检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Gao, Penglei Yang, Xi Zhang, Rui Guo, Ping Goulermas, John Y. Huang, Kaizhu The Department of Computer Science University of Liverpool LiverpoolL69 7ZX United Kingdom The Department of Intelligent Science Xi'an Jiaotong-Liverpool University Suzhou215123 China The Department of Foundational Mathematics Xi'an Jiaotong-Liverpool University Suzhou215123 China The Department of school of systems science Beijing Normal University Beijing100875 China The Institute of Applied Physical Sciences and Engineering Duke Kunshan University No. 8 Duke Avenue Kunshan215316 China

While exogenous variables have a major impact on performance improvement in time series analysis, inter-series correlation and time dependence among them are rarely considered in the present continuous methods. The dynamical systems of multivariate time series could be modelled with complex unknown partial differential equations (PDEs) which play a prominent role in many disciplines of science and engineering. In this paper, we propose a continuous-time model for arbitrary-step prediction to learn an unknown PDE system in multivariate time series whose governing equations are parameterised by self-attention and gated recurrent neural networks. The proposed model, Exogenous-guided Partial Differential Equation Network (EgPDE-Net), takes account of the relationships among the exogenous variables and their effects on the target series. Importantly, the model can be reduced into a regularised ordinary differential equation (ODE) problem with special designed regularisation guidance, which makes the PDE problem tractable to obtain numerical solutions and feasible to predict multiple future values of the target series at arbitrary time points. Extensive experiments demonstrate that our proposed model could achieve competitive accuracy over strong baselines: on average, it outperforms the best baseline by reducing 9.85% on RMSE and 13.98% on MAE for arbitrary-step prediction. © 2022, CC BY-NC-SA.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

C0,αboundary regularity for the pressure in weak solutions of the 2d Euler equations

arXiv

引用

arXiv 2021年

作者： Bardos, Claude W. Titi, Edriss S. Laboratoire J.-L. Lions BP187 Paris Cedex 0575252 France Department of Mathematics Texas A&m University College StationTX77843-3368 United States Department of Applied Mathematics and Theoretical Physics University of Cambridge CambridgeCB3 0WA United Kingdom Department of Computer Science and Applied Mathematics Weizmann Institute of Science Rehovot76100 Israel

The purpose of this note is to give a complete proof of a C0,αregularity result for the pressure for weak solutions of the two-dimensional "incompressible Euler equations" when the fluid velocity enjoys the same type of regularity in a compact simply connected domain with C2boundary. To accomplish our result we realize that it is compulsory to introduce a new weak formulation for the boundary condition of the pressure which is consistent with, and equivalent to, that of classical *** Codes 35Q35, 35Q31, 7603 © 2021, CC BY.

关键词： Euler equations

来源：评论

学校读者我要写书评

暂无评论

Causal inference in drug discovery and development

arXiv

引用

arXiv 2022年

作者： Michoel, Tom Zhang, Jitao David Computational Biology Unit Department of Informatics University of Bergen Postboks 7803 Bergen5020 Norway Pharma Early Research and Development Roche Innovation Centre Basel F. Hoffmann-La Roche Grenzacherstrasse 124 Basel4070 Switzerland Department of Mathematics and Computer Science University of Basel Spiegelgasse 1 Basel4051 Switzerland

To discover new drugs is to seek and to prove causality. As an emerging approach leveraging human knowledge and creativity, data, and machine intelligence, causal inference holds the promise of reducing cognitive bias and improving decision making in drug discovery. While it has been applied across the value chain, the concepts and practice of causal inference remain obscure to many practitioners. This article offers a non-technical introduction to causal inference, reviews its recent applications, and discusses opportunities and challenges of adopting the causal language in drug discovery and development. © 2022, CC BY-NC-ND.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Immersive Embedded Consumer Model Leveraging AI with Zero-Trust Architecture for Cyber-Physical System

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Rehman, Amjad Haseeb, Khalid Kolivand, Hoshang Saba, Tanzila Al-Khasawneh, Mahmoud A. Ahmad, Shabir Ullah, Inam Lab Riyadh12435 Saudi Arabia Liverpool John Moores University School of Computer Science and Mathematics United Kingdom School of Computing and Digital Technologies Staffordshire University Liverpool Staffordshire United Kingdom University City Sharjah 1797 United Arab Emirates Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Jordan School of Computing Skyline University College Sharjah United Arab Emirates Incheon Startup Park Center of Artificial Intelligence for Medical Instruments Convensia-daero Incheon204 Korea Republic of Gachon University Department of Computer Engineering Seongnam13120 Korea Republic of

