检索结果-内蒙古大学图书馆

Feature selection with distance correlation

Physical Review D 2024年第5期109卷 054009-054009页

作者： Ranit Das Gregor Kasieczka David Shih NHETC Department of Physics and Astronomy Rutgers University Piscataway New Jersey 08854 USA Institut für Experimentalphysik Universität Hamburg 22761 Hamburg Germany Center for Data and Computing in Natural Sciences (CDCS) 22607 Hamburg Germany

Choosing which properties of the data to use as input to multivariate decision algorithms—also known as feature selection—is an important step in solving any problem with machine learning. While there is a clear trend towards training sophisticated deep networks on large numbers of relatively unprocessed inputs (so-called automated feature engineering), for many tasks in physics, sets of theoretically well-motivated and well-understood features already exist. Working with such features can bring many benefits, including greater interpretability, reduced training and run time, and enhanced stability and robustness. We develop a new feature selection method based on distance correlation, and demonstrate its effectiveness on the tasks of boosted top- and W-tagging. Using our method to select features from a set of over 7,000 energy flow polynomials, we show that we can match the performance of much deeper architectures, by using only ten features and two orders-of-magnitude fewer model parameters.

关键词： Phenomenology Signatures with jets Signatures with top quarks Strong interaction Machine learning Particle data analysis

来源：评论

学校读者我要写书评

暂无评论

Fast Simulation of Highly Granular Calorimeters with Generative Models: Towards a First Physics Application

Fast Simulation of Highly Granular Calorimeters with Generat...

引用

2023 European Physical Society Conference on High Energy Physics, EPS-HEP 2023

作者： Buhmann, Erik Buss, Thorsten Diefenbacher, Sascha Eren, Engin Gaede, Frank Kasieczka, Gregor Korcari, William Korol, Anatolii Krüger, Katja Madlener, Thomas McKeown, Peter Rustige, Lennart Institut für Experimentalphysik Universität Hamburg Luruper Chaussee 149 Hamburg22761 Germany Physics Division Lawrence Berkeley National Laboratory 1 Cyclotron Rd BerkeleyCA94720 United States Deutsches Elektronen-Synchrotron DESY Notkestr. 85 Hamburg22607 Germany Center for Data and Computing in Natural Sciences CDCS Deutsches Elektronen-Synchrotron DESY Notkestr. 85 Hamburg22607 Germany

While simulation plays a crucial role in high energy physics, it also consumes a significant fraction of the available computational resources, with these computing pressures being set to increase drastically for the upcoming high luminosity phase of the LHC and for future colliders. At the same time, the significantly higher granularity present in future detectors increases the physical accuracy required of a surrogate simulator. Machine learning methods based on deep generative models hold promise to provide a computationally efficient solution, while retaining a high degree of physical fidelity. Significant strides have already been taken towards developing these models for the generation of particle showers in highly granular calorimeters, the subdetector which constitutes the most computationally intensive part of a detector simulation. However, to apply these models to a general detector simulation, methods must be developed to cope with particles incident at various points and under varying angles in the detector. This contribution will address steps taken to tackle the challenges faced when applying these simulators in more general scenarios, as well as the effects on physics observables after interfacing with reconstruction algorithms. In particular, results achieved with bounded information bottleneck and normalising flow architectures based on regular grid geometries, as well as a more flexible diffusion model using point clouds, will be discussed. Combined with progress on integrating these surrogate simulators into existing full simulation chains, these developments bring an application to benchmark physics analyses closer. © Copyright owned by the author(s) under the terms of the Creative Commons.

关键词： Calorimeters

来源：评论

学校读者我要写书评

暂无评论

Characterizing Complex Network Properties of Knowledge Graphs 15

Characterizing Complex Network Properties of Knowledge Graph...

引用

15th International Conference on Knowledge Engineering and Ontology Development, KEOD 2023 as part of the 15th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management, IC3K 2023

作者： Rossanez, Anderson da Silva Torres, Ricardo dos Reis, Julio Cesar Institute of Computing University of Campinas SP Campinas Brazil Agricultural Biosystems Engineering Wageningen Data Competence Center Wageningen University & Research Wageningen Netherlands Department of ICT and Natural Sciences Norwegian University of Science and Technology Ålesund Norway

ISBN: (纸本)9789897586712

Knowledge Graphs have been established as one the most relevant representations to encode knowledge, with relevant applications in the public and private sectors. One common research direction concerning the analysis of created knowledge graphs relies on the assumption that their intrinsic properties and structure are similar to what is observed in complex networks. However, studies concerning identifying typical complex network structures in knowledge graphs are lacking in the literature. This paper bridges this gap by analyzing commonly and recently used knowledge graphs in the semantic web field, seeking to demonstrate their complex network properties. Evaluation involving DBpedia and Wikidata data confirms the occurrence of intrinsic complex network structures in their respective knowledge graphs. Copyright © 2023 by SCITEPRESS – science and Technology Publications, Lda. Under CC license (CC BY-NC-ND 4.0).

