检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Reul, Christian Christ, Dennis Hartelt, Alexander Balbach, Nico Wehner, Maximilian Springmann, Uwe Wick, Christoph Grundig, Christine Büttner, Andreas Puppe, Frank Chair for Artificial Intelligence and Applied Computer Science University of Würzburg Würzburg97074 Germany Center for Information and Language Processing LMU Munich Munich80538 Germany Institute for Modern Art History University of Zurich Zurich8006 Switzerland Institute for Philosophy University of Würzburg Würzburg97074 Germany

Optical Character Recognition (OCR) on historical printings is a challenging task mainly due to the complexity of the layout and the highly variant typography. Nevertheless, in the last few years great progress has been made in the area of historical OCR, resulting in several powerful open-source tools for preprocessing, layout recognition and segmentation, character recognition and post-processing. The drawback of these tools often is their limited applicability by non-technical users like humanist scholars and in particular the combined use of several tools in a workflow. In this paper we present an open-source OCR software called OCR4all, which combines state-of-the-art OCR components and continuous model training into a comprehensive workflow. A comfortable GUI allows error corrections not only in the final output, but already in early stages to minimize error propagations. Further on, extensive configuration capabilities are provided to set the degree of automation of the workflow and to make adaptations to the carefully selected default parameters for specific printings, if necessary. Experiments showed that users with minimal or no experience were able to capture the text of even the earliest printed books with manageable effort and great quality, achieving excellent character error rates (CERs) below 0.5%. The fully automated application on 19th century novels showed that OCR4all can considerably outperform the commercial state-of-the-art tool ABBYY Finereader on moderate layouts if suitably pretrained mixed OCR models are available. The architecture of OCR4all allows the easy integration (or substitution) of newly developed tools for its main components by standardized interfaces like PageXML, thus aiming at continual higher automation for historical printings. Copyright © 2019, The Authors. All rights reserved.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

Erratum to: Search for resonant and nonresonant production of pairs of dijet resonances in proton-proton collisions at = 13 TeV