The rapid expansion of the wireless network and its combination with the Consumer Internet of Things (CIoT) has introduced significant research challenges for Cyber-Physical Systems (CPS). The distributed nature of these embedded networks provides big data analytics with the integration of sensors, electronic devices, hardware, and network components. They provide diverse functionalities while sensing the observing environment based on the demand of network users with timely feedback, which supports efficient decision-making. However, CIoT devices in CPS increasingly interact with both physical and digital environments, such interaction raises the research challenges of performance optimization, data breaches, and long-run seamless connectivity. In addition, the constraint devices demanded lightweight communication methods to remain robust and enhance network stability. This paper presents an adaptive model that leverages AI-based optimization techniques with efficient data management and utilization of resources in consumer applications. Moreover, the integrated edges provide consistency and resilience of communication services in unpredictable systems, while adopting a Zero-Trust architecture with more trustworthy and secure transmissions. It increases the system's scalability and improves the response time with the limited computing power of devices for real-time processing. Simulation results demonstrated the significant outcomes of the proposed model over the dynamic scenarios for packet delivery ratio by 35.5%, network throughput by 38.7%, energy consumption by 41.6%, and latency by 45% against existing solutions. © 1975-2011 IEEE.

关键词： consumer technologies edge intelligence embedded systems information security technological development

来源：评论

学校读者我要写书评

暂无评论

Machine learning based recommendation systems for the mode of childbirth 2nd

Machine learning based recommendation systems for the mode o...

引用

2nd International Conference on computer science and Cyber Security, ICONCS 2020

作者： Kowsher, Md. Prottasha, Nusrat Jahan Tahabilder, Anik Islam, Md. Babul Department of Applied Mathematics Noakhali Science and Technology University Noakhali3814 Bangladesh Department of Computer Science and Engineering Daffodil International University Dhaka1207 Bangladesh School of Engineering + Technology Western Carolina University CullowheeNC28723 United States Department of Applied Physics and Electronic Engineering University of Rajshahi Rajshahi6205 Bangladesh

ISBN: (纸本)9783030528553

Machine learning method gives a learning technique that can be applied to extract information from data. Lots of researches are being conducted that involves machine learning techniques for medical diagnosis, prediction and treatment. The goal of this study is to perform several machine learning actions for finding the appropriate mode of birth (cesarean or normal) to minimize maternal mortality rate. To generate a computer-aided decision for selecting between the most common way of baby birth, C-section and vaginal birth, we have used supervised machine learning to train our classification model. A dataset consists of the information of 13,527 delivery patients has been collected from Tarail Upazilla Health complex, Bangladesh. We have implemented nine machine learning classifier algorithms over the whole datasets and compared the performances of all those proposed techniques. The computer recommended mode of baby delivery suggested by the most convincing method named "impact learning," showed an accuracy of 0.89089172 with the F1 value of 0.877871741. © ICST Institute for computer sciences, Social Informatics and Telecommunications Engineering 2020.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

A Multiagent Path Search Algorithm for Large-Scale Coalition Structure Generation

arXiv

引用

arXiv 2025年

作者： Taguelmimt, Redha Aknine, Samir Boukredera, Djamila Changder, Narayan Sandholm, Tuomas Clermont Auvergne University Clermont Auvergne INP CNRS LIMOS Clermont-FerrandF-63000 France Univ Lyon UCBL CNRS INSA Lyon Centrale Lyon Univ Lyon 2 LIRIS UMR5205 Lyon France Laboratory of Applied Mathematics Faculty of Exact Sciences University of Bejaia Bejaia Algeria TCG Centres for Research and Education in Science and Technology Kolkata India Carnegie Mellon University Computer Science Department Pittsburgh United States Strategy Robot Inc. Strategic Machine Inc. Optimized Markets Inc.

Coalition structure generation (CSG), i.e. the problem of optimally partitioning a set of agents into coalitions to maximize social welfare, is a fundamental computational problem in multiagent systems. This problem is important for many applications where small run times are necessary, including transportation and disaster response. In this paper, we develop SALDAE, a multiagent path finding algorithm for CSG that operates on a graph of coalition structures. Our algorithm utilizes a variety of heuristics and strategies to perform the search and guide it. It is an anytime algorithm that can handle large problems with hundreds and thousands of agents. We show empirically on nine standard value distributions, including disaster response and electric vehicle allocation benchmarks, that our algorithm enables a rapid finding of high-quality solutions and compares favorably with other state-of-the-art *** Codes 93A16, 68T01 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

Long-Short Term Memory Model for χ(2) Nonlinear Processes: Enhancing Simulation with ML

arXiv

引用

arXiv 2025年

作者： Hirschman, Jack Abedi, Erfan Wang, Minyang Zhang, Hao Borthakur, Abhimanyu Baker, Justin Carbajo, Sergio Department of Applied Physics Stanford University StanfordCA94305 United States SLAC National Accelerator Laboratory Menlo ParkCA94025 United States Department of Electrical & Computer Engineering UCLA Los AngelesCA90095 United States Department of Mathematics UCLA Los AngelesCA90095 United States Department of Statistics & Data Science UCLA Los AngelesCA90095 United States Physics & Astronomy Department UCLA Los AngelesCA90095 United States California NanoSystems Institute Los AngelesCA90095 United States

Modeling second-order (χ(2)) nonlinear optical processes remains computationally expensive due to the need to resolve fast field oscillations and simulate wave propagation using methods like the split-step Fourier method (SSFM). This can become a bottleneck in real-time applications, such as high-repetition-rate laser systems requiring rapid feedback and control. We present an LSTM-based surrogate model trained on SSFM simulations generated from a start-to-end model of the photocathode drive laser at SLAC National Accelerator Laboratory’s Linac Coherent Light Source II. The model achieves over 250× speedup while maintaining high fidelity, enabling future real-time optimization and laying the foundation for data-integrated modeling frameworks. © 2025, CC BY.