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Resonant anomaly detection without background sculpting

引用

Physical Review D 2023年第11期107卷 114012-114012页

作者： Anna Hallin Gregor Kasieczka Tobias Quadfasel David Shih Manuel Sommerhalder NHETC Department of Physics and Astronomy Rutgers University Piscataway New Jersey 08854 USA Institut für Experimentalphysik Universität Hamburg 22761 Hamburg Germany Center for Data and Computing in Natural Sciences (CDCS) 22607 Hamburg Germany

We introduce a new technique named latent CATHODE (LaCATHODE) for performing “enhanced bump hunts,” a type of resonant anomaly search that combines conventional one-dimensional bump hunts with a model-agnostic anomaly score in an auxiliary feature space where potential signals could also be localized. The main advantage of LaCATHODE over existing methods is that it provides an anomaly score that is well behaved when evaluating it beyond the signal region, which is essential to prevent the sculpting of background distributions in the bump hunt. LaCATHODE accomplishes this by constructing the anomaly score directly in the latent space learned by a conditional normalizing flow trained on sideband regions. We demonstrate the superior stability and comparable performance of LaCATHODE for enhanced bump hunting in an illustrative toy example as well as on the LHC Olympics R&D dataset.

关键词： Hadronic decays Particle phenomena Hypothetical particles Artificial neural networks data analysis Hadron colliders Machine learning

来源：评论

学校读者我要写书评

暂无评论

Generative Models for Fast Simulation of Electromagnetic and Hadronic Showers in Highly Granular Calorimeters 41

Generative Models for Fast Simulation of Electromagnetic and...

引用

41st International Conference on High Energy Physics, ICHEP 2022

作者： Bieringer, S. Buhmann, E. Diefenbacher, S. Eren, E. Gaede, F. Kasieczka, G. Korcari, W. Korol, A. Krüger, K. McKeown, P. Rustige, L. Shekhzadeh, I. Institut für Experimentalphysik Universität Hamburg Luruper Chaussee 149 Hamburg22761 Germany Deutsches Elektronen-Synchrotron DESY Notkestr. 85 Hamburg22607 Germany Center for Data and Computing in Natural Sciences CDCS Deutsches Elektronen-Synchrotron DESY Notkestr. 85 Hamburg22607 Germany

While simulation is a crucial cornerstone of modern high energy physics, it places a heavy burden on the available computing resources. These computing pressures are expected to become a major bottleneck for the upcoming high luminosity phase of the LHC and for future colliders, motivating a concerted effort to develop computationally efficient solutions. Methods based on generative machine learning models hold promise to alleviate the computational strain produced by simulation, while providing the physical accuracy required of a surrogate simulator. This contribution provides an overview of a growing body of work focused on simulating showers in highly granular calorimeters, which is making significant strides towards realising fast simulation tools based on deep generative models. Progress on the simulation of both electromagnetic and hadronic showers will be reported, with a focus on the high degree of physical fidelity achieved. Additional steps taken to address the challenges faced when broadening the scope of these simulators, such as those posed by multi-parameter conditioning, will also be discussed. © Copyright owned by the author(s) under the terms of the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License (CC BY-NC-ND 4.0)

关键词： Calorimeters

来源：评论

学校读者我要写书评

暂无评论

Tree-based algorithms for weakly supervised anomaly detection

引用

Physical Review D 2024年第3期109卷 034033-034033页

作者： Thorben Finke Marie Hein Gregor Kasieczka Michael Krämer Alexander Mück Parada Prangchaikul Tobias Quadfasel David Shih Manuel Sommerhalder Institut für Theoretische Teilchenphysik und Kosmologie RWTH Aachen University 52074 Aachen Germany Institut für Experimentalphysik Universität Hamburg 22761 Hamburg Germany Center for Data and Computing in Natural Sciences (CDCS) 22607 Hamburg Germany NHETC Department of Physics and Astronomy Rutgers University Piscataway New Jersey 08854 USA

Weakly supervised methods have emerged as a powerful tool for model-agnostic anomaly detection at the Large Hadron Collider (LHC). While these methods have shown remarkable performance on specific signatures such as dijet resonances, their application in a more model-agnostic manner requires dealing with a larger number of potentially noisy input features. In this paper, we show that using boosted decision trees as classifiers in weakly supervised anomaly detection gives superior performance compared to deep neural networks. Boosted decision trees are well known for their effectiveness in tabular data analysis. Our results show that they not only offer significantly faster training and evaluation times, but they are also robust to a large number of noisy input features. By using advanced gradient boosted decision trees in combination with ensembling techniques and an extended set of features, we significantly improve the performance of weakly supervised methods for anomaly detection at the LHC. This advance is a crucial step toward a more model-agnostic search for new physics.

