检索结果-内蒙古大学图书馆

A NONLOCAL KRONECKER-BASIS-REPRESENTATION METHOD FOR LOW-DOSE CT SINOGRAM RECOVERY

Journal of Computational Mathematics 2024年第4期42卷 1080-1108页

作者： Jian Lu Huaxuan Hu Yuru Zou Zhaosong Lu Xiaoxia Liu Keke Zu Lin Li Shenzhen Key Laboratory of Advanced Machine Learning and Applications College of Mathematics and StatisticsShenzhen UniversityShenzhen 518060China National Center for Applied Mathematics Shenzhen(NCAMS) Shenzhen 518055China Department of Industrial and Systems Engineering University of Minnesota Twin CitiesMinneapolisMN55455USA Department of Applied Mathematics The Hong Kong Polytechnic UniversityHong Kong SARChina School of Electronic Engineering Xidian UniversityXi'an 710071China

Low-dose computed tomography(LDCT)contains the mixed noise of Poisson and Gaus-sian,which makes the image reconstruction a challenging *** order to describe the statistical characteristics of the mixed noise,we adopt the sinogram preprocessing as a stan-dard maximum a posteriori(MAP).Based on the fact that the sinogram of LDCT has non-local self-similarity property,it exhibits low-rank *** conventional way of solving the low-rank problem is implemented in matrix forms,and ignores the correlations among similar patch *** avoid this issue,we make use of a nonlocal Kronecker-Basis-Representation(KBR)method to depict the low-rank problem.A new denoising model,which consists of the sinogram preprocessing for data fidelity and the nonlocal KBR term,is developed in this *** proposed denoising model can better illustrate the generative mechanism of the mixed noise and the prior knowledge of the ***-merical results show that the proposed denoising model outperforms the state-of-the-art algorithms in terms of peak-signal-to-noise ratio(PSNR),feature similarity(FSIM),and normalized mean square error(NMSE).

关键词： Low-dose computed tomography Kronecker-basis-representation Low-rank imation.Noise-generating-mechanism

来源：评论

学校读者我要写书评

暂无评论

Urban Patterns from Space: A Remote Sensing Based Comparison Between France and Germany

引用

KN - Journal of Cartography and Geographic Information 2024年第3期74卷 233-249页

作者： Schmitt, Andreas Haselmayr, Teresa Taubenböck, Hannes Institute for Applications of Machine Learning and Intelligent Systems (IAMLIS) Hochschule München University of Applied Sciences Lothstraße 34 Bavaria Munich 80335 Germany Geoinformatics Department Hochschule München University of Applied Sciences Karlstraße 6 Bavaria Munich 80333 Germany Earth Observation Center (EOC) German Aerospace Center (DLR) Oberpfaffenhofen Bavaria Weßling 82234 Germany Institute for Geography and Geology Julius-Maximilians-University of Würzburg Am Hubland Bavaria Würzburg 97074 Germany

This article presents two novel methods on how to derive and visualise settlement patterns from space: a non-parametric approach called multi-scale homogeneity and a parametric, unsupervised approach known as hierarchical multi-scale clustering that models the urban clusters with the help of Gaussian bell curves. The main advantage of remote sensing based acquisition and fully automated evaluation methods is their consistency over large coverages. The Global Urban Footprint-Density (GUF-DenS) indicating the degree of impervious surfaces worldwide serves as database. The geographical focus lies on the neighbouring central-European countries France and Germany. Assuming that the centralist and federal administrative systems resulting from the individual history show a certain impact on the urban patterns, both countries are first examined separately, then together as union. The numerical comparison proofs the expected differences: the settlement pattern of the capital Paris as the largest metropolitan region in France is dominating, whereas several economic clusters of more of less similar size like Rhine–Ruhr and Rhine–Main characterise the German urban landscape. The most interesting and unexpected findings are located along the border, where neighbouring urban ellipses overlay in the separate processing and form transnational clusters when processed as union. One can interpret that the national border does not play a role in the urban development (any longer). The temporal change of the settlement patterns as effect of the regional planning strategies or the opening of the inner-European border cannot be derived from the mono-temporal GUF-DenS and thus, will be subject to future studies. © The Author(s) 2024.

