检索结果-内蒙古大学图书馆

2020 IEEE International Conference on Artificial Intelligence and Computer Applications, ICAICA 2020

作者： Xu, Zhenpeng Chen, Xinhai Chi, Lihua Liu, Jie Gong, Chunye Sci. and Technol. on Parallel and Distributed Proc. Lab. Lab. of Software Eng. for Complex Systems National University of Defense Technology Changsha China College of Computer Science and Electronic Engineering Hunan University Changsha China

ISBN: (纸本)9781728170046

With the rapid development of highperformance computing, computational fluid dynamics (CFD) has become an important part of hydrodynamics and aerodynamics. Mesh quality is the key factor that affects the accuracy and efficiency of CFD numerical calculation. However, the current the process of mesh quality discrimination is very time-consuming. The manpower time needed for this process takes up a large proportion in the whole numerical calculation process. A large number of artificial intelligence algorithms have been put forward to replace the human to efficiently complete all kinds of tedious tasks. In this paper, we propose a convolutional neural network (CNN) based mesh quality discrimination method, MeshNet. MeshNet uses residual neural network structure to learn mesh features and automatically judge the mesh quality. The experimental results show that the proposed network can greatly save labor time cost and achieve an accuracy of 94.41% for mesh quality discrimination. © 2020 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

TempDiff: Enhancing Temporal-awareness in Latent Diffusion for Real-World Video Super-Resolution

引用

COMPUTER GRAPHICS FORUM 2024年第7期43卷

作者： Jiang, Q. Wang, Q. L. Chi, L. H. Chen, X. H. Zhang, Q. Y. Zhou, R. Deng, Z. Q. Deng, J. S. Tang, B. B. Lv, S. H. Liu, J. Natl Univ Def Technol Sci & Technol Parallel & Distributed Proc Lab Changsha Peoples R China Natl Univ Def Technol Lab Digitizing Software Frontier Equipment Changsha Peoples R China Hunan GuoKe Computil Technol Co Ltd Changsha Peoples R China Zhousuyue Digital Video Ltd Changsha Peoples R China Hunan Malanshan Video Adv Technol Res Inst Co LTD Changsha Peoples R China Natl Univ Def Technol Coll Adv Interdisciplinary Studies Changsha Peoples R China Changsha Plan Technol Co Ltd Changsha Peoples R China Lifezone Ltd & KellTech Ltd Ebene Mauritius

Latent diffusion models (LDMs) have demonstrated remarkable success in generative modeling. It is promising to leverage the potential of diffusion priors to enhance performance in image and video tasks. However, applying LDMs to video super-resolution (VSR) presents significant challenges due to the high demands for realistic details and temporal consistency in generated videos, exacerbated by the inherent stochasticity in the diffusion process. In this work, we propose a novel diffusion-based framework, Temporal-awareness Latent Diffusion Model (TempDiff), specifically designed for real-world video super-resolution, where degradations are diverse and complex. TempDiff harnesses the powerful generative prior of a pre-trained diffusion model and enhances temporal awareness through the following mechanisms: 1) Incorporating temporal layers into the denoising U-Net and VAE-Decoder, and fine-tuning these added modules to maintain temporal coherency;2) Estimating optical flow guidance using a pre-trained flow net for latent optimization and propagation across video sequences, ensuring overall stability in the generated high-quality video. Extensive experiments demonstrate that TempDiff achieves compelling results, outperforming state-of-the-art methods on both synthetic and real-world VSR benchmark datasets. Code will be available at https://***/jiangqin567/TempDiff

关键词： CCS Concepts • Computing methodologies → Computer vision tasks

来源：评论

学校读者我要写书评

暂无评论

MVE-Net: An Automatic 3-D Structured Mesh Validity Evaluation Framework Using Deep Neural Networks

引用

COMPUTER-AIDED DESIGN 2021年 141卷 103104-103104页

作者： Chen, Xinhai Liu, Jie Gong, Chunye Li, Shengguo Pang, Yufei Chen, Bo Natl Univ Def Technol Sci & Technol Parallel & Distributed Proc Lab Changsha 410073 Peoples R China Natl Univ Def Technol Lab Software Engn Complex Syst Changsha 410073 Peoples R China China Aerodynam Res & Dev Ctr Mianyang 621000 Sichuan Peoples R China

