检索结果-内蒙古大学图书馆

Application of Kronecker convolutions in deep learning technique for automated detection of kidney stones with coronal CT images

学校读者我要写书评

暂无评论

Information sciences 2023年 640卷

作者： Patro, Kiran Kumar Allam, Jaya Prakash Neelapu, Bala Chakravarthy Tadeusiewicz, Ryszard Acharya, U Rajendra Hammad, Mohamed Yildirim, Ozal Plawiak, Pawel Department of Electronics and Communication Engineering Aditya Institute of Technology and Management AP Tekkali532201 India Department of Electronics and Communication Engineering National Institute of Technology Rourkela Odisha Rourkela769008 India Department of Biotechnology and Medical Engineering National Institute of Technology Rourkela Odisha Rourkela769008 India AGH University of Science and Technology Department of Biocybernetics and Biomedical Engineering Krakow Poland School of Mathematics Physics and Computing University of Southern Queensland Springfield Australia EIAS Data Science Lab College of Computer and Information Sciences Prince Sultan University Riyadh11586 Saudi Arabia Department of Information Technology Faculty of Computers and Information Menoufia University Shibin El Kom32511 Egypt Department of Software Engineering Firat University Elazig Turkey Department of Computer Science Faculty of Computer Science and Telecommunications Cracow University of Technology Warszawska 24 Krakow31-155 Poland Institute of Theoretical and Applied Informatics Polish Academy of Sciences Baltycka 5 Gliwice44-100 Poland

Kidney stone disease is a serious public health concern that is getting worse with changes in diet, obesity, medical conditions, certain supplements etc. A kidney stone also called a renal calculus, is a hard buildup of urine minerals that form in the kidneys. Computed tomography (CT) is one of the imaging models used to identify kidney stones by clinical experts. Due to the low resolution of these images, sometimes detecting kidney stones is tedious with the naked eye, which may lead to false alarms. In this work, a computer-based diagnosis system with a deep learning technique has been developed as a practical solution to aid clinicians in their diagnosis. The traditional convolutional neural network (CNN)-based deep learning technology can detect stones in the kidney. Still, it suffers from the performance and standard implementation of the convolution operations in convolution layers. A Kronecker product-based convolution technique is incorporated in the proposed deep learning architecture to reduce the redundancy in feature maps without convolution overlapping. Our proposed method helps to make the network more effective by extracting abstract and in-depth features from the input images. The publicly available GitHub kidney stone CT scans are utilized to develop the proposed architecture. Our automated model detected kidney stones with an accuracy of 98.56% utilizing CT images. Our system is more effective than the most recent and cutting-edge techniques developed for identifying kidney stones of any size, including the smallest ones. © 2023 The Author(s)

关键词： Convolution

Erratum to:Influence of structural defects on charge density waves in 1T-TaS_(2)

学校读者我要写书评

暂无评论

Nano Research 2024年第3期17卷 2204-2204页

作者： Iaroslav Lutsyk Karol Szalowski Pawel Krukowski Pawel Dabrowski Maciej Rogala Witold Kozlowski Maxime Le Ster Michal Piskorski Dorota A.Kowalczyk Wojciech Rys Rafal Dunal Aleksandra Nadolska Klaudia Toczek Przemyslaw Przybysz Ewa Lacinska Johannes Binder Andrzej Wysmolek Natalia Olszowska Jacek J.Kolodziej Martin Gmitra Takuma Hattori Yuji Kuwahara Guang Bian Tai-Chang Chiang Pawel J.Kowalczyk Faculty of Physics and Applied Informatics University of LodzPomorska 149/15390-236 LodzPoland Faculty of Physics University of WarsawPasteura 502-093 WarsawPoland Faculty of Physics Astronomyand Applied Computer ScienceJagiellonian UniversityLojasiewicza 1130-348 KrakowPoland National Synchrotron Radiation Centre SOLARIS Jagiellonian UniversityCzerwone Maki 9830-392 KrakówPoland Institute of Physics Faculty of SciencePavol JozefŠafárik University in KošicePark Angelinum 904001 KošiceSlovakia Institute of Experimental Physics Slovak Academy of SciencesWatsonova 4704001 KošiceSlovakia Department of Precision Engineering Graduate School of EngineeringOsaka University2-1 Yamada-okaSuita 565-0871Japan Department of Physics and Astronomy University of MissouriColumbiaMissouri 65211USA Department of Physics and Frederick Seitz Materials Research Laboratory University of Illinois at Urbana-ChampaignUrbanaIllinois 61801-3080USA