关键词： Built-up density Cluster analysis Gaussian mixture model Inner-European border Settlement pattern Spatial homogeneity Unsupervised clustering

来源：评论

学校读者我要写书评

暂无评论

Correlation between remotely sensed solid waste on streets and socioeconomic class of an urban area

Correlation between remotely sensed solid waste on streets a...

引用

Urban Remote Sensing Joint Event

作者： Yrneh Zarit Ulloa Torrealba Dominik Neumayer Andreas Schmitt Hannes Taubenböck Munich University of Applied Sciences Munich German Aerospace Center (DLR) Earth Observation Center (EOC) Oberpfaffenhofen & University of Wuerzburg Wuerzburg Germany Munich University of Applied Sciences Munich Germany Institute for Applications of Machine Learning and Intelligent Systems (IAMLIS) Munich University of Applied Sciences Munich Germany

Solid waste dumped on the streets affects human hygiene, well-being, and increases deprivation. This happens as result of a failure in the solid waste management of a city. This is especially observed in informal poorer areas. With the current increase of population in urban settlements, and especially in informal areas, new techniques are in demand to identify litter dumped on the streets in a rapid manner. In this study, aerial imagery of the city of Medellín were segmented with a k-means based algorithm and classified with a Random Forest decision tree ensemble. The results show, that with this approach garbage detection is possible with an Overall Accuracy of 82 %. Comparison with socioeconomic data from a national census on housing shows that solid waste was identified with higher shares in poorer districts. This method can be implemented at city scale and therefore might be useful for decision makers.

关键词：

来源：评论

学校读者我要写书评

暂无评论

InfoFlowNet: A Multi-head Attention-based Self-supervised learning Model with Surrogate Approach for Uncovering Brain Effective Connectivity

arXiv

引用

arXiv 2023年

作者： Chuang, Chun-Hsiang Fang, Shao-Xun Huang, Chih-Sheng Ding, Weiping Research Center for Education and Mind Sciences College of Education National Tsing Hua University Hsinchu Taiwan Institute of Information Systems and Applications College of Electrical Engineering and Computer Science National Tsing Hua University Hsinchu Taiwan Department of Education and Learning Technology National Tsing Hua University Hsinchu Taiwan Department of Computer Science and Engineering National Taiwan Ocean University Keelung Taiwan Department of Artificial Intelligence Research and Development Elan Microelectronics Corporation Hsinchu Taiwan College of Artificial Intelligence and Green Energy National Yang Ming Chiao Tung University Hsinchu Taiwan College of Electrical Engineering and Computer Science National Taipei University of Technology Hsinchu Taiwan School of Information Science and Technology Nantong University Nantong China Institute of Information Systems and Applications College of Electrical Engineering and Computer Science NTHU Treasure Taipei Chapter of IEEE Computational Intelligence Society Taiwan

Deciphering brain network topology can enhance the depth of neuroscientific knowledge and facilitate the development of neural engineering methods. Effective connectivity, a measure of brain network dynamics, is particularly useful for investigating the directional influences among different brain regions. In this study, we introduce a novel brain causal inference model named InfoFlowNet, which leverages the self-attention mechanism to capture associations among electroencephalogram (EEG) time series. The proposed method estimates the magnitude of directional information flow (dIF) among EEG processes by measuring the loss of model inference resulting from the shuffling of the time order of the original time series. To evaluate the feasibility of InfoFlowNet, we conducted experiments using a synthetic time series and two EEG datasets. The results demonstrate that InfoFlowNet can extract time-varying causal relationships among processes, reflected in the fluctuation of dIF values. Compared with the Granger causality model and temporal causal discovery framework, InfoFlowNet can identify more significant causal edges underlying EEG processes while maintaining an acceptable computation time. Our work demonstrates the potential of InfoFlowNet for analyzing effective connectivity in EEG data. The findings highlight the importance of effective connectivity in understanding the complex dynamics of the brain network. Copyright © 2023, The Authors. All rights reserved.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Using deep learning to generate key variables in global mitigation scenarios