An important objective of quality control in CFD pre-processing is the facility to indicate to the engineer the validity of the generated mesh. Existing quality measures mainly focus on the subjective evaluation of the shape information of mesh elements, such as aspect ratio, skewness, and shape regularity, and often ignore mesh distribution details. In order to ensure a precise evaluation result, these measures usually work with knowledge-based manual re-evaluation, which heavily increases the meshing cost and hampers automation of the meshing process. In this work, we propose an automatic 3-D structured mesh validity evaluation framework, MVE-Net. It takes mesh files as input, employs deep neural networks to study the role of mesh point distribution on numerical accuracy, and finally outputs the overall validity of the mesh for the simulation. For training the network, we introduce the first 3-D mesh benchmark dataset containing 24576 labeled structured meshes with different models and sizes. The experimental results on the dataset demonstrate the potential of deep neural networks in 3-D mesh validity evaluation and the effectiveness of MVE-Net. The well-trained MVE-Net can be a useful and helpful tool in the fully automatic pre-processing procedure. (C) 2021 Elsevier Ltd. All rights reserved.

关键词： Computational fluid dynamics (CFD) Mesh validity Benchmark dataset Neural network

来源：评论

学校读者我要写书评

暂无评论

A linearized coarse mesh finite difference preconditioner for the within-group Krylov subspace iteration based on two-dimensional method of characteristics

引用

ANNALS OF NUCLEAR ENERGY 2021年 151卷 107889-107889页

作者： Zhang, Guangchun Li, Zhifeng Liu, Jie Natl Univ Def Technol Sci & Technol Parallel & Distributed Proc Lab Changsha 410073 Peoples R China Natl Univ Def Technol Lab Software Engn Complex Syst Changsha 410073 Peoples R China South China Univ Technol Sch Elect Power Guangzhou 510640 Peoples R China

In this work, a preconditioner is developed based on the linear coarse mesh finite difference (CMFD) formulation for the flexible generalized minimal residual (FGMRES) algorithm, and applied to accelerate within-group Krylov iterations based on the two-dimensional (2-D) method of characteristics (MOC). The conventional CMFD method is linearized by replacing the multiplicative updating operator with an additive correction operator in the prolongation step. The effectiveness of the linearized CMFD preconditioner for problems featuring steep flux gradients and high scattering ratios can be demonstrated by the numerical results for the IAEA LWR pool reactor problem. The total FGMRES iterations and computing time were decreased by 52.7% and 41.8%, respectively. However, only modest efficiency improvements were achieved for the 2-D C5G7 and the KAIST-2A benchmark problems, revealing the degraded performance of the linearized CMFD preconditioner for problems with strong local heterogeneities. (C) 2020 Elsevier Ltd. All rights reserved.

关键词： Method of characteristics Krylov subspace iteration method Preconditioner IAEA LWR pool reactor problem 2-D C5G7 benchmark problem KAIST-2A benchmark problem

来源：评论

学校读者我要写书评

暂无评论

Towards more effective and economic sparsely-activated model

arXiv

引用

arXiv 2021年

作者： Jiang, Hao Zhan, Ke Qu, Jianwei Wu, Yongkang Fei, Zhaoye Zhang, Xinyu Chen, Lei Dou, Zhicheng Qiu, Xipeng Guo, Zikai Lai, Ruofei Wu, Jiawen Hu, Enrui Zhang, Yinxia Jia, Yantao Yu, Fan Cao, Zhao Distributed and Parallel Software Lab Huawei China School of Computer Science Fudan University Department of Computer Science and Engineering Hong Kong University of Science and Technology Gaoling School of Artificial Intelligence Renmin University of China

The sparsely-activated models have achieved great success in natural language processing through large-scale parameters and relatively low computational cost, and gradually become a feasible technique for training and implementing extremely large models. Due to the limit of communication cost, activating multiple experts is hardly affordable during training and inference. Therefore, previous work usually activate just one expert at a time to alleviate additional communication cost. Such routing mechanism limits the upper bound of model performance. In this paper, we first investigate a phenomenon that increasing the number of activated experts can boost the model performance with higher sparse ratio. To increase the number of activated experts without an increase in computational cost, we propose SAM (Switch and Mixture) routing, an efficient hierarchical routing mechanism that activates multiple experts in a same device (GPU). Our methods shed light on the training of extremely large sparse models and experiments prove that our models can achieve significant performance gain with great efficiency improvement. Copyright © 2021, The Authors. All rights reserved.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Unraveling the Mechanism of Near-Infrared Thermally Activated Delayed Fluorescence of TPA-Based Molecules: Effect of Hydrogen Bond Steric Hindrance