引用

Journal of High Energy Physics 2025年第5期2025卷 1-23页

作者： Tumasyan, A. Adam, W. Andrejkovic, J. W. Bergauer, T. Chatterjee, S. Damanakis, K. Dragicevic, M. Escalante Del Valle, A. Hussain, P. S. Jeitler, M. Krammer, N. Lechner, L. Liko, D. Mikulec, I. Paulitsch, P. Pitters, F. M. Schieck, J. Schöfbeck, R. Schwarz, D. Templ, S. Waltenberger, W. Wulz, C.-E. Darwish, M. R. Janssen, T. Kello, T. Rejeb Sfar, H. Van Mechelen, P. Bols, E. S. D’Hondt, J. De Moor, A. Delcourt, M. El Faham, H. Lowette, S. Moortgat, S. Morton, A. Müller, D. Sahasransu, A. R. Tavernier, S. Van Doninck, W. Vannerom, D. Clerbaux, B. De Lentdecker, G. Favart, L. Jaramillo, J. Lee, K. Mahdavikhorrami, M. Makarenko, I. Malara, A. Paredes, S. Pétré, L. Postiau, N. Starling, E. Thomas, L. Vanden Bemden, M. Vander Velde, C. Vanlaer, P. Dobur, D. Knolle, J. Lambrecht, L. Mestdach, G. Niedziela, M. Rendón, C. Roskas, C. Samalan, A. Skovpen, K. Tytgat, M. Van Den Bossche, N. Vermassen, B. Wezenbeek, L. Benecke, A. Bethani, A. Bruno, G. Bury, F. Caputo, C. David, P. Delaere, C. Donertas, I. S. Giammanco, A. Jaffel, K. Jain, Sa. Lemaitre, V. Mondal, K. Prisciandaro, J. Taliercio, A. Tran, T. T. Vischia, P. Wertz, S. Alves, G. A. Coelho, E. Hensel, C. Moraes, A. Rebello Teles, P. Aldá Júnior, W. L. Alves Gallo Pereira, M. Barroso Ferreira Filho, M. Brandao Malbouisson, H. Carvalho, W. Chinellato, J. Da Costa, E. M. Da Silveira, G. G. De Jesus Damiao, D. Dos Santos Sousa, V. Fonseca De Souza, S. Martins, J. Mora Herrera, C. Mota Amarilo, K. Mundim, L. Nogima, H. Santoro, A. Silva Do Amaral, S. M. Sznajder, A. Thiel, M. Torres Da Silva De Araujo, F. Vilela Pereira, A. Bernardes, C. A. Calligaris, L. Fernandez Perez Tomei, T. R. Gregores, E. M. Mercadante, P. G. Novaes, S. F. Padula, Sandra S. Aleksandrov, A. Antchev, G. Hadjiiska, R. Iaydjiev, P. Misheva, M. Rodozov, M. Shopova, M. Sultanov, G. Dimitrov, A. Ivanov, T. Litov, L. Pavlov, B. Petkov, P. Petrov, A. Shumka, E. Cheng, T. Javaid, T. Mittal, M. Yuan, L. Ahmad, M. Bauer, G. Hu, Z. Lezki, S. Yi, K. Chen, G. M. Chen, H. S. Chen, M. Iemmi, F. Jiang, C. H. Kapo Yerevan Physics Institute Yerevan Armenia Yerevan State University Yerevan Armenia Institut für Hochenergiephysik Vienna Austria TU Wien Vienna Austria Universiteit Antwerpen Antwerpen Belgium Institute of Basic and Applied Sciences Faculty of Engineering Arab Academy for Science Technology and Maritime Transport Alexandria Egypt Université Libre de Bruxelles Bruxelles Belgium Vrije Universiteit Brussel Brussel Belgium Ghent University Ghent Belgium Université Catholique de Louvain Louvain-la-Neuve Belgium Centro Brasileiro de Pesquisas Fisicas Rio de Janeiro Brazil Universidade do Estado do Rio de Janeiro Rio de Janeiro Brazil Universidade Estadual de Campinas Campinas Brazil Federal University of Rio Grande do Sul Porto Alegre Brazil UFMS Nova Andradina Brazil The University of the State of Amazonas Manaus Brazil Universidade Estadual Paulista Universidade Federal do ABC São Paulo Brazil Institute for Nuclear Research and Nuclear Energy Bulgarian Academy of Sciences Sofia Bulgaria University of Sofia Sofia Bulgaria Beihang University Beijing China University of Chinese Academy of Sciences Beijing China Department of Physics Tsinghua University Beijing China Nanjing Normal University Department of Physics Nanjing China The University of Iowa Iowa City USA Institute of High Energy Physics Beijing China State Key Laboratory of Nuclear Physics and Technology Peking University Beijing China Sun Yat-Sen University Guangzhou China Institute of Modern Physics and Key Laboratory of Nuclear Physics and Ion-beam Application (MOE) - Fudan University Shanghai China Zhejiang University Hangzhou China Universidad de Los Andes Bogota Colombia Universidad de Antioquia Medellin Colombia University of Split Faculty of Electrical Engineering Mechanical Engineering and Naval Architecture Split Croatia University of Split Faculty of Science Split Croatia Institute Rudjer Boskovic Zagreb Croatia University of Cyprus Nicosia Cyprus Charles University Prag

来源：评论

学校读者我要写书评

暂无评论

Towards Neural Charged Particle Tracking in Digital Tracking Calorimeters with Reinforcement Learning

