检索结果-内蒙古大学图书馆

MH-DCNet: An improved flow field prediction framework coupling neural network with physics solver

COMPUTERS & FLUIDS 2024年 284卷

作者： Xiao, Qisong Chen, Xinhai Liu, Jie Gong, Chunye Sun, Yufei Natl Univ Def Technol Sci & Technol Parallel & Distributed Proc Lab Changsha 410073 Peoples R China Natl Univ Def Technol Lab Digitizing Software Frontier Equipment Changsha 410073 Peoples R China Nankai Univ Coll Software Tianjin 300350 Peoples R China

With the development of intelligent computing technology, deep learning methods have provided an efficient solution for rapid flow field prediction in computational fluid dynamics (CFD) problems. However, existing methods have limitations in handling interference among physical variables due to different data distributions, leading to a decline in prediction performance. In this paper, we propose MH-DCNet, an improved flow field prediction framework that couples a neural network with a physics solver. Specifically, to address the data distribution problem, we design a multi-head deep convolutional neural network that decouples the prediction of physical variables through multiple encoders and decoders. We also develop a hybrid loss function by introducing the mean structural similarity to better capture the complex spatial structures and distribution features of flow fields. We evaluate MH-DCNet with unseen geometries and various flow conditions. Experimental results show that MH-DCNet outperforms other advanced models in efficiency and generalization capability. It accelerates the prediction process by 2.35 times compared to the CFD method while meeting the convergence constraints.

关键词： Computational fluid dynamics Deep learning Flow field prediction Hybrid loss function

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

Who Will Become a Long-Term Contributor? A Prediction Model based on the Early Phase Behaviors 18

Who Will Become a Long-Term Contributor? A Prediction Model ...

引用

10th Asia-Pacific Symposium on Internetware (Internetware)

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

ISBN: (纸本)9781450365901

The continuous contribution from peripheral participants is crucial for the success of open source projects. Thus, how to identify the potential Long-Term Contributors (LTC) early and retain them is of great importance. We propose a prediction model to measure the chance for an individual to become a LTC contributor through his capacity, willingness, and the opportunity to contribute at the time of joining. Using data of Rails hosted on GitHub, we find that the probability for a new joiner to become a LTC is associated with his willingness and environment. Specifically, future LTCs tend to be more active and show more community-oriented attitude than other joiners during their first month. This implies that the interaction between individual's attitude and project's climate are associated with the odds that an individual would become a valuable contributor or disengage from the project. We evaluated our prediction model by using the 10 crossvalidation method. Results show that our model archives the mean AUC as 0.807, which is valuable for OSS projects to identify potential long-term contributors and adopt better strategies to retain them for continuous contribution.

关键词： Long Term Contributor Developer behavior GitHub Open Source

来源：评论

学校读者我要写书评

暂无评论

Dual Mutual Learning for Cross-Modality Person Re-Identification

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2022年第8期32卷 5361-5373页

作者： Zhang, Demao Zhang, Zhizhong Ju, Ying Wang, Cong Xie, Yuan Qu, Yanyun Xiamen Univ Sch Informat Xiamen 361005 Peoples R China East China Normal Univ Sch Comp Sci & Software Engn Shanghai 200050 Peoples R China Huawei Techol Distributed & Parallel Software Lab 2012 Labs Shenzhen 518129 Peoples R China

Cross-modality person re-identification (Re-ID) is more challenging than traditional visible Re-ID due to the huge cross-modality gap from heterogeneous images. To alleviate this problem, existing methods often utilize a dual path learning framework equipped with metric loss to learn discriminative features. Despite effectiveness, the inevitable degeneration of intra-modality discrimination by taking cross-modality discrimination into consideration is unsolvable. Such degeneration substantially hinders the model's capability of further improving feature representations. To mitigate this degeneration, we propose a Dual Mutual Learning (DML) method for cross-modality Re-ID which conducts mutual learning between the cross-modality and each of two single modalities. We design a triple-branch deep model containing the RGB and IR branches and the cross-modality branch. The cross-modality branch is designed to learn modality-invariant feature subspace for appearance similarity measurement. Both the RGB branch and IR branch provide attention supervision information to the cross-modality branch for attention feature alignment so as to enhance the intra-modality discrimination. Experimental results on two standard benchmarks demonstrate DML is superior to state-of-the-art methods.