引用

JOURNAL OF PHYSICAL CHEMISTRY A 2021年第14期125卷 2905-2912页

作者： Leng, Can You, Sheng Si, Yubing Qin, Hai-Mei Liu, Jie Huang, Wei-Qing Li, Keqin Natl Univ Def Technol Sci & Technol Parallel & Distributed Proc Lab Changsha 410073 Peoples R China Natl Univ Def Technol Lab Software Engn Complex Syst Changsha 410073 Peoples R China Natl Supercomp Ctr Changsha Changsha 410082 Peoples R China Xiamen Univ Coll Chem & Chem Engn Fujian Prov Key Lab Theoret & Computat Chem Xiamen 361005 Peoples R China Hunan Univ Sch Phys & Elect Dept Appl Phys Changsha 410082 Peoples R China Zhengzhou Univ Coll Chem Zhengzhou 450001 Peoples R China Hunan Univ Coll Comp Sci & Elect Engn Changsha 410082 Peoples R China SUNY Coll New Paltz Dept Comp Sci New Paltz NY 12561 USA

A recently synthesized novel molecule (named CAT-1) exhibits intriguing near-infrared (NIR) thermally activated delayed fluorescence (TADF) close to 1000 nm wavelength;however, the mechanism behind these intrinsic properties is not fully understood. Herein, we unravel that the fluorescence emission spectrum with a broad wavelength range (770-950 nm) of CAT-1 is primarily induced by hydrogen bond steric hindrance based on density functional theory and Marcus theory. It is found that the hydrogen bond steric hindrance plays a critical role in inhibiting the twist of the configuration of different excited states, which leads to the minor driving force for fast electron trapping between the excited states, as well as small internal reorganization energy caused by less changed geometric configuration. Furthermore, such steric hindrance will cause a more distorted plane, resulting in a less favorable electron delocalization. A faster reverse intersystem crossing (RISC) rate is then obtained due to the nearly unchanged conformation between excited states caused by steric hindrance, although the spin-orbit coupling is small. Consequently, the NIR TADF with a longer wavelength can be emitted in CAT-1. This work shows that the hydrogen bond steric hindrance can fine-tune the electronic interactions of the donor and acceptor units to control the TADF.

关键词： Electrical energy Noncovalent interactions Quantum mechanics Excited states Molecules

来源：评论

学校读者我要写书评

暂无评论

A region-based hypergraph network for joint entity-relation extraction

引用

KNOWLEDGE-BASED SYSTEMS 2021年 228卷 107298-107298页

作者： Wan, Qian Wei, Luona Chen, Xinhai Liu, Jie Natl Univ Def Technol Sci & Technol Parallel & Distributed Proc Lab Changsha 410073 Hunan Peoples R China Natl Univ Def Technol Lab Software Engn Complex Syst Changsha 410073 Hunan Peoples R China Natl Univ Def Technol Coll Syst Engn Changsha 410073 Hunan Peoples R China

In joint entity and relation extraction, the input document is divided into multiple potential entity regions and context regions, where the characteristics of entities and their relations can often be reflected in the context. Therefore, an effective joint modeling method designed toward the features of different regions can lead to superior performance of joint entity and relation extraction. Previous works tend to implement in-depth modeling only for potential entity regions, ignoring the importance of contextual information for joint entity and relation extraction. In this paper, we propose a Region-based Hypergraph Network (RHGN) for joint entity and relation extraction. The RHGN introduces the concept of regional hypernodes for the first time, and proposes a cooperative method of GCN and BiLSTM to generate hypernodes for each region. Then, a region-based relation hypergraph is constructed for fairly and efficiently aggregate the features of all regions in the sentence. In order to initialize and update the features of the edges and hypernodes in the hypergraph, a Sequence-Enhanced Graph (SEG) unit is designed. Finally, we perform comparison experiments with existing competitive models on three public datasets: the CoNLL04, SciERC and ADE datasets. Experimental results demonstrate that our model achieves a significant improvement over the previous models on both entity recognition and relation extraction, and it also shows superior performance for dataset with nested entities. Extensive additional experiments further confirm the effectiveness of our approach. (C) 2021 Elsevier B.V. All rights reserved.

关键词： Information extraction Named entity recognition Relation extraction Graph network Deep learning

来源：评论

学校读者我要写书评

暂无评论

PINN-FFHT: A physics-informed neural network for solving fluid flow and heat transfer problems without simulation data

引用

INTERNATIONAL JOURNAL OF MODERN PHYSICS C 2022年第12期33卷 2250166-2250166页

作者： Zhang, Qingyang Guo, Xiaowei Chen, Xinhai Xu, Chuanfu Liu, Jie Natl Univ Def Technol Sci & Technol Parallel & Distributed Proc Lab Changsha 410073 Hunan Peoples R China Natl Univ Def Technol Inst Quantum Informat Changsha 410073 Hunan Peoples R China Natl Univ Def Technol State Key Lab High Performance Comp Changsha 410073 Hunan Peoples R China Natl Univ Def Technol Lab Software Engn Complex Syst Changsha 410073 Hunan Peoples R China