TechRxiv

引用

TechRxiv 2022年

作者： Kortus, Tobias Keidel, Ralf Gauger, Nicolas R. Aehle, Max Alme, Johan Barnaföldi, Gergely Gábor Bodova, Tea Borshchov, Vyacheslav van den Brink, Anthony Chaar, Mamdouh Eikeland, Viljar Feofilov, Gregory Garth, Christoph Genov, Georgi Grøttvik, Ola Helstrup, Håvard Igolkin, Sergey Keidel, Ralf Kobdaj, Chinorat Leonhardt, Viktor Mehendale, Shruti Mulawade, Raju Ningappa Odland, Odd Harald O’Neill, George Papp, Gábor Peitzmann, Thomas Pettersen, Helge Egil Seime Piersimoni, Pierluigi Protsenko, Maksym Rauch, Max Rehman, Attiq Ur Richter, Matthias Röhrich, Dieter Santana, Joshua Schilling, Alexander Seco, Joao Songmoolnak, Arnon Sudár, Ákos Sølie, Jarle Rambo Tambave, Ganesh Tymchuk, Ihor Ullaland, Kjetil Varga-Kofarago, Monika Volz, Lennart Wagner, Boris Wendzel, Steffen Wiebel, Alexander Xiao, RenZheng Yang, Shiming Yokoyama, Hiroki Zillien, Sebastian University of Applied Sciences Worms Worms67549 Germany Chair for Scientific Computing TU Kaiserslautern Kaiserslautern67663 Germany Department of Physics and Technology University of Bergen Bergen5007 Norway Wigner Research Centre for Physics Budapest Hungary Kharkiv Ukraine Institute for Subatomic Physics Utrecht University/Nikhef Utrecht Netherlands St. Petersburg University St. Petersburg Russia Scientific Visualization Lab TU Kaiserslautern Kaiserslautern67663 Germany Department of Computer Science Electrical Engineering and Mathematical Sciences Western Norway University of Applied Sciences Bergen5020 Norway Institute of Science Suranaree University of Technology Nakhon Ratchasima Thailand Department of Oncology and Medical Physics Haukeland University Hospital Bergen5021 Norway Institute for Physics Eötvös Loránd University 1/A Pázmány P. Sétány BudapestH-1117 Hungary UniCamillus Saint Camillus International University of Health Sciences Rome Italy Department of Physics University of Oslo Oslo0371 Norway Department of Biomedical Physics in Radiation Oncology DKFZ—German Cancer Research Center Heidelberg Germany Department of Physics and Astronomy Heidelberg University Heidelberg Germany Budapest University of Technology and Economics Budapest Hungary Department of Diagnostic Physics Division of Radiology and Nuclear Medicine Oslo University Hospital Oslo Norway Bhubaneswar India Biophysics GSI Helmholtz Center for Heavy Ion Research GmbH Darmstadt Germany Department of Medical Physics and Biomedical Engineering University College London London United Kingdom College of Mechanical & Power Engineering China Three Gorges University Yichang China

We propose a novel technique for reconstructing charged particles in digital tracking calorimeters using reinforcement learning aiming to benefit from the rapid progress and success of neural network architectures without the dependency on simulated or manually-labeled data. Here we optimize by trial-and-error a behavior policy acting as an approximation to the full combinatorial optimization problem, maximizing the physical plausibility of sampled trajectories. In modern processing pipelines used in high energy physics and related applications, tracking plays an essential role allowing to identify and follow charged particle trajectories traversing particle detectors. Due to the high multiplicity of charged particles and their physical interactions, randomly deflecting the particles, the reconstruction is a challenging undertaking, requiring fast, accurate and robust algorithms. Our approach works on graph-structured data, capturing track hypotheses through edge connections between particles in the detector layers. We demonstrate in a comprehensive study on simulated data for a particle detector used for proton computed tomography, the high potential as well as the competitiveness of our approach compared to a heuristic search algorithm and a model trained on ground truth. Finally, we point out limitations of our approach, guiding towards a robust foundation for further development of reinforcement learning based tracking. © 2022, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Influence of high-energy local orbitals and electron-phonon interactions on the band gaps and optical absorption spectra of hexagonal boron nitride

