检索结果-内蒙古大学图书馆

Learned multiphysics inversion with differentiable programming and machine learning

Leading Edge 2023年第7期42卷 474-486页

作者： Louboutin, Mathias Yin, Ziyi Orozco, Rafael Grady, Thomas J. Siahkoohi, Ali Rizzuti, Gabrio Witte, Philipp A. Møyner, Olav Gorman, Gerard J. Herrmann, Felix J. Georgia Institute of Technology School of Earth and Atmospheric Sciences AtlantaGA United States Georgia Insitute of Technology School of Computational Science and Engineering AtlantaGA United States Georgia Institute of Technology College of Computing GA Atlanta United States Utrecht University Utrecht Netherlands Microsoft Corp. RedmondWA United States SINTEF Trondheim Norway Imperial College London Department of Earth Science and Engineering London United Kingdom

We present the Seismic Laboratory for Imaging and Modeling/Monitoring open-source software framework for computational geophysics and, more generally, inverse problems involving the wave equation (e.g., seismic and medical ultrasound), regularization with learned priors, and learned neural surrogates for multiphase flow simulations. By integrating multiple layers of abstraction, the software is designed to be both readable and scalable, allowing researchers to easily formulate problems in an abstract fashion while exploiting the latest developments in high-performance computing. The design principles and their benefits are illustrated and demonstrated by means of building a scalable prototype for permeability inversion from time-lapse crosswell seismic data, which, aside from coupling of wave physics and multiphase flow, involves machine learning. © 2023 The Authors. Published by the Society of Exploration Geophysicists. All article content, except where otherwise noted (including republished material), is licensed under a Creative Commons Attribution 4.0 Unported License (CC BY). See.

关键词： Multiphysics

来源：评论

学校读者我要写书评

暂无评论

Priority-Based Uplink Raw Slot Utilization in the IEEE 802.11ah Networks

Priority-Based Uplink Raw Slot Utilization in the IEEE 802.1...

引用

International Conference on Advanced engineering Theory and Applications, AETA 2022

作者： Dang, Duc Ngoc Minh Tran, Anh Khoa Pham, Nhat Truong Computing Fundamental Department FPT University Ho Chi Minh Viet Nam Department of Electrical and Electronics Engineering Ton Duc Thang University Ho Chi Minh City Viet Nam Division of Computational Mechatronics Institute for Computational Science Ton Duc Thang University Ho Chi Minh City Viet Nam

ISBN: (纸本)9789819987023

The IEEE 802.11ah standard allows an Access Point (AP) to connect up to 8192 stations at a transmission range of up to 1 km. The goal of the IEEE 802.11ah standard is to maintain wide connectivity and energy efficiency. Some stations are allocated to RAW slots, but they do not have uplink data packets to transmit results in low channel efficiency. The new MAC protocol (PUT-MAC) allows stations to use adjacent RAW slots in a priority manner to improve channel access usage efficiency. The stations use different Arbitration Inter Frame Space and contention window values to contend channel in the same RAW slot. The paper conducts simulations to compare the network performance of the PUT-MAC protocol with the IEEE 802.11ah. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

A Convergence Analysis of a Structure-Preserving Gradient Flow Method for the All-Electron Kohn-Sham Model

引用

Numerical mathematics(Theory,Methods and Applications) 2023年第3期16卷 597-621页

作者： Yedan Shen Ting Wang Jie Zhou Guanghui Hu School of Mathematics and Information Science Guangzhou UniversityGuangzhouChina Faculty of Science and Technology University of MacaoMacao SARChina Hunan Key Laboratory for Computation and Simulation in Science and Engineering Xiangtan UniversityXiangtanChina School of Mathematical Computational Sciences Xiangtan UniversityXiangtanChina Zhuhai UM Science&Technology Research Institute ZhuhaiChina Guangdong-Hong Kong-Macao Joint Laboratory for Data-Driven Fluid Mechanics and Engineering Applications University of MacaoMacao SARChina

In[Dai et al.,***.18(4)(2020)],a structure-preserving gradient flow method was proposed for the ground state calculation in Kohn-Sham density functional theory,based on which a linearized method was developed in[Hu et al.,EAJAM.13(2)(2023)]for further improving the numerical *** this paper,a complete convergence analysis is delivered for such a linearized method for the all-electron Kohn-Sham ***,the convergence,the asymptotic stability,as well as the structure-preserving property of the linearized numerical scheme in the method is discussed following previous works,while spatially,the convergence of the h-adaptive mesh method is demonstrated following[Chen et al.,***.12(2014)],with a key study on the boundedness of the Kohn-Sham potential for the all-electron Kohn-Sham *** examples confirm the theoretical results very well.