关键词： Pulse repetition rate

来源：评论

学校读者我要写书评

暂无评论

Second order convergence of a modified MAC scheme for Stokes interface problems

arXiv

引用

arXiv 2023年

作者： Dong, Haixia Zhao, Zhongshu Li, Shuwang Ying, Wenjun Zhang, Jiwei MOE-LCSM School of Mathematics and Statistics Hunan Normal University Hunan Changsha410081 China School of Mathematical Sciences Institute of Natural Sciences Shanghai Jiao Tong University Minhang Shanghai200240 China Department of Applied Mathematics Illinois Institute of Technology Rettaliata Engineering Center Room 11B 10 W. 32nd Street ChicagoIL60616 United States School of Mathematical Sciences MOE-LSC Institute of Natural Sciences Shanghai Jiao Tong University Minhang Shanghai200240 China School of Mathematics and Statistics Hubei Key Laboratory of Computational Science Wuhan University Wuhan430072 China

Stokes flow equations have been implemented successfully in practice for simulating problems with moving interfaces. Though computational methods produce accurate solutions and numerical convergence can be demonstrated using a resolution study, the rigorous convergence proofs are usually limited to particular reformulations and boundary conditions. In this paper, a rigorous error analysis of the marker and cell (MAC) scheme for Stokes interface problems with constant viscosity in the framework of the finite difference method is presented. Without reformulating the problem into elliptic PDEs, the main idea is to use a discrete Ladyzenskaja-Babuska-Brezzi (LBB) condition and construct auxiliary functions, which satisfy discretized Stokes equations and possess at least second order accuracy in the neighborhood of the moving interface. In particular, the method, for the first time, enables one to prove second order convergence of the velocity gradient in the discrete 2-norm, in addition to the velocity and pressure fields. Numerical experiments verify the desired properties of the methods and the expected order of accuracy for both two-dimensional and three-dimensional examples. Copyright © 2023, The Authors. All rights reserved.

关键词： Finite difference method

来源：评论

学校读者我要写书评

暂无评论

Machine learning based non-Newtonian fluid model with molecular fidelity

arXiv

引用

arXiv 2020年

作者： Lei, Huan Wu, Lei Weinan, E. Department of Computational Mathematics Science & Engineering Department of Statistics & Probability Michigan State University MI48824 United States Department of Mathematics and Program in Applied and Computational Mathematics Princeton University NJ08544 United States

We introduce a machine-learning-based framework for constructing continuum non-Newtonian fluid dynamics model directly from a micro-scale description. Polymer solution is used as an example to demonstrate the essential ideas. To faithfully retain molecular fidelity, we establish a micro-macro correspondence via a set of encoders for the micro-scale polymer configurations and their macro-scale counterparts, a set of nonlinear conformation tensors. The dynamics of these conformation tensors can be derived from the micro-scale model and the relevant terms can be parametrized using machine learning. The final model, named the deep non-Newtonian model (DeePN2), takes the form of conventional non-Newtonian fluid dynamics models, with a new form of the objective tensor derivative. Numerical results demonstrate the accuracy of DeePN2. Copyright © 2020, The Authors. All rights reserved.

关键词： Viscous flow

来源：评论

学校读者我要写书评

暂无评论

Inverse Initial Boundary Value Problem for a Non-linear Hyperbolic Partial Differential Equation

arXiv

引用

arXiv 2020年

作者： Nakamura, Gen Vashisth, Manmohan Watanabe, Michiyuki Department of Mathematics Hokkaido University Sapporo060-0810 Japan Beijing Computational Science Research Center Beijing100193 China Department of Applied Mathematics Faculty of Science Okayama University of Science Japan

In this article we are concerned with an inverse initial boundary value problem for a non-linear wave equation in space dimension n ≥ 2. In particular we consider the so called interior determination problem. This non-linear wave equation has a trivial solution, i.e. zero solution. By linearizing this equation at the trivial solution, we have the usual linear wave equation with a time independent potential. For any small solution u = u(t, x) of this non-linear equation, it is the perturbation of linear wave equation with time-independent potential perturbed by a divergence with respect to (t, x) of a vector whose components are quadratics with respect to ∇t,xu(t, x). By ignoring the terms with smallness O(|∇t,xu(t, x)|3), we will show that we can uniquely determine the potential and the coefficients of these quadratics by many boundary measurements at the boundary of the spacial domain over finite time interval and the final overdetermination at t = T . In other words, the measurement is given by the so-called the input-output map (see (1.5)). Copyright © 2020, The Authors. All rights reserved.

关键词： Initial value problems

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：