引用

Physical Review B 2020年第4期102卷 045117-045117页

作者： Tong Shen Xiao-Wei Zhang Honghui Shang Min-Ye Zhang Xinqiang Wang En-Ge Wang Hong Jiang Xin-Zheng Li State Key Laboratory for Artificial Microstructure and Mesoscopic Physics Frontier Science Center for Nano-optoelectronics and School of Physics Peking University Beijing 100871 China International Center for Quantum Materials and School of Physics Peking University Beijing 100871 China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing 100871 China Beijing National Laboratory for Molecular Sciences College of Chemistry and Molecular Engineering Peking University Beijing 100871 China Collaborative Innovation Center of Quantum Matter Peking University Beijing 100871 China Ceramic Division Songshan Lake Lab Institute of Physics Chinese Academy of Sciences Guangdong 523808 China School of Physics Liaoning University Shenyang 110036 China

We report ab initio band diagram and optical absorption spectra of hexagonal boron nitride (h-BN), focusing on unravelling how the completeness of the basis set for GW calculations and electron-phonon interactions (EPIs) impact on them. The completeness of the basis set, an issue which was seldom discussed in previous optical spectra calculations of h-BN, is found crucial in providing converged quasiparticle band gaps. In the comparison among three different codes, we demonstrate that by including high-energy local orbitals in the all-electron linearized augmented plane waves based GW calculations, the quasiparticle direct and fundamental indirect band gaps are widened by ∼0.2 eV, giving values of 6.81 eV and 6.25 eV, respectively at the GW0 level. EPIs, on the other hand, reduce them to 6.62 eV and 6.03 eV respectively at 0 K, and 6.60 eV and 5.98 eV respectively at 300 K. With clamped crystal structure, the first peak of the absorption spectrum is at 6.07 eV, originating from the direct exciton contributed by electron transitions around K in the Brillouin zone. After including the EPIs-renormalized quasiparticles in the Bethe-Salpeter equation, the exciton-phonon coupling shifts the first peak to 5.83 eV at 300 K, lower than the experimental value of ∼6.00 eV. This accuracy is acceptable to an ab initio description of excited states with no fitting parameter.

关键词： Bethe-Salpeter equation Electron-phonon coupling Excitons GW method

来源：评论

学校读者我要写书评

暂无评论

The importance of the heritage values of Al-Ukhaidhir palace, Karbala city, Iraq 2

The importance of the heritage values of Al-Ukhaidhir palace...

引用

2nd International Conference on architecture and Civil Engineering, ICACE 2018

作者： Akram, Omar K Mohammed Jamil, Nada F Ismail, Sumarni Franco, Daniel J Graça, Andreia Faculty of Design and Architecture Universiti Putra Malaysia Malaysia Foreign Affairs Office Kurdistan Region Iraq Faculty of Computer Science and Information Technology Universiti Putra Malaysia Malaysia Superior School of Technology and Management Polytechnic Institute of Beja Portugal

Karbala is distinguished by its rich architectural heritage. Deterioration of historic buildings can affect the city itself as well as the country as general. This research highlights the issue that Al-Ukhaidhir palace, located in Karbala city, is facing. There is no attention from local population, neither experts to protect the architectural heritage values of Al-Ukhaidhir palace. Therefore, there is a dire need for an action to protect the historical palace, aiming to save it for next generations and to increase tourism not just in the city, but for the country in general. After the introduction of the background problem, this study presents a literature review on Al-Ukhaidhir Palace, highlighting their significant heritage values and then summarizing the issues that are presently putting Al-Ukhaidhir Palace into danger. The methodology of this research is based in a case study, which follows a Qualitative method. This study contributes in identification of the significant values of the palace, proposing a theory on the protection of Islamic architecture Heritage, from the issues that Al-Ukhaidhir Palace in Karbala City is facing and highlights the important role of experts and local population in the preservation process of heritage sites with its recommendations. It helps on the protection and documentation of heritage values in Al-Ukhaidhir Palace, having a global impact towards humanity issues. © 2018 Web Portal IOP. All rights reserved.