关键词： Kohn-Sham density functional theory gradient flow model structure-preserving linear scheme convergence analysis

来源：评论

学校读者我要写书评

暂无评论

ONE-HOT GENERALIZED LINEAR MODEL FOR SWITCHING BRAIN STATE DISCOVERY 12

ONE-HOT GENERALIZED LINEAR MODEL FOR SWITCHING BRAIN STATE D...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Li, Chengrui Kim, Soon Ho Rodgers, Chris Choi, Hannah Wu, Anqi School of Computational Science & Engineering Georgia Institute of Technology AtlantaGA30305 United States School of Mathematics Georgia Institute of Technology AtlantaGA30305 United States Department of Neurosurgery School of Medicine Emory University AtlantaGA30322 United States

Exposing meaningful and interpretable neural interactions is critical to understanding neural circuits. Inferred neural interactions from neural signals primarily reflect functional connectivity. In a long experiment, subject animals may experience different stages defined by the experiment, stimuli, or behavioral states, and hence functional connectivity can change over time. To model dynamically changing functional connectivity, prior work employs state-switching generalized linear models with hidden Markov models (i.e., HMM-GLMs). However, we argue they lack biological plausibility, as functional connectivities are shaped and confined by the underlying anatomical connectome. Here, we propose two novel prior-informed state-switching GLMs, called Gaussian HMM-GLM (Gaussian prior) and one-hot HMM-GLM (Gumbel-Softmax one-hot prior). We show that the learned prior should capture the state-invariant interaction, shedding light on the underlying anatomical connectome and revealing more likely physical neuron interactions. The state-dependent interaction modeled by each GLM offers traceability to capture functional variations across multiple brain states. Our methods effectively recover true interaction structures in simulated data, achieve the highest predictive likelihood, and enhance the interpretability of interaction patterns and hidden states when applied to real neural data. The code is available at https://***/JerrySoybean/onehot-hmmglm. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

An Efficient Method for Seeds Classification and Quality Testing Using Fast R-CNN 5

An Efficient Method for Seeds Classification and Quality Tes...

引用

5th International Conference on Inventive Research in computing Applications, ICIRCA 2023

作者： Ashwini, S. Rao, B. Srinivasa Shirgire, Anil Kannan, K.R. Kumar, T Ch Anil Sivashankar, G. School of Computing Srm Institute of Science and Technology Department of Computing Technologies Chennai India Gokaraju Rangaraju Institute of Engineering and Technology Department of Computer Science and Engineering Telangana Hyderabad India Dr D y Patil Institute of Technology Maharashtra Pune India Hindusthan Institute of Technology Department of Ece Tamilnadu Coimbatore India Vignan's Foundation for Science Technology and Research Department of Mechanical Engineering Andhra Pradesh Guntur India Srm University Department of Computational Intelligence Tamilnadu Chennai India

ISBN: (纸本)9798350321425

Research into agriculture is gaining an increasing attention in recent years. The newest innovations use a variety of computational technology to make agricultural tasks easier. Seed quality is the most important of many factors that determine agricultural output. Further insights into quality manufacturing, seed quality control, and impurity discovery can be gained by proper seed classification. Seeds have traditionally been sorted into different categories based on their appearance (including their color, texture, and shape). This is often done by experts who must visually inspect each sample, which is a laborious and time-consuming process. Seed sorting is a labor-intensive process that can be greatly improved by automating the inspection process. This study presents a classification system for seeds using Fast RCNN, inspired by the success of computational intelligence methods in other image classification challenges. The suggested method includes five stages: wiener filter preprocessing;HE image enhancement;binarization;adaptive watershed segmentation;and Rapid R-CNN model training. The proposed approach outperforms other two models such as CNN and RNN. © 2023 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Improved Turbo Message Passing for Compressive Robust Principal Component Analysis: Algorithm Design and Asymptotic Analysis

arXiv

引用

arXiv 2024年

作者： He, Zhuohang Ma, Junjie Yuan, Xiaojun The National Key Laboratory of Wireless Communications University of Electronic Science and Technology of China Chengdu611731 China The Institute of Computational Mathematics and Scientific/Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100864 China