In recent years, physics-informed neural networks (PINNs) have come to the foreground in many disciplines as a new way to solve partial differential equations. Compared with traditional discrete methods and data-driven surrogate models, PINNs can learn the solutions of partial differential equations without relying on tedious mesh generation and simulation data. In this paper, an original neural network structure PINN-FFHT based on PINNs is devised to solve the fluid flow and heat transfer problems. PINN-FFHT can simultaneously predict the flow field and take into consideration the influence of flow on the temperature field to solve the energy equation. A flexible and friendly boundary condition (BC) enforcement method and a dynamic strategy that can adaptively balance the loss term of velocity and that of temperature are proposed for training PINN-FFHT, serving to accelerate the convergence and improve the accuracy of predicted results. Three cases are predicted to validate the capabilities of the network, including the laminar flow with the Dirichlet BCs in heat transfer, respectively, under the Cartesian and the cylindrical coordinate systems, and the thermally fully developed flow with the Neumann BCs in heat transfer. Results show that PINN-FFHT is faster in convergence speed and higher in accuracy than traditional PINN methods.

关键词： Physics-informed neural networks (PINNs) partial differential equations fluid flow heat transfer boundary conditions

来源：评论

学校读者我要写书评

暂无评论

Exploring the Relationship Between Developer Activities and Profile Images on GitHub 19

Exploring the Relationship Between Developer Activities and ...

引用

11th Asia-Pacific Symposium on Internetware (Internetware)

作者： Wu, Yiwen Zhang, Yang Wang, Tao Wang, Huaimin Natl Univ Def Technol Key Lab Parallel & Distributed Comp Lab Software Engn Complex Syst Coll Comp Changsha 410073 Peoples R China

ISBN: (纸本)9781450377010

In the GitHub platform, social media profile images are one of many visual components of developers. Besides, developer activities such as reporting issues or following other developers are regarded as important development and self-expression behaviors. However, to the best of our knowledge, no study has yet been conducted to study the relationship between GitHub developer activities and profile images. In this paper, we aim to investigate the relationship between developer activities and profile images to gain some insights into the developers' internal properties. During our experiments, we manually classify profile images into seven categories. Next, we investigate the relationship between developer's demographic information and developer activity. Further, using logistic regression analysis, when controlled for various variables, we statistically identify and quantify the relationships between developer activities and profile image categories. We find that several profile image categories significantly correlate with developer's demographic information and activities. We also provide a rich resource of research ideas for further study. Our examination and analysis provide insights into the developers' internal properties when using different profile images. Moreover, this study is the first step in understanding the relationship between developer activities and profile images on GitHub. CCS CONCEPTS software and its engineering -> Collaboration in software development;Human-centered computing -> Empirical studies in collaborative and social computing.

关键词： GitHub Internal property Developer activity Profile image

来源：评论

学校读者我要写书评

暂无评论

An improved data-free surrogate model for solving partial differential equations using deep neural networks

引用

SCIENTIFIC REPORTS 2021年第1期11卷 1-17页

作者： Chen, Xinhai Chen, Rongliang Wan, Qian Xu, Rui Liu, Jie Natl Univ Def Technol Sci & Technol Parallel & Distributed Proc Lab Changsha 410000 Peoples R China Natl Univ Def Technol Lab Software Engn Complex Syst Changsha 410000 Peoples R China Chinese Acad Sci Shenzhen Inst Adv Technol Shenzhen 518000 Peoples R China

Partial differential equations (PDEs) are ubiquitous in natural science and engineering problems. Traditional discrete methods for solving PDEs are usually time-consuming and labor-intensive due to the need for tedious mesh generation and numerical iterations. Recently, deep neural networks have shown new promise in cost-effective surrogate modeling because of their universal function approximation abilities. In this paper, we borrow the idea from physics-informed neural networks (PINNs) and propose an improved data-free surrogate model, DFS-Net. Specifically, we devise an attention-based neural structure containing a weighting mechanism to alleviate the problem of unstable or inaccurate predictions by PINNs. The proposed DFS-Net takes expanded spatial and temporal coordinates as the input and directly outputs the observables (quantities of interest). It approximates the PDE solution by minimizing the weighted residuals of the governing equations and data-fit terms, where no simulation or measured data are needed. The experimental results demonstrate that DFS-Net offers a good trade-off between accuracy and efficiency. It outperforms the widely used surrogate models in terms of prediction performance on different numerical benchmarks, including the Helmholtz, Klein-Gordon, and Navier-Stokes equations.

关键词：

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：