检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Fang, Zhiwei Wang, Sifan Perdikaris, Paris Graduate Group in Applied Mathematics and Computational Science University of Pennsylvania PhiladelphiaPA19104 United States Department of Mechanichal Engineering and Applied Mechanics University of Pennsylvania PhiladelphiaPA19104 United States

While the popularity of physics-informed neural networks (PINNs) is steadily rising, to this date, conventional PINNs have not been successful in simulating multi-scale and singular perturbation problems. In this work, we present a new training paradigm referred to as "gradient boosting" (GB), which significantly enhances the performance of physics informed neural networks (PINNs). Rather than learning the solution of a given partial differential equation (PDE) using a single neural network directly, our algorithm employs a sequence of neural networks to achieve a superior outcome. This approach allows us to solve problems presenting great challenges for traditional PINNs. Our numerical experiments demonstrate the effectiveness of our algorithm through various benchmarks, including comparisons with finite element methods and PINNs. Furthermore, this work also unlocks the door to employing ensemble learning techniques in PINNs, providing opportunities for further improvement in solving PDEs. © 2023, CC BY-NC-SA.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

Cascading Waves of Fluctuation in Time-delay Multi-agent Rendezvous

Cascading Waves of Fluctuation in Time-delay Multi-agent Ren...

引用

American Control Conference (ACC)

作者： Guangyi Liu Vivek Pandey Christoforos Somarakis Nader Motee Department of Mechanical Engineering and Mechanics Lehigh University Bethlehem PA USA Intelligent System Laboratory Palo Alto Research Center - Xerox During the Production of This Paper Applied Mathematics and Data Science Group Merck West Point PA USA

We develop a framework to assess the risk of cascading failures when a team of agents aims to solve the distributed rendezvous problem in time in the presence of exogenous noise and communication time-delay. The notion of value-at-risk (VaR) measure is used to evaluate the risk of cascading failures (i.e., network-based waves of large fluctuations) when some agents have failed to rendezvous. Furthermore, an explicit formula is obtained to calculate the risk of higher-order cascading failures recursively. Finally, from a risk-aware design perspective, we report an evaluation of the most vulnerable sequence of agents in various communication graphs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Wind speed prediction and insight for generalized predictive modeling framework: a comparative study for different artificial intelligence models

引用

Neural Computing and Applications 2024年第23期36卷 14119-14150页

作者： Bhagat, Suraj Kumar Tiyasha, Tiyasha Shather, A.H. Jamei, Mehdi Kumar, Adarsh Al-Khafaji, Zainab Goliatt, Leonardo Shafik, Shafik S. Alawi, Omer A. Yaseen, Zaher Mundher Faculty of Civil Engineering Ton Duc Thang University Ho Chi Minh City Viet Nam Department of Computer Engineering Technology Al Kitab University Altun Kopru Kirkuk00964 Iraq Faculty of Civil Engineering and Architecture Shahid Chamran University of Ahvaz Ahvaz Iran Canadian Centre for Climate Change and Adaptation University of Prince Edward Island St PetersPE Canada Building and Construction Techniques Engineering Department College of Engineering and Engineering Techniques Al-Mustaqbal University Hillah Babylon51001 Iraq Department of Computational and Applied Mechanics Federal University of Juiz de Fora Juiz de Fora Brazil Experimental Nuclear Radiation Research Group Scientific Research Center Al-Ayen University Thi-Qar64001 Iraq Johor Bahru Skudai81310 Malaysia Civil and Environmental Engineering Department King Fahd University of Petroleum and Minerals Dhahran31261 Saudi Arabia Department of Civil Engineering School of Engineering and Computing Dev Bhoomi Uttarakhand University Dehradun India Dept of Environmental Science Gitam School of Science GITAM University Visakhapatnam India

Wind speed (WS) has played a vital role in local urban and sub-urban weather, agriculture, and ecosystem. Several meteorological parameters are influencing WS such as relative humidity (at 2 m, %), surface pressure (kPa), maximum temperature (at 2 m, °C), minimum temperature (at 2 m, °C), average temperature (at 2 m, °C), and all sky insolation incident on a horizontal surface (kW-h/m2/day). The current research was conducted to predict WS at different locations at Vietnam using the feasibility of computer aid models (i.e., multivariate adaptive regression splines (MARS), extreme gradient boosting (XGBoost) and random forest generator (Ranger)). Pearson correlation (PC) was investigated to select the high significant predictors to predict the WS at 10 m high. All inputs (maximum number, 6) are chosen by the PC approach for PhuongNinh, DaNang, and HaNoi;and for minimum number of inputs i.e four, are selected for PhuongHung, CanTho, and SaPa city;that exhibit the relationship with WS, citywise. The sequence selection of input parameters differed in each station as per the PC analysis. Based on the statistical evaluation and graphical presentation, MARS model attained the best prediction results, followed by XGBoost and Ranger. MARS predictive model remains at the top performance among others based on 95% confidence interval. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Human Action Classification using seismic sensor and machine learning techniques 5

Human Action Classification using seismic sensor and machine...