关键词： Hadronic decays Particle production Hypothetical particles data analysis Hadron colliders Machine learning

来源：评论

学校读者我要写书评

暂无评论

Kinematic inventory of rock glaciers in the Nyainqentanglha Range using the MT-InSAR method

引用

International Journal of Digital Earth 2023年第1期16卷 3923-3948页

作者： Xuefei Zhang Min Feng Jinhao Xu Dezhao Yan Jing Wang Xiaoqing Zhou Tao Li Xiang Zhang Land Satellite Remote Sensing Application Center Ministry of Natural ResourcesBeijingPeople’s Republic of China Tibetan Plateau Data Center State Key Laboratory of Tibetan Plateau Earth SystemEnvironment and Resources(TPESER)Institute of Tibetan Plateau ResearchChinese Academy of SciencesBeijingPeople’s Republic of China Academy of Plateau Science and Sustainability Qinghai Normal UniversityXiningPeople’s Republic of China University of Chinese Academy of Sciences BeijingPeople’s Republic of China Research Institute of Intelligent Computing Zhejiang LaboratoryHangzhouPeople’s Republic of China

Rock glaciers are typical periglacial landforms with tongue or lobate morphological shapes and characterized by the distinct front,lateral margins,and often by ridge-and-furrow surface topography textures as well as kinematic characteristics,widely distributed in alpine *** Synthetic aperture radar interferometry(MT-InSAR),is a remote sensing technique with demonstrated effectiveness for detecting landform ***,its application to rock glaciers is challenged by temporal decorrelation and atmospheric phase noises due to complex topography and snow *** designed a quadtree segmentation and parallel computing-based MT-InSAR method to improve the quality and efficiency of deformation measurement of rock *** applied the method to a rock glacier inventory of the Nyainqentanglha Range,China,derived from high-resolution Gaofen-2 images,to quantify the activity rate of each rock *** showed that 32.1%(6,389)of the identified rock glaciers exhibited slope-parallel deformation rates exceeding 100 mm/*** activities of the rock glaciers exhibited strong correlations with their distance to glaciers,precipitation,freeze-thaw magnitude,and permafrost occurrence *** results demonstrate the effectiveness of the developed segmentation-parallel MT-InSAR method for monitoring rock glacier deformation over a large region.

关键词： Rock glacier MT-InSAR quadtree segmentation Nyaingentanglha kinematics

来源：评论

学校读者我要写书评

暂无评论

MetaCity: data-driven sustainable development of complex cities

引用

The Innovation 2025年第2期6卷 88-103,87页

作者： Yunke Zhang Yuming Lin Guanjie Zheng Yu Liu Nicholas Sukiennik Fengli Xu Yongjun Xu Feng Lu Qi Wang Yuan Lai Li Tian Nan Li Dongping Fang Fei Wang Tao Zhou Yong Li Yu Zheng Zhiqiang Wu Huadong Guo Department of Electronic Engineering Beijing National Research Center for Information Science and Technology(BNRist)Tsinghua UniversityBeijing 100084China John Hopcroft Center for Computer Science Shanghai Jiao Tong UniversityShanghai 200240China University of Chinese Academy of Sciences Beijing 100049China Institute of Computing Technology Chinese Academy of SciencesBeijing 100190China Institute of Geographic Sciences and Natural Resources Research Chinese Academy of SciencesBeijing 100101China Department of Civil and Environmental Engineering Northeastern UniversityBostonMA 02115USA School of Architecture Tsinghua UniversityBeijing 100084China School of Civil Engineering Tsinghua UniversityBeijing 100084China Big Data Research Center University of Electronic Science and Technology of ChinaChengdu 611731China JD iCity JD Technology&JD Intelligent Cities ResearchBeijing 100176China College of Architecture and Urban Planning Tongji UniversityShanghai 200292China International Research Center of Big Data for Sustainable Development Goals Beijing 100094China Aerospace Information Research Institute Chinese Academy of SciencesBeijing 100094China These authors contributed equally