关键词： Facings

来源：评论

学校读者我要写书评

暂无评论

Bottom quark energy loss and hadronization with B+ and nuclear modification factors using pp and PbPb collisions at = 5.02 TeV

引用

Journal of High Energy Physics 2025年第2期2025卷 1-40页

作者： Hayrapetyan, A. Tumasyan, A. Adam, W. Andrejkovic, J. W. Bergauer, T. Chatterjee, S. Damanakis, K. Dragicevic, M. Hussain, P. S. Jeitler, M. Krammer, N. Li, A. Liko, D. Mikulec, I. Schieck, J. Schöfbeck, R. Schwarz, D. Sonawane, M. Templ, S. Waltenberger, W. Wulz, C.-E. Darwish, M. R. Janssen, T. Van Mechelen, P. Breugelmans, N. D’Hondt, J. Dansana, S. De Moor, A. Delcourt, M. Heyen, F. Lowette, S. Makarenko, I. Müller, D. Tavernier, S. Tytgat, M. Van Onsem, G. P. Van Putte, S. Vannerom, D. Bilin, B. Clerbaux, B. Das, A. K. De Lentdecker, G. Evard, H. Favart, L. Gianneios, P. Jaramillo, J. Khalilzadeh, A. Khan, F. A. Lee, K. Mahdavikhorrami, M. Malara, A. Paredes, S. Shahzad, M. A. Thomas, L. Vanden Bemden, M. Vander Velde, C. Vanlaer, P. De Coen, M. Dobur, D. Gokbulut, G. Hong, Y. Knolle, J. Lambrecht, L. Marckx, D. Mota Amarilo, K. Samalan, A. Skovpen, K. Van Den Bossche, N. van der Linden, J. Wezenbeek, L. Benecke, A. Bethani, A. Bruno, G. Caputo, C. De Favereau De Jeneret, J. Delaere, C. Donertas, I. S. Giammanco, A. Guzel, A. O. Jain, Sa. Lemaitre, V. Lidrych, J. Mastrapasqua, P. Tran, T. T. Wertz, S. Alves, G. A. Alves Gallo Pereira, M. Coelho, E. Correia Silva, G. Hensel, C. Menezes De Oliveira, T. Moraes, A. Rebello Teles, P. Soeiro, M. Vilela Pereira, A. Aldá Júnior, W. L. Barroso Ferreira Filho, M. Brandao Malbouisson, H. Carvalho, W. Chinellato, J. Da Costa, E. M. Da Silveira, G. G. De Jesus Damiao, D. Fonseca De Souza, S. Gomes De Souza, R. Macedo, M. Martins, J. Mora Herrera, C. Mundim, L. Nogima, H. Pinheiro, J. P. Santoro, A. Sznajder, A. Thiel, M. Bernardes, C. A. Calligaris, L. Fernandez Perez Tomei, T. R. Gregores, E. M. Maietto Silverio, I. Mercadante, P. G. Novaes, S. F. Orzari, B. Padula, Sandra S. Aleksandrov, A. Antchev, G. Hadjiiska, R. Iaydjiev, P. Misheva, M. Shopova, M. Sultanov, G. Dimitrov, A. Litov, L. Pavlov, B. Petkov, P. Petrov, A. Shumka, E. Keshri, S. Thakur, S. Cheng, T. Javaid, T. Yuan, L. Hu, Z. Liang, Z. Liu, J. Yi, K. Chen, G. M. Chen, H. S. Chen, M. Iemmi, F. Jiang, C. H. Yerevan Physics Institute Yerevan Armenia Yerevan State University Yerevan Armenia Institut für Hochenergiephysik Vienna Austria TU Wien Vienna Austria Universiteit Antwerpen Antwerpen Belgium Institute of Basic and Applied Sciences Faculty of Engineering Arab Academy for Science Technology and Maritime Transport Alexandria Egypt Vrije Universiteit Brussel Brussel Belgium Ghent University Ghent Belgium Université Libre de Bruxelles Bruxelles Belgium Université Catholique de Louvain Louvain-la-Neuve Belgium Centro Brasileiro de Pesquisas Fisicas Rio de Janeiro Brazil Universidade do Estado do Rio de Janeiro Rio de Janeiro Brazil Universidade Estadual de Campinas Campinas Brazil Federal University of Rio Grande do Sul Porto Alegre Brazil UFMS Nova Andradina Brazil Universidade Estadual Paulista Universidade Federal do ABC São Paulo Brazil Institute for Nuclear Research and Nuclear Energy Bulgarian Academy of Sciences Sofia Bulgaria University of Sofia Sofia Bulgaria Instituto De Alta Investigación Universidad de Tarapacá Arica Chile Beihang University Beijing China Department of Physics Tsinghua University Beijing China Nanjing Normal University Nanjing China The University of Iowa Iowa City USA Institute of High Energy Physics Beijing China University of Chinese Academy of Sciences Beijing China China Center of Advanced Science and Technology Beijing China China Spallation Neutron Source Guangdong China State Key Laboratory of Nuclear Physics and Technology Peking University Beijing China Guangdong Provincial Key Laboratory of Nuclear Science and Guangdong-Hong Kong Joint Laboratory of Quantum Matter South China Normal University Guangzhou China Sun Yat-Sen University Guangzhou China University of Science and Technology of China Hefei China Henan Normal University Xinxiang China Institute of Modern Physics and Key Laboratory of Nuclear Physics and Ion-beam Application (MOE) - Fudan University Shanghai China Zhejiang University Hangzhou Ch