引用

Nature Climate Change 2025年 1-9页

作者： Peijin Li Peijie Zhou Rongqi Zhu Yang Ou Haewon McJeon Edward Byers Center for Machine Learning Research and Center for Data Science Peking University Beijing China AI for Science Institute Beijing China National Engineering Laboratory for Big Data Analysis and Applications Beijing China College of Environmental Sciences and Engineering Peking University Beijing China Institute of Carbon Neutrality Peking University Beijing China Graduate School of Green Growth and Sustainability Korea Advanced Institute of Science and Technology Daejeon Republic of Korea International Institute for Applied Systems Analysis Laxenburg Austria

Integrated assessment models (IAMs) are the dominant tools for projecting mitigation scenarios. However, IAM-based scenarios often face challenges such as modelling biases and large computational burden. Here we develop a deep learning framework to generate key variables through synthetic mitigation scenarios aligned with the Sixth Assessment Report (AR6) Scenarios Database. By analysing 1,202 scenarios from a diverse set of IAMs, we select key drivers that enable a more detailed sectoral representation. Next, we trained three generative deep learning models to produce 30,000 synthetic scenarios at low computational cost across various IPCC AR6 climate categories, replicating variable distributions and correlations while also demonstrating physical consistency in power sector variables through internal validation checks. We found that the variational autoencoder achieved the highest label transferring accuracy among three frameworks. This study illustrates the potential of deep learning to complement IAM approaches and provides a basis for handling complex mitigation scenario generation tasks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SE(3)-equivariant prediction of molecular wavefunctions and electronic densities 21

SE(3)-equivariant prediction of molecular wavefunctions and ...

引用

Proceedings of the 35th International Conference on Neural Information Processing systems

作者： Oliver T. Unke Mihail Bogojeski Michael Gastegger Mario Geiger Tess Smidt Klaus-Robert Müller Machine Learning Group Technische Universität Berlin Berlin Germany and DFG Cluster of Excellence "Unifying Systems in Catalysis" (UniSysCat) Technische Universität Berlin Berlin Germany and BIFOLD – Berlin Institute for the Foundations of Learning and Data Berlin Germany and Google Research Brain Team Berlin Germany Machine Learning Group Technische Universität Berlin Berlin Germany and BIFOLD – Berlin Institute for the Foundations of Learning and Data Berlin Germany Machine Learning Group Technische Universität Berlin Berlin Germany and DFG Cluster of Excellence "Unifying Systems in Catalysis" (UniSysCat) Technische Universität Berlin Berlin Germany and BASLEARN – TU Berlin/BASF Joint Lab for Machine Learning Technische Universität Berlin Berlin Germany Institute of Physics École Polytechnique Fédérale de Lausanne Lausanne Switzerland Computational Research Division Lawrence Berkeley National Laboratory Berkeley CA and Center for Advanced Mathematics for Energy Research Applications (CAMERA) Lawrence Berkeley National Laboratory Berkeley CA Machine Learning Group Technische Universität Berlin Berlin Germany Department of Artificial Intelligence Korea University Anam-dong Seongbuk-gu Seoul Korea and Max Planck Institute for Informatics Stuhlsatzenhausweg 66123 Saarbrücken Germany and BIFOLD – Berlin Institute for the Foundations of Learning and Data Berlin Germany and Google Research Brain Team Berlin Germany

ISBN: (纸本)9781713845393

Machine learning has enabled the prediction of quantum chemical properties with high accuracy and efficiency, allowing to bypass computationally costly ab initio calculations. Instead of training on a fixed set of properties, more recent approaches attempt to learn the electronic wavefunction (or density) as a central quantity of atomistic systems, from which all other observables can be derived. This is complicated by the fact that wavefunctions transform non-trivially under molecular rotations, which makes them a challenging prediction target. To solve this issue, we introduce general SE(3)-equivariant operations and building blocks for constructing deep learning architectures for geometric point cloud data and apply them to reconstruct wavefunctions of atomistic systems with unprecedented accuracy. Our model achieves speedups of over three orders of magnitude compared to ab initio methods and reduces prediction errors by up to two orders of magnitude compared to the previous state-of-the-art. This accuracy makes it possible to derive properties such as energies and forces directly from the wavefunction in an end-to-end manner. We demonstrate the potential of our approach in a transfer learning application, where a model trained on low accuracy reference wavefunctions implicitly learns to correct for electronic many-body interactions from observables computed at a higher level of theory. Such machine-learned wavefunction surrogates pave the way towards novel semi-empirical methods, offering resolution at an electronic level while drastically decreasing computational cost. Additionally, the predicted wavefunctions can serve as initial guess in conventional ab initio methods, decreasing the number of iterations required to arrive at a converged solution, thus leading to significant speedups without any loss of accuracy or robustness. While we focus on physics applications in this contribution, the proposed equivariant framework for deep learning on point clouds is p

