. We have developed a new microedge-centric dataflow model that processes shared information as fine-grained microedge aggregation tasks. This dataflow model is supported by the Read-Process-Activate-Generate execution model, which aims to optimize parallelism among these tasks. Furthermore, our newly developed MeHyper, a microedge-centric HGNN accelerator, incorporates a decoupled pipeline for improved computational parallelism and a hierarchical feature management strategy to reduce off-chip memory accesses for large volumes of intermediate feature vectors generated. Our evaluation demonstrates that MeHyper substantially outperforms the leading CPUbased system PyG-CPU and the GPU-based system HyperGef, delivering performance improvements of $1,032.23 \times$ and $10.51 \times$, and energy efficiencies of $1,169.03 \times$ and $9.96 \times$, respectively.

关键词： Computational modeling Neural networks Redundancy Pipelines Memory management parallel processing Vectors Energy efficiency Hardware acceleration

来源：评论

学校读者我要写书评

暂无评论

Robust Iterative Permittivity Inversion Method Based on Reduced Order Models

Robust Iterative Permittivity Inversion Method Based on Redu...

引用

Antennas and Propagation & USNC/URSI national Radio Science Meeting

作者： Tianchen Shao Zekui Jia Maokun Li Fan Yang Shengheng Xu Department of Electronic Engineering Beijing National Research Center for Information Science and Technology Tsinghua University Beijing China Elmore Family School of Electrical and Computer Engineering Purdue University West Lafayette IN USA

ISBN: (数字)9798350369908

ISBN: (纸本)9798350369915

To mitigate the nonlinearity and cycle-skipping effects inherent in inverse scattering problems (ISPs), we propose a robust permittivity inversion method using the iterative data to Born (DtB) process. The DtB process is based on reduced order models (ROMs) obtained by the Galerkin approximation of wave operators. We incorporate the layer-peeling (LP) strategy to ensure efficient and stable convergence. Furthermore, two regularization techniques are implemented to improve the robustness of the inversion algorithm in noisy environments. The inversion algorithm is validated through a 2D example.

关键词： Scattering Approximation algorithms Robustness Reduced order systems Iterative methods Noise measurement Permittivity

来源：评论

学校读者我要写书评

暂无评论

A Graph Sequence Generator and Multi-head Self-attention Mechanism based Knowledge Graph Reasoning Architecture 26

A Graph Sequence Generator and Multi-head Self-attention Mec...

引用

26th International Conference on computer Supported Cooperative Work in Design, CSCWD 2023

作者： Wu, Yuejia Zhou, Jian-Tao College of Computer Science Inner Mongolia University Hohhot China National & Local Joint Engineering Research Center Intelligent Info. Proc. Technology for Mongolian Engineering Research Center of Ecological Big Data Ministry of Education Hohhot China Inner Mongolia Engineering Laboratory for Cloud Computing and Service Software Inner Mongolia Key Laboratory of Social Computing and Data Processing Hohhot China Inner Mongolia Key Laboratory of Discipline Inspection and Supervision Big Data Inner Mongolia Engineering Laboratory for Big Data Analysis Technology Hohhot China

ISBN: (纸本)9798350331684

Knowledge Graph (KG) is an essential research direction that involves storing and managing knowledge data, but its incompleteness and sparsity hinder its development in various applications. Knowledge Graph Reasoning (KGR) is an effective method to solve this limitation via reasoning missing knowledge based on existing knowledge. The graph Convolution Network (GCN) based method is one of the state-of-the-art approaches to this work. However, there are still some problems, such as the insufficient ability to perceive graph structure and the poor effect of learning data features which may limit the reasoning accuracy. This paper proposes a KGR architecture based on a graph sequence generator and multi-head self-attention mechanism, named GaM-KGR, to improve the above problems and enhance prediction accuracy. Specifically, the GaM-KGR first introduces the graph generation model into the field of KGR for graph representation learning to obtain the hidden features in the data so that enhancing the reasoning effect and then embeds the generated graph sequence into the multi-head self-attention mechanism for subsequent processing to improve the graph structure perception ability of the proposed architecture, so that it can process the graph structure data more appropriately. Extensive experimental results show that the GaM-KGR architecture can achieve the state-of-the-art prediction results of current GCN-based models. © 2023 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Multi-Spacecraft Pursuit-Evasion-Defense Strategy Based on Game Theory for On-Orbit Spacecraft Servicing

Multi-Spacecraft Pursuit-Evasion-Defense Strategy Based on G...