关键词： Training Task analysis Surveillance Sensors Representation learning Knowledge engineering Convolutional neural networks Cross-modality person re-identification mutual learning attention alignment

来源：评论

学校读者我要写书评

暂无评论

Refinement and verification in component-based model-driven design

引用

SCIENCE OF COMPUTER PROGRAMMING 2009年第4期74卷 168-196页

作者： Chen, Zhenbang Liu, Zhiming Ravn, Anders P. Stolz, Volker Zhan, Naijun UNU IIST Macao Peoples R China Univ Aalborg Dept Comp Sci Aalborg Denmark CAS Inst Software Comp Sci Lab Beijing Peoples R China Natl Lab Parallel & Distributed Proc Changsha Hunan Peoples R China

Modern software development is complex as it has to deal with many different and yet related aspects of applications. In practical software engineering this is now handled by a UML-like modelling approach in which different aspects are modelled by different notations. Component-based and object-oriented design techniques are found effective in the support of separation of correctness concerns of different aspects. These techniques are practised in a model-driven development process in which models are constructed in each phase of the development. To ensure the correctness of the software system developed, all models constructed in each phase are verifiable. This requires that the modelling notations are formally defined and related in order to have tool support developed for the integration of sophisticated checkers, generators and transformations. This paper summarises our research on the method of Refinement of Component and Object Systems (rCOS) and illustrates it with experiences from the work on the Common Component Modelling Example (CoCoME). This gives evidence that the formal techniques developed in rCOS can be integrated into a model-driven development process and shows where it may be integrated in computer-aided software engineering (CASE) tools for adding formally supported checking, transformation and generation facilities. (C) 2009 Published by Elsevier B.V.

关键词： Formal methods Multi-view modelling rCOS software design process Tool design UML

来源：评论

学校读者我要写书评

暂无评论

Remote storage management in science gateways via data bridging

引用

CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE 2015年第16期27卷 4398-4411页

作者： Hajnal, Akos Marton, Istvan Farkas, Zoltan Kacsuk, Peter Hungarian Acad Sci Lab Parallel & Distributed Syst Inst Comp Sci & Control H-1132 Budapest Hungary Univ Westminster Comp Sci & Software Engn Dept London W1W 6UW England

State-of-the-art science gateways can be connected to several distributed computing infrastructures (DCIs) and are able to run jobs and workflows simultaneously in all those DCIs. Flexibility of accessing diverse data storages from these workflows and assisting end users to manage these storages are however the missing features in current gateway implementations, in which these problems often prove to be a barrier of exploiting the power of distributed computing by user communities having no or little IT competence. This paper addresses these issues by integrating a data bridging service called Data Avenue into WS-PGRADE/gUSE portal framework. Data Avenue offers tools for the end users to easily manage their data residing on various storage resources, and also, jobs become capable of accessing different storages regardless of the particular distributed computing infrastructure where the job is currently being run. Copyright (c) 2014 John Wiley & Sons, Ltd.

关键词： data storage systems data handling data transfer grid computing

来源：评论

学校读者我要写书评

暂无评论

Hyperlink-induced Pre-training for Passage Retrieval in Open-domain Question Answering 60

Hyperlink-induced Pre-training for Passage Retrieval in Open...

引用

60th Annual Meeting of the Association-for-Computational-Linguistics (ACL)

作者： Zhou, Jiawei Li, Xiaoguang Shang, Lifeng Luo, Lan Zhan, Ke Hu, Enrui Zhang, Xinyu Jiang, Hao Cao, Zhao Yu, Fan Jiang, Xin Liu, Qun Chen, Lei Hong Kong Univ Sci & Technol Hong Kong Peoples R China Huawei Noahs Ark Lab Shenzhen Peoples R China Huawei Distributed & Parallel Software Lab Shenzhen Peoples R China

ISBN: (纸本)9781955917216

To alleviate the data scarcity problem in training question answering systems, recent works propose additional intermediate pre-training for dense passage retrieval (DPR). However, there still remains a large discrepancy between the provided upstream signals and the downstream question-passage relevance, which leads to less improvement. To bridge this gap, we propose the HyperLink-induced Pre-training (HLP), a method to pre-train the dense retriever with the text relevance induced by hyperlink-based topology within Web documents. We demonstrate that the hyperlink-based structures of dual-link and co-mention can provide effective relevance signals for large-scale pre-training that better facilitate downstream passage retrieval. We investigate the effectiveness of our approach across a wide range of open-domain QA datasets under zero-shot, few-shot, multihop, and out-of-domain scenarios. The experiments show our HLP outperforms the BM25 by up to 7 points as well as other pre-training methods by more than 10 points in terms of top-20 retrieval accuracy under the zero-shot scenario. Furthermore, HLP significantly outperforms other pre-training methods under the other scenarios.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