关键词：

来源：评论

学校读者我要写书评

暂无评论

Serial-EMD: Fast empirical mode decomposition method for multi-dimensional signals based on serialization

arXiv

引用

arXiv 2021年

作者： Zhang, Jin Feng, Fan Marti-Puig, Pere Caiafa, Cesar F. Sun, Zhe Duan, Feng Solé-Casals, Jordi College of Computer Science Nankai University Tianjin300071 China College of Artificial Intelligence Nankai University Tianjin300350 China Data and Signal Processing Group University of Vic—Central University of Catalonia Catalonia Vic08500 Spain Instituto Argentino de Radioastronomía CONICET CCT La Plata CIC-PBA UNLP V. Elisa1894 Argentina Tensor Learning Team Center for Advanced Intelligence Project RIKEN Tokyo103-0027 Japan Computational Engineering Applications Unit Head Office for Information Systems and Cybersecurity RIKEN Saitama351-0198 Japan

Empirical mode decomposition (EMD) has developed into a prominent tool for adaptive, scale-based signal analysis in various fields like robotics, security and biomedical engineering. Since the dramatic increase in amount of data puts forward higher requirements for the capability of real-time signal analysis, it is difficult for existing EMD and its variants to trade off the growth of data dimension and the speed of signal analysis. In order to decompose multi-dimensional signals at a faster speed, we present a novel signal-serialization method (serial-EMD), which concatenates multi-variate or multi-dimensional signals into a one-dimensional signal and uses various one-dimensional EMD algorithms to decompose it. To verify the effects of the proposed method, synthetic multi-variate time series, artificial 2D images with various textures and real-world facial images are tested. Compared with existing multi-EMD algorithms, the decomposition time becomes significantly reduced. In addition, the results of facial recognition with Intrinsic Mode Functions (IMFs) extracted using our method can achieve a higher accuracy than those obtained by existing multi-EMD algorithms, which demonstrates the superior performance of our method in terms of the quality of IMFs. Furthermore, this method can provide a new perspective to optimize the existing EMD algorithms, that is, transforming the structure of the input signal rather than being constrained by developing envelope computation techniques or signal decomposition methods. In summary, the study suggests that the serial-EMD technique is a highly competitive and fast alternative for multi-dimensional signal analysis. Copyright © 2021, The Authors. All rights reserved.

关键词： Signal analysis

来源：评论

学校读者我要写书评

暂无评论

Misconceptions Mining and Visualizations for Chinese-Based MOOCs Forum Based on NLP 2

Misconceptions Mining and Visualizations for Chinese-Based M...

引用

2017 IEEE 2nd International Conference on Big Data Analysis（ICBDA 2017）

作者： Hao-Hsuan Hsu Nen-Fu Huang So-Chen Chen Chia-An Lee Jian-Wei Tzeng Institute of Information Systems and Applications Tsing Hua University Netxtream Technologies Inc. Department of Computer Science Tsing Hua University Center for Teaching and Learning Development Tsing Hua University

ISBN: (纸本)9781509036202

With the popularity of MOOCs(Massive Open Online Courses),massive structured,semi-structured and unstructured data about learning is recorded for further analysis and *** is the direct way for learners to ask questions and clarify their ***,we utilize the plain text of posts and responses in MOOCs forum to extract keywords of misconceptions for instructors based on Natural Language Processing(NLP) *** this study,the researchers mining these misconceptions from over 120 thousands of single Chinese words and 15 thousands of English words in a ***,we visualize them by word clouds and social network graphs for quickly and better understanding of misconceptions and their correlation.