The name of the second author in original paper was unfortunately *** should be“Karol Szalowski”,instead of“Karoli Szalowski”.

关键词： structural charge defects

Two instances of random access code in the quantum regime

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Sakharwade, Nitica Studziński, Michal Eckstein, Michal Horodecki, Pawel International Centre for Theory of Quantum Technologies University of Gdańsk Jana Bażyńskiego 1A Gdańsk80-309 Poland Perimeter Institute for Theoretical Physics Waterloo Canada Department of Physics and Astronomy University of Waterloo Waterloo Canada Institute of Theoretical Physics and Astrophysics National Quantum Information Centre in Gdańsk Faculty of Mathematics Physics and Informatics University of Gdańsk Wita Stwosza 57 Gdańsk80-952 Poland Institute of Theoretical Physics Faculty of Physics Astronomy and Applied Computer Science Jagiellonian University ul. Lojasiewicza 11 Kraków30-348 Poland Faculty of Applied Physics and Mathematics National Quantum Information Centre Gdansk University of Technology Gabriela Narutowicza 11/12 Gdańsk80-233 Poland

We consider two classes of quantum generalisations of Random Access Code (RAC) and study the bounds for probabilities of success for such tasksa. It provides a useful framework for the study of certain information processing tasks with constrained resources. The first class is based on a random access code with quantum inputs and output known as the No-Signalling Quantum RAC (NS-QRAC) box [A. Grudka et al., Phys. Rev. A 92, 052312 (2015)], where unbounded entanglement and constrained classical communication are allowed. We show that it can be seen as quantum teleportation with constrained classical communication and provide a lower quantum bound for the success probability. We consider two modifications to the NS-QRAC scenario: The first, where unbounded entanglement and constrained quantum communication is allowed and the second, where bounded entanglement and unconstrained classical communication is allowed. We find a monogamy relation for the transmission fidelities, which - in contrast to the usual communication schemes - involves multiple senders and a single receiver. We provide an upper bounds for the latter and a lower one for the former. The second class is based on a RAC with a quantum channel and shared entanglement [A. Tavakoli et al., PRX Quantum 2, 040357 (2021)]. We study the set of tasks where two inputs made of two digits of d-base are encoded over a qudit and a maximally entangled state. We show that such tasks can be seen as quantum dense-coding with constrained quantum communication and explicit protocols, which give lower quantum bounds for the tasks' efficiency, in dimensions d = 2, 3, 4. The employed encoding utilises Gray codes. Copyright © 2022, The Authors. All rights reserved.

关键词： Quantum communication

Differential cross-section measurements of the production of four charged leptons in association with two jets using the ATLAS detector