The production cross sections of $$ {\textrm{B}}_{\textrm{s}}^0 $$ and B+ mesons are reported in proton-proton (pp) collisions recorded by the CMS experiment at the CERN LHC with a center-of-mass energy of 5.02 TeV. The data sample corresponds to an integrated luminosity of 302 pb−1. The cross sections are based on measurements of the $$ {\textrm{B}}_{\textrm{s}}^0 $$ → J/ψ(μ+μ−)ϕ(1020)(K+K−) and B+ → J/ψ(μ+μ−)K+ decay channels. Results are presented in the transverse momentum (pT) range 7–50 GeV/c and the rapidity interval |y| < 2.4 for the B mesons. The measured pT-differential cross sections of B+ and $$ {\textrm{B}}_{\textrm{s}}^0 $$ in pp collisions are well described by fixed-order plus next-to-leading logarithm perturbative quantum chromodynamics calculations. Using previous PbPb collision measurements at the same nucleon-nucleon center-of-mass energy, the nuclear modification factors, RAA, of the B mesons are determined. For pT > 10 GeV/c, both mesons are found to be suppressed in PbPb collisions (with RAA values significantly below unity), with less suppression observed for the $$ {\textrm{B}}_{\textrm{s}}^0 $$ mesons. In this pT range, the RAA values for the B+ mesons are consistent with those for inclusive charged hadrons and D0 mesons. Below 10 GeV/c, both B+ and $$ {\textrm{B}}_{\textrm{s}}^0 $$ are found to be less suppressed than either inclusive charged hadrons or D0 mesons, with the $$ {\textrm{B}}_{\textrm{s}}^0 $$ RAA value consistent with unity. The RAA values found for the B+ and $$ {\textrm{B}}_{\textrm{s}}^0 $$ are compared to theoretical calculations, providing constraints on the mechanism of bottom quark energy loss and hadronization in the quark-gluon plasma, the hot and dense matter created in ultrarelativistic heavy ion collisions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimizing micro-tiles in micro-structures as a design paradigm