Cities are complex systems that develop under complicated interactions among their human and environmental *** generates substantial outcomes and opportunities while raising challenges including congestion,air pollution,inequality,etc.,calling for efficient and reasonable solutions to sustainable ***,booming technologies generate large-scale data of complex cities,providing a chance to propose data-driven solutions for sustainable urban *** paper provides a comprehensive overview of data-driven urban sustainability *** this review article,we conceptualize MetaCity,a general framework for optimizing resource usage and allocation problems in complex cities with data-driven *** this framework,we decompose specific urban sustainable goals,e.g.,efficiency and resilience,review practical urban problems under these goals,and explore the probability of using data-driven technologies as potential solutions to the challenge of *** the basis of extensive urban data,we integrate urban problem discovery,operation of urban systems simulation,and complex decision-making problem solving into an entire cohesive framework to achieve sustainable development goals by optimizing resource allocation problems in complex cities.

关键词： resource usage sustainable development urbanization resilience data driven urban systems simulation complex cities complexity

来源：评论

学校读者我要写书评

暂无评论

data-driven Intra-Autonomous Systems Graph Generator

arXiv

引用

arXiv 2023年

作者： Dadauto, Caio Vinicius da Fonseca, Nelson Luis Saldanha Torres, Ricardo da Silva The Institute of Computing UNICAMP University of Campinas Brazil The Department of ICT and Natural Sciences NTNU Norwegian University of Science and Technologies Ålesund Norway Wageningen Data Competence Center Wageningen Netherlands

Accurate modeling of realistic network topologies is essential for evaluating novel Internet solutions. Current topology generators, notably scale-free-based models, fail to capture multiple properties of intra-AS topologies. While scale-free networks encode node-degree distribution, they overlook crucial graph properties like betweenness, clustering, and assortativity. The limitations of existing generators pose challenges for training and evaluating deep learning models in communication networks, emphasizing the need for advanced topology generators encompassing diverse Internet topology characteristics. This paper introduces a novel deep-learning-based generator of synthetic graphs representing intra-autonomous in the Internet, named Deep-Generative Graphs for the Internet (DGGI). It also presents a novel massive dataset of real intra-AS graphs extracted from the project Internet Topology data Kit (ITDK), called Internet Graphs (IGraphs)1. It is shown that DGGI creates synthetic graphs that accurately reproduce the properties of centrality, clustering, assortativity, and node degree. The DGGI generator overperforms existing Internet topology generators. On average, DGGI improves the Maximum Mean Discrepancy (MMD) metric 84.4%, 95.1%, 97.9%, and 94.7% for assortativity, betweenness, clustering, and node degree, respectively. © 2023, CC BY-SA.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Morphological classification of radio galaxies with Wasserstein generative adversarial network-supported augmentation

引用

RAS Techniques and Instruments 2023年第1期2卷 264-277页

作者： Rustige, Lennart Kummer, Janis Griese, Florian Borras, Kerstin Brüggen, Marcus Connor, Patrick L.S. Gaede, Frank Kasieczka, Gregor Knopp, Tobias Schleper, Peter Center for Data and Computing in Natural Sciences (CDCS) Notkestrasse 9 Hamburg D-22607 Germany Deutsches Elektronen-Synchrotron DESY Notkestrasse 85 Hamburg D-22607 Germany Universität Hamburg Hamburger Sternwarte Gojenbergsweg 112 Hamburg D-21029 Germany Section for Biomedical Imaging University Medical Center Hamburg-Eppendorf Hamburg D-20246 Germany Institute for Biomedical Imaging Hamburg University of Technology Hamburg D-21073 Germany Physics Institute III A RWTH Aachen University Templergraben 55 Aachen D-52062 Germany Institut für Experimentalphysik Universität Hamburg Luruper Chaussee 149 Hamburg D-22761 Germany

Machine learning techniques that perform morphological classification of astronomical sources often suffer from a scarcity of labelled training data. Here, we focus on the case of supervised deep learning models for the morphological classification of radio galaxies, which is particularly topical for the forthcoming large radio surveys. We demonstrate the use of generative models, specifically Wasserstein generative adversarial networks (wGANs), to generate data for different classes of radio galaxies. Further, we study the impact of augmenting the training data with images from our wGAN on three different classification architectures. We find that this technique makes it possible to improve models for the morphological classification of radio galaxies. A simple fully connected neural network benefits most from including generated images into the training set, with a considerable improvement of its classification accuracy. In addition, we find it is more difficult to improve complex classifiers. The classification performance of a convolutional neural network can be improved slightly. However, this is not the case for a vision transformer. © 2023 The Author(s)

关键词： data Methods Machine Learning methods: data analysis methods: statistical radio continuum: galaxies techniques: image processing

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：