Compressive Robust Principal Component Analysis (CRPCA) naturally arises in various applications as a means to recover a low-rank matrix low-rank matrix L and a sparse matrix S from compressive measurements. In this paper, we approach the problem from a Bayesian inference perspective. We establish a probabilistic model for the problem and develop an improved turbo message passing (ITMP) algorithm based on the sum-product rule and the appropriate approximations. Additionally, we establish a state evolution framework to characterize the asymptotic behavior of the ITMP algorithm in the large-system limit. By analyzing the established state evolution, we further propose sufficient conditions for the global convergence of our algorithm. Our numerical results validate the theoretical results, demonstrating that the proposed asymptotic framework accurately characterize the dynamical behavior of the ITMP algorithm, and the phase transition curve specified by the sufficient condition agrees well with numerical simulations. © 2024, CC BY.

关键词： Asymptotic analysis

来源：评论

学校读者我要写书评

暂无评论

A Rolling Bearing Fault Diagnosis Method Using Multi-Sensor Data and Periodic Sampling

A Rolling Bearing Fault Diagnosis Method Using Multi-Sensor ...

引用

2022 IEEE International Conference on Multimedia and Expo, ICME 2022

作者： Zheng, Jianbo Yang, Chao Zheng, Fangrong Jiang, Bin College of Computer Science and Electronic Engineering Hunan University China Key Laboratory for Embedded and Network Computing of Hunan Province China School of Computational Science and Electronics Hunan Institute of Engineering China

ISBN: (数字)9781665485630

ISBN: (纸本)9781665485630

In recent years, bearing fault diagnosis based on deep learning has gradually become the mainstream. However, the existing studies still have some defects, such as unreasonable sampling and incomplete utilization of bearing data, limiting the further improvement of the performance of the fault diagnosis model. This paper proposes a fault diagnosis method using multi-sensor data and periodic sampling to solve the problems above. First, the vibration data of different bearing positions are fused into multi-channel fusion data to improve the defect of insufficient data utilization. Second, based on the sampling length and sampling stride, periodic sampling is carried out for the fusion data to solve the problem of unreasonable sampling. Third, the traditional convolutional neural network is adjusted to extract more detailed fault features and obtain the best recognition effect. Finally, the experimental results verify the effectiveness of the proposed method. © 2022 IEEE.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

Marine Ecosystem Monitoring: Applying Remote Sensing and AI to Track and Predict Coral Reef Health

引用

Remote Sensing in Earth Systems sciences 2024年第4期7卷 486-499页

作者： Veeranjaneyulu, Rayavarapu Govindarajan, Dinesh Subramanian, Chandramohan Devi, Deva Uma Banerjee, Sudipta Edpuganti, Sai Krishna Upadhyay, Shrikant Department of Computer Science & amp Engineering PACE Institute of Technology and Sciences Andhra Pradesh Ongole India Department of Computational Intelligence School of Computing SRM Institute of Science and Technology Kattankulathur (KTR) Chennai India Department of ECE SCSVMV Deemed University Tamil Nadu Kanchipuram India Department of Computer Science and Engineering Gayatri Vidya Parishad College of Engineering (A) Andhra Pradhesh Visakhapatnam India Department of Computer Science and Engineering Symbiosis Institute of Technology Symbiosis International (Deemed University) (SIU) Pune Campus Pune India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram Guntur Dist. India Department of Electronics and Communication Engineering MLR Institute of Technology Hyderabad India