arXiv

引用

arXiv 2019年

作者： Antolin, Pablo Buffa, Annalisa Cohen, Elaine Dannenhoffer, John F. Elber, Gershon Elgeti, Stefanie Haimes, Robert Riesenfeld, Richard École Polytechnique Fédérale de Lausanne Institute of Mathematics Lausanne Switzerland École Polytechnique Fédérale de Lausanne Institute of Mathematics Istituto di Matematica Lausanne Switzerland Department of Computer Science University of Utah SLC UT United States Mechanical & Aerospace Engineering Syracuse University SyracuseNY United States Department of Computer Science Technion Israel Institute of Technology Haifa32000 Israel Chair for Computational Analysis of Technical Systems RWTH Aachen University Aachen Germany Department of Aeronautics and Astronautics MIT CambridgeMA United States

In recent years, new methods have been developed to synthesize complex porous and micro-structured geometry in a variety of ways. In this work, we take these approaches one step further and present these methods as an efficacious design paradigm. Specifically, complex micro-structure geometry can be synthesized while optimizing certain properties such as maximal heat exchange in heat exchangers, or minimal weight under stress specifications. By being able to adjust the geometry, the topology and/or the material properties of individual tiles in the micro-structure, possibly in a gradual way, a porous object can be synthesized that is optimal with respect to the design specifications. As part of this work, we exemplify this paradigm on a variety of diverse applications. Copyright © 2019, The Authors. All rights reserved.

关键词： Microstructure

来源：评论

学校读者我要写书评

暂无评论

Augmentation of wastewater-based epidemiology with machine learning to support global health surveillance

Nature Water

引用

Nature Water 2025年 1-11页

作者： Aßmann, Eva Greiner, Timo Richard, Hugues Wade, Matthew Agrawal, Shelesh Amman, Fabian Böttcher, Sindy Lackner, Susanne Landthaler, Markus Mangul, Serghei Munteanu, Viorel Psomopoulos, Fotis Smith, Maureen Trofimova, Maria Ullrich, Alexander von Kleist, Max Wyler, Emanuel Hölzer, Martin Irrgang, Christopher Centre for Artificial Intelligence in Public Health Research (ZKI-PH) Robert Koch Institute Berlin Germany Genome Competence Center (MF1) Robert Koch Institute Berlin Germany Department of Infectious Disease Epidemiology Robert Koch Institute Berlin Germany Chief Data Officer Group UK Health Security Agency London United Kingdom Chair of Water and Environmental Biotechnology Institute IWAR Department of Civil and Environmental Engineering Sciences Technical University of Darmstadt Darmstadt Germany CeMM Research Center for Molecular Medicine of the Austrian Academy of Sciences Vienna Austria Institute for Hygiene and Applied Immunology Medical University of Vienna Vienna Austria Gastroenteritis and Hepatitis Pathogens and Enteroviruses (FG15) Robert Koch Institute Berlin Germany Berlin Institute for Medical Systems Biology Max Delbrück Center for Molecular Medicine in the Helmholtz Association (MDC) Berlin Germany Institute for Biology Humboldt-Universität zu Berlin Berlin Germany Titus Family Department of Clinical Pharmacy USC Alfred E. Mann School of Pharmacy and Pharmaceutical Sciences University of Southern California Los Angeles CA United States Department of Biological and Morphofunctional Sciences College of Medicine and Biological Sciences Stefan cel Mare University of Suceava Suceava Romania Department of Computers Informatics and Microelectronics Technical University of Moldova Chisinau Moldova Institute of Applied Biosciences Center for Research and Technology Hellas Thessaloniki Greece Systems Medicine of Infectious Disease (P5) Robert Koch Institute Berlin Germany Department of Mathematics and Computer Science Freie Universität Berlin Berlin Germany