引用

IEEE Conference on Aerospace

作者： Xu Tang Dong Ye Kay-Soon Low Sha Luo Zhaowei Sun Research Center of Satellite Technology Harbin Institute of Technology Harbin China Satellite Technology and Research Centre National University of Singapore Singapore Electrical and Computer Engineering University of Canterbury Christchurch New Zealand

In the last decade, technologies such as spacecraft's navigation and guidance, rendezvous and docking have gradually matured. Moreover, research on spacecraft with autonomous maneuvering and intelligent decision-making capability for on-orbit servicing is also increasingly receiving more attention. With the rapid development of new space industry in particular large scale small satellite constellation, spacecraft that have the ability to avoid collisions, and on-orbit servicing spacecraft have become an important topic. Based on the game theory, this paper studies the process of terminal approach and rendezvous in the mission of spacecraft on-orbit servicing by taking terminal zero effort miss distance as the cost function. The established game control strategy is formulated differently from the traditional bilateral game as multiple spacecraft coexist in constellation have been taken into consideration. To reduce the control difficulty caused by the unknown terminal approaching time and the time to avoid collision, the time equation is established by calculating the corresponding time node to improve the designed game control strategies. Simulation study has been conducted and the results show the effectiveness of the proposed game control strategies.

关键词： Space vehicles Industries Simulation Small satellites Games Satellite navigation systems Cost function

来源：评论

学校读者我要写书评

暂无评论

Editorial

引用

Intelligent and Converged Networks 2022年第1期3卷 I0001-I0003页

作者： Linglong Dai Chan-Byoung Chae Shi Jin Marco Di Renzo Rui Zhang Beijing National Research Center for Information Science and Technology(BNRist)and the Department of Electronic Engineering Tsinghua UniversityBeijing 100084China School of Integrated Technology Yonsei Institute of Convergence TechnologyYonsei UniversityIncheon 406-840Republic of Korea. National Mobile Communications Research Laboratory Southeast UniversityNanjing 210096China. the UniversitéParis-Saclay CNRSCentraleSupélecLaboratoire des Signaux et Systèmes3 Rue Joliot-Curie91192 Gif-sur-YvetteFrance. Department of Electrical and Computer Engineering National University of SingaporeSingapore 117583Singapore

Reconfigurable Intelligent Surface(RIS),also known as intelligent reflecting surface or large intelligent surface,is an emerging new physical-layer technology in the field of wireless *** basic idea of RIS is to deploy a reconfigurable passive array in the environment to manipulate the propagation of electron-magnetic *** promises a new design paradigm for wireless communications,where the wireless propagation environment can be dynamically controlled,which is substantially different from the conventional design that focuses only on the transmitter and *** RIS-aided wireless communications,some of the current methodologies in conventional communication systems need to be revised,and some novel solutions are required to realize the potential benefits of the *** the number of publications about RIS has recently sharply increased,there are still many challenging issues to be extensively investigated,such as the RIS channel modeling,fundamental performance limits,the system design,joint optimization of the RIS and the transceivers,channel state information acquisition,and interdisciplinary applications.

关键词： passive sharply revised

来源：评论

学校读者我要写书评

暂无评论

A Near Lossless Learned Image Coding Network Quantization Approach for Cross-Platform Inference

A Near Lossless Learned Image Coding Network Quantization Ap...