关键词： MOOCs misconceptions mining Chinese-based forum NLP word cloud social network graph

来源：评论

学校读者我要写书评

暂无评论

FAIR for AI: An interdisciplinary and international community building perspective

arXiv

引用

arXiv 2022年

作者： Huerta, E.A. Blaiszik, Ben Brinson, L. Catherine Bouchard, Kristofer E. Diaz, Daniel Doglioni, Caterina Duarte, Javier M. Emani, Murali Foster, Ian Fox, Geoffrey Harris, Philip Heinrich, Lukas Jha, Shantenu Katz, Daniel S. Kindratenko, Volodymyr Kirkpatrick, Christine R. Lassila-Perini, Kati Madduri, Ravi K. Neubauer, Mark S. Psomopoulos, Fotis E. Roy, Avik Rübel, Oliver Zhao, Zhizhen Zhu, Ruike Data Science and Learning Division Argonne National Laboratory LemontIL60439 United States Department of Computer Science University of Chicago ChicagoIL60637 United States Globus University of Chicago ChicagoIL60637 United States Department of Mechanical Engineering and Materials Science Duke University DurhamNC27708 United States Scientific Data Division Lawrence Berkeley National Laboratory BerkeleyCA94720 United States Biological Systems & Engineering Lawrence Berkeley National Laboratory BerkeleyCA94720 United States Helen Wills Neuroscience Institute University of California Berkeley BerkeleyCA94720 United States Department of Physics University of California La Jolla San DiegoCA92093 United States Lund University Department of Physics Box 118 Lund221 00 Sweden School of Physics & Astronomy The University of Manchester ManchesterM13 9PL United Kingdom Leadership Computing Facility Argonne National Laboratory LemontIL60439 United States Biocomplexity Institute Department of Computer Science University of Virginia CharlottesvilleVA22904 United States Department of Physics Massachusetts Institute of Technology CambridgeMA02139 United States Technical University Munich Arcisstraße 21 München80333 Germany Computational Science Initiative Brookhaven National Laboratory UptonNY11973 United States Electrical and Computer Engineering Rutgers The State University of New Jersey PiscatawayNJ08854 United States National Center for Supercomputing Applications University of Illinois Urbana-Champaign UrbanaIL61801 United States Department of Computer Science University of Illinois at Urbana-Champaign UrbanaIL61801 United States Department of Electrical & Computer Engineering University of Illinois at Urbana-Champaign UrbanaIL61801 United States School of Information Sciences University of Illinois at Urbana-Champaign UrbanaIL61801 United States San Diego Supercomputer Center University of California La Jolla San DiegoCA

A foundational set of findable, accessible, interoperable, and reusable (FAIR) principles were proposed in 2016 as prerequisites for proper data management and stewardship, with the goal of enabling the reusability of scholarly data. The principles were also meant to apply to other digital assets, at a high level, and over time, the FAIR guiding principles have been reinterpreted or extended to include the software, tools, algorithms, and workflows that produce data. FAIR principles are now being adapted in the context of AI models and datasets. Here, we present the perspectives, vision, and experiences of researchers from different countries, disciplines, and backgrounds who are leading the definition and adoption of FAIR principles in their communities of practice, and discuss outcomes that may result from pursuing and incentivizing FAIR AI research. The material for this report builds on the FAIR for AI Workshop held at Argonne National Laboratory on June 7, 2022. Copyright © 2022, The Authors. All rights reserved.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

Selective Combination of Pivot and Direct Statistical Machine Translation Models 6

Selective Combination of Pivot and Direct Statistical Machin...

引用

6th International Joint Conference on Natural Language Processing, IJCNLP 2013

作者： El Kholy, Ahmed Habash, Nizar Leusch, Gregor Matusov, Evgeny Sawaf, Hassan Center for Computational Learning Systems Columbia University Science Applications International Corporation eBay Inc

ISBN: (纸本)9784990734800

In this paper, we propose a selective combination approach of pivot and direct statistical machine translation (SMT) models to improve translation quality. We work with Persian-Arabic SMT as a case study. We show positive results (from 0.4 to 3.1 BLEU on different direct training corpus sizes) in addition to a large reduction of pivot translation model size. © IJCNLP *** right reserved.

关键词： Computer aided language translation

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：