学校读者我要写书评

暂无评论

Journal of High Energy physics 2024年第1期2024卷 4页

作者： Aad, G. Abbott, B. Abeling, K. Abicht, N.J. Abidi, S.H. Aboulhorma, A. Abramowicz, H. Abreu, H. Abulaiti, Y. Abusleme Hoffman, A.C. Acharya, B.S. Adam Bourdarios, C. Adamczyk, L. Adamek, L. Addepalli, S.V. Addison, M.J. Adelman, J. Adiguzel, A. Adye, T. Affolder, A.A. Afik, Y. Agaras, M.N. Agarwala, J. Aggarwal, A. Agheorghiesei, C. Ahmad, A. Ahmadov, F. Ahmed, W.S. Ahuja, S. Ai, X. Aielli, G. Aikot, A. Ait Tamlihat, M. Aitbenchikh, B. Aizenberg, I. Akbiyik, M. Åkesson, T.P.A. Akimov, A.V. Akiyama, D. Akolkar, N.N. Al Khoury, K. Alberghi, G.L. Albert, J. Albicocco, P. Albouy, G.L. Alderweireldt, S. Aleksa, M. Aleksandrov, I.N. Alexa, C. Alexopoulos, T. Alfonsi, F. Algren, M. Alhroob, M. Ali, B. Ali, H.M.J. Ali, S. Alibocus, S.W. Aliev, M. Alimonti, G. Alkakhi, W. Allaire, C. Allbrooke, B.M.M. Allen, J.F. Allendes Flores, C.A. Allport, P.P. Aloisio, A. Alonso, F. Alpigiani, C. Alvarez Estevez, M. Alvarez Fernandez, A. Alves Cardoso, M. Alviggi, M.G. Aly, M. Amaral Coutinho, Y. Ambler, A. Amelung, C. Amerl, M. Ames, C.G. Amidei, D. Amor Dos Santos, S.P. Amos, K.R. Ananiev, V. Anastopoulos, C. Andeen, T. Anders, J.K. Andrean, S.Y. Andreazza, A. Angelidakis, S. Angerami, A. Anisenkov, A.V. Annovi, A. Antel, C. Anthony, M.T. Antipov, E. Antonelli, M. Anulli, F. Aoki, M. Aoki, T. Aparisi Pozo, J.A. Aparo, M.A. Aperio Bella, L. Appelt, C. Apyan, A. Aranzabal, N. Arcangeletti, C. Arce, A.T.H. Arena, E. Arguin, J.-F. Argyropoulos, S. Arling, J.-H. Arnaez, O. Arnold, H. Artoni, G. Asada, H. Asai, K. Asai, S. Asbah, N.A. Assahsah, J. Assamagan, K. Astalos, R. Atashi, S. Atkin, R.J. Atkinson, M. Atmani, H. Atmasiddha, P.A. Augsten, K. Auricchio, S. Auriol, A.D. Austrup, V.A. Avolio, G. Axiotis, K. Azuelos, G. Babal, D. Bachacou, H. Bachas, K. Bachiu, A. Backman, F. Badea, A. Bagnaia, P. Bahmani, M. Bailey, A.J. Bailey, V.R. Baines, J.T. Baines, L. Bakalis, C. Baker, O.K. Bakos, E. Bakshi Gupta, D. Balakrishnan, V. Balasubramanian, R. Baldin, E.M. Balek, P. Ballabene, E. Balli, F. Baltes, L.M. Balunas, W.K. Balz, J. Banas, E. Department of Physics University of Adelaide Adelaide Australia Department of Physics University of Alberta Edmonton AB Canada Department of Physics Ankara University Ankara Turkey Division of Physics TOBB University of Economics and Technology Ankara Turkey LAPP Université Savoie Mont Blanc CNRS/IN2P3 Annecy France APC Université Paris Cité CNRS/IN2P3 Paris France High Energy Physics Division Argonne National Laboratory Argonne IL United States Department of Physics University of Arizona Tucson AZ United States Department of Physics University of Texas at Arlington Arlington TX United States Physics Department National and Kapodistrian University of Athens Athens Greece Physics Department National Technical University of Athens Zografou Greece Department of Physics University of Texas at Austin Austin TX United States Institute of Physics Azerbaijan Academy of Sciences Baku Azerbaijan Institut de Física d’Altes Energies (IFAE) Barcelona Institute of Science and Technology Barcelona Spain Institute of High Energy Physics Chinese Academy of Sciences Beijing China Physics Department Tsinghua University Beijing China Department of Physics Nanjing University Nanjing China School of Science Shenzhen Campus of Sun Yat-sen University Shenzhen China University of Chinese Academy of Science (UCAS) Beijing China Institute of Physics University of Belgrade Belgrade Serbia Department for Physics and Technology University of Bergen Bergen Norway Physics Division Lawrence Berkeley National Laboratory Berkeley CA United States University of California Berkeley CA United States Institut für Physik Humboldt Universität zu Berlin Berlin Germany Albert Einstein Center for Fundamental Physics and Laboratory for High Energy Physics University of Bern Bern Switzerland School of Physics and Astronomy University of Birmingham Birmingham United Kingdom Department of Physics Bogazici University Istanbul Turkey Department of Physics Engineering Gaziant