An Analysis on Matching Mechanisms and Token Pruning for Late-interaction Models

引用

ACM TRANSACTIONS ON INFORMATION SYSTEMS 2024年第5期42卷 1-28页

作者： Liu, Qi Guo, Gang Mao, Jiaxin Dou, Zhicheng Wen, Ji-Rong Jiang, Hao Zhang, Xinyu Cao, Zhao Renmin Univ China Gaoling Sch Artificial Intelligence Being Key Lab Data Management & Anal Methods 59 Zhongguancun St Beijing 100872 Peoples R China Distributed & Parallel Software Lab 360 Jiangshu Rd Hangzhou 310056 Zhejiang Peoples R China

With the development of pre-trained language models, the dense retrieval models have become promising alternatives to the traditional retrieval models that rely on exact match and sparse bag-of-words representations. Different from most dense retrieval models using a bi-encoder to encode each query or document into a dense vector, the recently proposed late-interaction multi-vector models (i.e., ColBERT and COIL) achieve state-of-the-art retrieval effectiveness by using all token embeddings to represent documents and queries andmodeling their relevance with a sum-of-max operation. However, these fine-grained representations may cause unacceptable storage overhead for practical search systems. In this study, we systematically analyze the matching mechanism of these late-interaction models and show that the sum-of-max operation heavily relies on the co-occurrence signals and some important words in the document. Based on these findings, we then propose several simple document pruning methods to reduce the storage overhead and compare the effectiveness of different pruning methods on different late-interaction models. We also leverage query pruning methods to further reduce the retrieval latency. We conduct extensive experiments on both in-domain and out-domain datasets and show that some of the used pruning methods can significantly improve the efficiency of these late-interaction models without substantially hurting their retrieval effectiveness.

关键词： Neural networks pre-trained language model late-interaction models token pruning efficiency optimization

来源：评论

学校读者我要写书评

暂无评论

An Extended cCSP with Stable Failures Semantics

An Extended cCSP with Stable Failures Semantics

引用

7th International Colloquium Theoretical Aspects of Computing

作者： Chen, Zhenbang Liu, Zhiming Natl Lab Parallel & Distributed Proc Changsha Hunan Peoples R China Natl United Univ Int Inst Software Technol Macao SAR Peoples R China

ISBN: (纸本)9783642148071

Compensating CSP (cCSP) is an extension to CSP for modeling long-running transactions It can be used to specify programs of service orchestration written in a programming language like WS-BPEL So far, only an operational semantics and a trace semantics are given to cCSP In this paper, we extend cCSP with more operators and define for it a stable failures semantics in order to reason about non-determinism and deadlock We give some important algebraic laws for the new operators These laws can be Justified and understood from the stable failures semantics A case study is given to demonstrate the extended cCSP

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

The Inherent Mechanism and a Case Study of the Constructional Evolution of the JointCloud Ecosystem

引用

IEEE INTERNET OF THINGS JOURNAL 2020年第3期7卷 1561-1571页

作者： Shi, Peichang Liu, Hui Yang, Shangzhi Zhang, Yiqi Zhong, Yaoqi Natl Univ Def Technol Coll Comp Sci Natl Key Lab Parallel & Distributed Proc Changsha 410073 Peoples R China Natl Univ Def Technol Coll Comp Sci Key Lab Software Engn Complex Syst Changsha 410073 Peoples R China

There have been dramatic increases in industrial investment and growing research interests in Internet of Things over the past few years. Driven by the application demand from Internet of everything in the future, the collaboration between traditional cloud and edge cloud is already on the way to provide better service to diverse users. However, due to the high marginal operation and maintenance costs, there remains a need for collaboration between traditional clouds. JointCloud computing is a new computing paradigm that supports collaboration within heterogeneous clouds, which is a complex problem that is difficult to manage using the traditional methodology of "top-down, decomposition, and reduction" in the benign construction of the JointCloud ecosystem. In this article, we first describe the inherent mechanism behind the constructional evolution of the JointCloud ecosystem, which details the inner workings of its elements and the general principals of how these various elements influence each other. We then propose a series of forward-looking, feasible operational methods to support the constructional evolution of the JointCloud ecosystem that incorporate efficient development methods, data-driven operations, AI-assisted decision making and so on. Finally, a case study of a cross-cloud migration deployment is used to illustrate the scientific basis of the systems inherent mechanism, as well as the efficacy of the supporting methods.

关键词： Cloud computing Ecosystems Internet of Things Collaboration Complex systems software systems BlockChain cloud computing constructional evolution edge cloud Internet of Things (IoT) JointCloud ecosystem

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：