引用

5th International Conference on Information systems and Computer Networks, ISCON 2021

作者： Chakraborty, Mainak Srinivasan, A. Reddy, Srinivasa Kumar Mandal, Sanjib Bhaumik, Subhasis School of Mechatronics and Robotics Indian Institute of Engineering Science and Technology Shibpur India Robotics and Automation Group CSIR CMERI Durgapur India Kolkata India Aerospace Engineering and Applied Mechanics Indian Institute of Engineering Science and Technology Durgapur India

ISBN: (纸本)9781665403412

In this work, we propose a novel method for identifying human activities like walking and running, utilising ground vibration obtained from seismic sensor and using machine learning techniques. The proposed methodology is based on statistical feature extraction. It is grounded on the idea, that each of the activity generate distinctly unique seismic signatures. We curated a unique dataset of various activites using off-the-shelve geophones and 16 bit analog to digital converter. The seismic data were sampled at 10000Hz. The datasets we recorded is 2 min long each. Single and 6-channels sensors are used to record the dataset. The data recorded is denoised using bandpass filter. The denoised data is used to detect peaks by comparing with neighbouring values. Peak based segementation is done and various statistical features are extracted from the dataset. The effectiveness of feature extraction is increased by converting the data in spectral domain, by extracting the power spectrum. The feature extracted are labelled and is used to train machine learning models. We have explored different machine learning algorithms and Random Forest algorithm gives the accuracy of 91.62%. © 2021 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Learning operators with coupled attention

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2022年第1期23卷 9636-9698页

作者： Georgios Kissas Jacob H. Seidman Leonardo Ferreira Guilhoto Victor M. Preciado George J. Pappas Paris Perdikaris Department of Mechanical Engineering and Applied Mechanics University of Pennsylvania Philadelphia PA Graduate Group in Applied Mathematics and Computational Science University of Pennsylvania Philadelphia PA Department of Electrical and Systems Engineering University of Pennsylvania Philadelphia PA

Supervised operator learning is an emerging machine learning paradigm with applications to modeling the evolution of spatio-temporal dynamical systems and approximating general black-box relationships between functional data. We propose a novel operator learning method, LOCA (Learning Operators with Coupled Attention), motivated from the recent success of the attention mechanism. In our architecture, the input functions are mapped to a finite set of features which are then averaged with attention weights that depend on the output query locations. By coupling these attention weights together with an integral transform, LOCA is able to explicitly learn correlations in the target output functions, enabling us to approximate nonlinear operators even when the number of output function measurements in the training set is very small. Our formulation is accompanied by rigorous approximation theoretic guarantees on the universal expressiveness of the proposed model. Empirically, we evaluate the performance of LOCA on several operator learning scenarios involving systems governed by ordinary and partial differential equations, as well as a black-box climate prediction problem. Through these scenarios we demonstrate state of the art accuracy, robustness with respect to noisy input data, and a consistently small spread of errors over testing data sets, even for out-of-distribution prediction tasks.

关键词： deep learning reproducing kernel Hilbert spaces wavelet scattering networks functional data analysis universal approximation

来源：评论

学校读者我要写书评

暂无评论

Realizability of Rectangular Euler Diagrams

arXiv

引用

arXiv 2024年

作者： Dürrschnabel, Dominik Priss, Uta Knowledge & Data Engineering Group University of Kassel Kassel Germany Interdisciplinary Research Center for Information System Design Kassel Germany Faculty of Computer Science Ostfalia University of Applied Sciences Wolfenbüttel Germany

Euler diagrams are a tool for the graphical representation of set relations. Due to their simple way of visualizing elements in the sets by geometric containment, they are easily readable by an inexperienced reader. Euler diagrams where the sets are visualized as aligned rectangles are of special interest. In this work, we link the existence of such rectangular Euler diagrams to the order dimension of an associated order relation. For this, we consider Euler diagrams in one and two dimensions. In the one-dimensional case, this correspondence provides us with a polynomial-time algorithm to compute the Euler diagrams, while the two-dimensional case is linked to an NP-complete problem which we approach with an exponential-time *** Codes 06A07, 68R05 Copyright © 2024, The Authors. All rights reserved.

关键词： Formal concept analysis

来源：评论

学校读者我要写书评

暂无评论

Experimental Characterization of the Thermal Properties of Thin Polypropylene Plates Reinforced with Residues and Fibers from the Borassus Wood (Rônier) of Chad

引用

Open Journal of applied sciences 2025年第2期15卷 517-529页

作者： Abakar Malgnan Kimtangar Ngargueudedjim Bruno Bassa Hinpere Wedjou Bianpambe Guy Edgar Ntamack Laboratory of Studies and Research in Industrial Technology Faculty of Exact and Applied Sciences University of NDjamena NDjamena Chad Department of Mechanical Engineering National Higher Institute of Sciences and Technology of Abch Abch Chad Group of Mechanics Materials and Acoustics (GMMA) Department of Physics Faculty of Science University of NGaoundr Ngaoundr Cameroon