Wastewater-based epidemiology (WBE) has proven to be a valuable tool for monitoring the evolution and spread of global health threats, from pathogens to antimicrobial resistances. Throughout the COVID-19 pandemic, multiple wastewater surveillance programmes have advanced statistical and machine learning methods for detecting pathogens from wastewater sequencing data and correlating measured targets with the represented population to infer meaningful conclusions for public health. Integrating contextual data can account for measurement uncertainties across the WBE workflow that affect the reliability of analyses. However, the broader availability and harmonization of data are major obstacles to method development. Here we review the benefits and limitations of wastewater-related data streams, highlighting the potential of machine learning to leverage these streams for normalization and other WBE applications. We emphasize the relevance of developing global frameworks for integrating WBE with other health surveillance systems and discuss next steps to address current and foreseeable challenges for robust and interpretable machine learning-enhanced WBE. © Springer Nature Limited 2025.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AutoInt: Automatic feature interaction learning via self-Attentive neural networks

arXiv

引用

arXiv 2018年

作者： Song, Weiping Shi, Chence Xiao, Zhiping Duan, Zhijian Xu, Yewen Zhang, Ming Tang, Jian Department of Computer Science School of Eecs Peking University Department of Computer Science University of California Los Angeles United States Mila-Quebec Ai Institute Hec Montreal and Cifar Ai Chair

Click-Through rate (CTR) prediction, which aims to predict the probability of a user clicking on an ad or an item, is critical to many online applications such as online advertising and recommender systems. The problem is very challenging since (1) the input features (e.g., the user id, user age, item id, item category) are usually sparse and high-dimensional, and (2) an effective prediction relies on highorder combinatorial features (a.k.a. cross features), which are very time-consuming to hand-craft by domain experts and are impossible to be enumerated. Therefore, there have been efforts in finding lowdimensional representations of the sparse and high-dimensional raw features and their meaningful combinations. In this paper, we propose an effective and efficient method called the AutoInt to automatically learn the high-order feature interactions of input features. Our proposed algorithm is very general, which can be applied to both numerical and categorical input features. Specifically, we map both the numerical and categorical features into the same low-dimensional space. Afterwards, a multihead self-Attentive neural network with residual connections is proposed to explicitly model the feature interactions in the lowdimensional space. With different layers of the multi-head selfattentive neural networks, different orders of feature combinations of input features can be modeled. The whole model can be efficiently fit on large-scale raw data in an end-To-end fashion. Experimental results on four real-world datasets show that our proposed approach not only outperforms existing state-of-The-Art approaches for prediction but also offers good explainability. Copyright © 2018, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Prediction of Potential Disease-Associated MicroRNAs Based on Hidden Conditional Random Field

引用

Journal of Harbin institute of Technology(New Series) 2018年第1期25卷 57-66页

作者： Maozu Guo Shuang Cheng Chunyu Wang Xiaoyan Liu Yang Liu School of Computer Science and Technology Harbin Institute of Technology Harbin 150001 China School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture Beijing 100044 China Beijing Key Laboratory for Research on Intelligent Processing Method of Building Big Data( Beijing University of Civil Engineering and Architecture) Beijing 100044China Institute of Materials China Academy of Engineering PhysicsMianyang 621700SichuanChina

MicroRNAs( miRNAs) are reported to be associated with various diseases. The identification of disease-related miRNAs would be beneficial to the disease diagnosis and prognosis. However,in contrast with the widely available expression profiling, the limited knowledge of molecular function restrict the development of previous methods based on network similarity measure. To construct reliable training data,the decision fusion method is used to prioritize the results of existing methods. After that,the performance of decision fusion method is validated. Furthermore,in consideration of the long range dependencies of successive expression values,Hidden Conditional Random Field model( HCRF) is selected and applied to miRNA expression profiling to infer disease-associated miRNAs. The results show that HCRF achieves superior performance and outperforms the previous methods. The results also demonstrate the power of using expression profiling for discovering disease-associated miRNAs.

关键词： expression profiling hidden conditional random field miRNA-disease association network

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：