Coral reefs are essential ecosystems, supporting a diverse range of marine life and offering considerable ecological, economic, and cultural benefits. However, they face increasing threats from climate change, pollution, and other human activities. Thus, effective monitoring and management of coral reefs are crucial for their conservation and sustainability. In this study, we employed a hybrid model, HCNN-SVM, which combines convolutional neural networks (CNNs) for feature extraction and support vector machines (SVMs) for classification. We utilized a coral-reef dataset from Kaggle, containing images from CoralNet and the Moorea Coral Reef Long Term Ecological Research (MCR LTER). To enhance image quality and ensure accurate reflectance values, we applied radiometric, geometric, and water column corrections during preprocessing. Feature extraction involved the use of spectral indices such as the Coral Bleaching Index (CBI) and Normalized Difference Vegetation Index (NDVI) to detect healthy and stressed corals, along with texture analysis to differentiate substrates. The model was trained on this diverse dataset, which captures various environmental conditions and reef types, achieving an accuracy of 98.55%. Cross-validation methods were employed to evaluate model performance, ensuring robustness and generalizability. The HCNN-SVM model demonstrated high accuracy in identifying and mapping coral reef components, making it a powerful tool for monitoring coral reef health and supporting conservation efforts. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Convolutional neural networks (CNNs) Coral Bleaching Index (CBI) Coral reef monitoring Feature extraction HCNN-SVM Moorea Coral Reef Long Term Ecological Research (MCR LTER) Normalized Difference Vegetation Index (NDVI) Support vector machines (SVMs)

来源：评论

学校读者我要写书评

暂无评论

Projective Exploration on Individual Stress Levels using Machine Learning 2

Projective Exploration on Individual Stress Levels using Mac...

引用

2nd International Conference on Artificial Intelligence and Smart Energy, ICAIS 2022

作者： Nagendra Prabhu, S. Singh, Amarjeet Bhavya, B. Sreeja, K. Bhargavi, P. Srm Institute of Science Technology School of Computing Department of Computational Intelligence Kattankulathur Chennai603203 India New Horizon College of Engineering Department of Computer Science and Engineering Department Bangalore India

ISBN: (纸本)9781665400527

Recently, Stress Prediction in every individual based on their profile and behaviour is a challenging task in the current sector. Current system is a manual process where it is difficult to identify the stress in the college students or employees. There is no automation for any stress prediction. System uses machine learning algorithms or AI algorithms to find out the stress levels, these technologies are used for application development. The purpose of this project is to reduce stress in students and employees. Computer science has come a long way in the last few years. It is massive and multifaceted. It has been used in a variety of applications to meet the basic needs of human society. In the field of healthcare, machine learning has made significant progress. Stress is a deadly disease that kills a large number of people worldwide. How machine learning techniques can assist in reducing the risk of stress prediction, is examined in this study. © 2022 IEEE.

关键词： Personnel

来源：评论

学校读者我要写书评

暂无评论

Isogeometric analysis for free vibration of bidirectional functionally graded plates in the fluid medium

引用

Defence Technology（防务技术） 2022年第8期18卷 1311-1329页

作者： Quoc-Hoa Pham Phu-Cuong Nguyen Van Ke Tran Trung Nguyen-Thoi Faculty of Civil Engineering Ho Chi Minh City Open UniversityHo Chi Minh CityViet Nam Faculty of Mechanical Engineering Le Quy Don Technical UniversityHanoiViet Nam Division of Computational Mathematics and Engineering Institute for Computational ScienceTon Duc Thang UniversityHo Chi Minh CityViet Nam Faculty of Civil Engineering Ton Duc Thang UniversityHo Chi Minh CityViet Nam

This paper for first time proposes an isogeometric analysis (IGA) for free vibration response of bi-directional functionally graded (BDFG) rectangular plates in the fluid medium. Material properties of the BDFG plate change in both the thickness and length directions via power-law distributions and Mori-Tanaka model. The governing equation of motion of BDFG plate in the fluid-plate system is formulated basing on Hamilton's principle and the refined quasi three-dimensional (3D) plate theory with improved function f(z). The fluid velocity potential is derived from the boundary conditions of the fluid-plate system and is used to determine the added mass. The discrete system of equations is derived from the Galerkin weak form and numerically analyzed by IGA. The accuracy and reliability of the proposed solutions are verified by comparing the obtained results with those published in the literature. Moreover, the effects of the various parameters such as the interaction boundary condition, geometric parameter, submerged depth of plate, fluid density, fluid level, and the material volume control coefficients on the free vibration behavior of BDFG plate in the fluid medium are investigated in detail. Some major findings regarding the numerical results are withdrawn in conclusions.

关键词： Contact plate-fluid Refined quasi 3D plate theory Mori-Tanaka model Isogeometric analysis Bidirectional functionally graded plate

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：