This study focuses on the thermophysical characterizations of composite materials made from polypropylene reinforced with residues and fibers from Borassus wood from Chad. These properties are experimentally determined at different temperatures using the hot wire method of the “FP2C” machine, where the hot wire probe is inserted between two specimens. The values of the thermal conductivity in powdered Borassus wood range from 0.170 W/mK to 0.182 W/mK for female wood (FNTF) and from 0.169 W/mK to 0.173 W/mK for male wood. For the female and male fibers, the thermal conductivity values range from 0.137 W/mK to 0.157 W/mK for the female and from 0.138 W/mK to 0.168 W/mK for the male. The thermal effusivity of the residues and fibers of Borassus wood varies from: 509.6 Ws1/2/m2K to 543 Ws1/2/m2K for the powder of female wood and from 524.6 Ws1/2/m2K to 547 Ws1/2/m2K for the powder of male wood. For the fibers of Borassus wood, the values range from 410.6 Ws1/2/m2K to 523.6 Ws1/2/m2K for the female wood fibers and from 420.3 Ws1/2/m2K to 480.3 Ws1/2/m2K for the male wood fibers. These results are important for the applications of Borassus wood residues and fibers in construction works regarding the thermal insulation of habitats.

关键词： Composite Materials Residues and Fibers of Rônier Wood from Chad Thin Sheets Thermal Properties Characterization

来源：评论

学校读者我要写书评

暂无评论

SCALABLE BAYESIAN OPTIMIZATION WITH HIGH-DIMENSIONAL OUTPUTS USING RANDOMIZED PRIOR NETWORKS

arXiv

引用

arXiv 2023年

作者： Bhouri, Mohamed Aziz Joly, Michael Yu, Robert Sarkar, Soumalya Perdikaris, Paris Department of Mechanical Engineering and Applied Mechanics University of Pennsylvania PhiladelphiaPA19104 United States Raytheon Technologies Graduate Group in Applied Mathematics and Computational Science University of Pennsylvania PhiladelphiaPA19104 United States

Several fundamental problems in science and engineering consist of global optimization tasks involving unknown high-dimensional (black-box) functions that map a set of controllable variables to the outcomes of an expensive experiment. Bayesian Optimization (BO) techniques are known to be effective in tackling global optimization problems using a relatively small number objective function evaluations, but their performance suffers when dealing with high-dimensional outputs. To overcome the major challenge of dimensionality, here we propose a deep learning framework for BO and sequential decision making based on bootstrapped ensembles of neural architectures with randomized priors. Using appropriate architecture choices, we show that the proposed framework can approximate functional relationships between design variables and quantities of interest, even in cases where the latter take values in high-dimensional vector spaces or even infinite-dimensional function spaces. In the context of BO, we augmented the proposed probabilistic surrogates with re-parameterized Monte Carlo approximations of multiple-point (parallel) acquisition functions, as well as methodological extensions for accommodating black-box constraints and multi-fidelity information sources. We test the proposed framework against state-of-the-art methods for BO and demonstrate superior performance across several challenging tasks with high-dimensional outputs, including a constrained multi-fidelity optimization task involving shape optimization of rotor blades in turbo-machinery. © 2023, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Homogenizing elastic properties of large digital rock images by combining CNN with hierarchical homogenization method

arXiv

引用

arXiv 2023年

作者： Ahmad, Rasool Liu, Mingliang Ortiz, Michael Mukerji, Tapan Cai, Wei Micro and Nano Mechanics Group Department of Mechanical Engineering Stanford University CA94305 United States Department of Energy Science and Engineering Stanford University CA94305 United States Division of Engineering and Applied Science California Institute of Technology PasadenaCA91125 United States

Determining effective elastic properties of rocks from their pore-scale digital images is a key goal of digital rock physics (DRP). Direct numerical simulation (DNS) of elastic behavior, however, incurs high computational cost;and surrogate machine learning (ML) model, particularly convolutional neural network (CNN), show promises to accelerate homogenization process. 3D CNN models, however, are unable to handle large images due to memory issues. To address this challenge, we propose a novel method that combines 3D CNN with hierarchical homogenization method (HHM). The surrogate 3D CNN model homogenizes only small subimages, and a DNS is used to homogenize the intermediate image obtained by assembling small subimages. The 3D CNN model is designed to output the homogenized elastic constants within the Hashin-Shtrikman (HS) bounds of the input images. The 3D CNN model is first trained on data comprising equal proportions of five sandstone (quartz mineralogy) images, and, subsequently, fine-tuned for specific rocks using transfer learning. The proposed method is applied to homogenize the rock images of size 300×300×300 and 600×600×600 voxels, and the predicted homogenized elastic moduli are shown to agree with that obtained from the brute-force DNS. The transferability of the trained 3D CNN model (using transfer learning) is further demonstrated by predicting the homogenized elastic moduli of a limestone rock with calcite mineralogy. The surrogate 3D CNN model in combination with the HHM is thus shown to be a promising tool for the homogenization of large 3D digital rock images and other random media. © 2023, CC BY.

关键词： Lime

来源：评论

学校读者我要写书评

暂无评论

Homogenizing Elastic Properties of Large Digital Rock Images by Combining Cnn with Hierarchical Homogenization Method

SSRN

引用

SSRN 2023年

关键词： Neural network models

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：