引用

IEEE Visual Communications and Image Processing (VCIP)

作者： Xinyu Hang Chuanmin Jia Siwei Ma Wen Gao National Engineering Research Center on Visual Technology School of Computer Science Peking University China National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University China Wangxuan Institute of Computer Technology Peking University China

This paper presents an innovative pipeline design for the quantization of neural image codecs, ensuring robust and consistent deployment across various platform inferences. Our approach addresses a significant challenge prevalent in neural image compression networks: the lack of quantization methods for entropy probability hyper-priors, such as Gaussian mixture models (GMMs), in the existing literature. Our method serves as a solution to prevent decoding errors stemming from float-point discrepancies between the encoder and decoder, especially when executed on different platforms. By implementing a quantization scheme based on look-up tables (LUTs), we achieve precise quantization of GMM probability models with minimal performance degradation, approaching near losslessness. Moreover, our contribution offers a comprehensive quantization pipeline that facilitates dependable data transmission and harmonious synchronization of arithmetic coding algorithms between the encoder and decoder components. Empirical evidence highlights the effectiveness of our method, demonstrating seamless codec matching on diverse platforms and substantiating its capacity to enhance the integrity and security of compressed data. This work enhances the practical applicability of neural compression techniques across real-world scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Modelling in-device inference and classification of binary digits using nonlinear dynamics of spin Hall oscillator

Modelling in-device inference and classification of binary d...

引用

2023 IEEE International Magnetic Conference - Short Papers, INTERMAG Short Papers 2023

作者： Mohan, John Rex Yamanaka, Chisato Feng, Ryoyan Mathew, Arun Jacob Nakamura, Yoji Medwal, Rohit Gupta, Surbhi Rawat, Rajdeep Singh Fukuma, Yasuhiro Kyushu Institute of Technology Faculty of Computer Science and Systems Engineering Department of Physics and Information Technology Iizuka820-8592 Japan Indian Institute of Technology Kanpur Department of Physics Kanpur208016 India National Institute of Education Nanyang Technological University Natural Sciences and Science Education 637616 Singapore Kyushu Institute of Technology Research Center for Neuromorphic AI Hardware Kitakyushu808-0196 Japan

ISBN: (纸本)9798350338362

In this work, we employ micromagnetic modelling of a spin Hall oscillator for a direct inference and classification of binary digit inputs. The spectral characteristics of the oscillation is utilized for the classification. We observed a direct inference of binary digit inputs up to a sequence of four binary digits. Subsequently, handwritten digit image recognition is tested with the Modified national Institute of Standards and Testing (MNIST) handwritten digit database and acquired an accuracy of 88.6% with a linear classifier network. © 2023 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Novel deep recurrent neural structure with Bayesian distributed backpropagation for biomaterial model involving ferro–copper/blood nanofluids

引用

European Physical Journal Plus 2024年第1期139卷 42-42页

作者： Khan, Maryam Pervaiz Mukhtar, Roshana Chang, Chuan-Yu Chaudhary, Naveed Ishtiaq Shoaib, Muhammad Raja, Muhamad Asif Zahoor Department of Computer Science and Information Engineering Graduate School of Engineering Science and Technology National Yunlin University of Science and Technology Yunlin 64002 Taiwan Department of Computer Science and Information Engineering National Yunlin University of Science and Technology Yunlin 64002 Taiwan Future Technology Research Center National Yunlin University of Science and Technology Yunlin 64002 Taiwan AI center Yuan Ze University Taoyuan 320 Taiwan

The aim of the presented study is to portray the numerical treatment for biomaterial fluid flow models (BFFMs) involving magnetized ferro and copper nanoparticles dispersed in blood between two rotating disks by exploiting the knacks of layered recurrent neural networks with Bayesian distributed backpropagation (LRNN-BDB). Mathematical formulation of BFFMs is governed with PDEs that are renovated into nonlinear ordinary differential system by operating suitable transformations. The synthetic data are acquired numerically by simulated the implicit backward differentiation formulas to measure the impact of porosity permeability, Darcy–Forchheimer, and Joule heating for BFFMs involving both ferro and copper nanomaterial mixed with blood as a base fluid. The supervised computing paradigm of LRNN-BDB is executed on acquired datasets, and outcomes of LRNN-BDB are regularly overlapping with numerical observations for each variant of BFFMs with negligible error. The stupendous knacks of LRNN-BDB procedures are efficaciously depicted through mean squared error-based iterative convergence plots, adaptive controlling metrics of learning, error distribution statistics on histogram illustrations, and regression measures for exhaustive experimentation on BFFMs. © 2024, The Author(s), under exclusive licence to Società Italiana di Fisica and Springer-Verlag GmbH Germany, part of Springer Nature.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Early Tumor Diagnosis in Brain MR Images via Deep Convolutional Neural Network Model

引用

computers, Materials & Continua 2021年第8期68卷 2413-2429页

作者： Tapan Kumar Das Pradeep Kumar Roy Mohy Uddin Kathiravan Srinivasan Chuan-Yu Chang Shabbir Syed-Abdul School of Information Technology and Engineering Vellore Institute of TechnologyVellore632014India Department of Computer Science and Engineering Indian Institute of Information TechnologySurat395007India Research Quality Management Section King Abdullah International Medical Research CenterKing Saud bin Abdulaziz University for Health SciencesMinistry of National Guard-Health AffairsRiyadh11426Kingdom of Saudi Arabia Department of Computer Science and Information Engineering National Yunlin University of Science and TechnologyYunlin64002Taiwan Graduate Institute of Biomedical Informatics Taipei Medical UniversityTaipeiTaiwan

Machine learning based image analysis for predicting and diagnosing certain diseases has been entirely trustworthy and even as efficient as a domain expert’s ***,the style of non-transparency functioning by a trained machine learning system poses a more significant impediment for seamless knowledge trajectory,clinical mapping,and delusion *** this proposed study,a deep learning based framework that employs deep convolution neural network(Deep-CNN),by utilizing both clinical presentations and conventional magnetic resonance imaging(MRI)investigations,for diagnosing tumors is *** research aims to develop a model that can be used for abnormality detection over MRI data quite efficiently with high *** research is based on deep learning and Deep-CNN was deployed to examine the MR brain image for tracing the *** system runs on Tensor flow and uses a feature extraction module in DeepCNN to elicit the factors of that part of the image from where underlying issues are identified and subsequently succeeded in prediction of the disease in the MR *** results of this study showed that our model did not have any adverse effect on classification,achieved higher accuracy than the peers in recent years,and attained good detection outcomes including case of *** the future work,further improvement can be made by designing models that can drastically reduce the parameter space without affecting classification accuracy.

关键词： Deep learning convolutional neural network brain tumor magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Cascaded Network with Hierarchical Self-Distillation for Sparse Point Cloud Classification

Cascaded Network with Hierarchical Self-Distillation for Spa...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Kaiyue Zhou Ming Dong Peiyuan Zhi Shengjin Wang Department of Electronic Engineering Tsinghua University China Beijing National Research Center for Information Science and Technology (BNRist) China Department of Computer Science Wayne State University USA

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Incomplete point clouds that are generally scanned with flaws or large gaps can cause to inaccurate predictions by learning-based classification methods. To address this issue, in this paper, we propose an end-to-end architecture that compensates for and identifies partial point clouds on the fly. First, we propose a cascaded solution that integrates both the upstream and downstream networks simultaneously, allowing the task-oriented downstream to identify the points generated by the completion-oriented upstream. These two streams complement each other, resulting in improved performance for both completion and downstream-dependent tasks. Second, to explicitly understand the predicted points’ pattern, we introduce hierarchical self-distillation (HSD), which can be applied to arbitrary hierarchy-based point cloud methods. On the classification task, our proposed method performs competitively on the synthetic dataset and achieves superior results on the challenging real-world benchmark when compared to the state-of-the-art models.

关键词： Point cloud compression Predictive models Data collection Benchmark testing Streams Synthetic data

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：