Differential cross-sections are measured for the production of four charged leptons in association with two jets. These measurements are sensitive to final states in which the jets are produced via the strong interaction as well as to the purely-electroweak vector boson scattering process. The analysis is performed using proton-proton collision data collected by ATLAS at s = 13 TeV and with an integrated luminosity of 140 fb⁻¹. The data are corrected for the effects of detector inefficiency and resolution and are compared to state-of-the-art Monte Carlo event generator predictions. The differential cross-sections are used to search for anomalous weak-boson self-interactions that are induced by dimension-six and dimension-eight operators in Standard Model effective field theory. © The Author(s) 2024.

关键词： Hadron-Hadron Scattering

Sparse Universum quadratic surface support vector machine models for binary classification

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Moosaei, Hossein Mousavi, Ahmad Hladík, Milan Gao, Zheming Department of Mathematics Faculty of Science University of Bojnord Bojnord Iran Department of Applied Mathematics School of Computer Science Faculty of Mathematics and Physics Charles University Prague Czech Republic Institute for Mathematics and its Applications University of Minnesota MinneapolisMN55455 United States Department of Applied Mathematics Faculty of Mathematics and Physics Charles University Prague Czech Republic College of Information Science and Engineering Northeastern University ShenyangLiaoning110819 China

In binary classification, kernel-free linear or quadratic support vector machines are proposed to avoid dealing with difficulties such as finding appropriate kernel functions or tuning their hyper-parameters. Furthermore, Universum data points, which do not belong to any class, can be exploited to embed prior knowledge into the corresponding models so that the generalization performance is improved. In this paper, we design novel kernel-free Universum quadratic surface support vector machine models. Further, we propose the L1 norm regularized version that is beneficial for detecting potential sparsity patterns in the Hessian of the quadratic surface and reducing to the standard linear models if the data points are (almost) linearly separable. The proposed models are convex such that standard numerical solvers can be utilized for solving them. Nonetheless, we formulate a least squares version of the L1 norm regularized model and next, design an effective tailored algorithm that only requires solving one linear system. Several theoretical properties of these models are then reported/proved as well. We finally conduct numerical experiments on both artificial and public benchmark data sets to demonstrate the feasibility and effectiveness of the proposed models. Copyright © 2021, The Authors. All rights reserved.

关键词： Support vector machines

Design and implementation of a novel approach for long-lived particle reconstruction in LHCb experiment at CERN

学校读者我要写书评

暂无评论

computer physics Communications 2025年

作者： Piotr Kulczycki Grzegorz Gołaszewski Tomasz Szumlak Szymon Łukasik AGH University of Krakow Faculty of Physics and Applied Computer Science Division for Information Technology and Systems Research Polish Academy of Sciences Systems Research Institute Centre of Information Technology for Data Analysis Methods

The subject of this paper is the improvement of the procedure to reconstruct long-lived particles in the LHCb (Large Hadron Collider beauty) experiment, one of the main experiments conducted by the European Organization for Nuclear Research CERN in Geneva. The goal of this procedure is to detect or, in other words, reconstruct long-lived particle tracks, based on observations obtained from measurement modules placed far apart, with a primary focus of eliminating erroneously created tracks, the so-called ghost-tracks. The investigated method is carried out by pairing proper trajectories and two autonomous filtering algorithms that are based on the nonparametric estimation of a distribution density as well as an autoencoder, a neural network designated for unsupervised learning. The values obtained from these two algorithms founded on complementary methodologies, mathematical statistics and computational intelligence, are combined with the t-norm. As a result, the number of ghost-tracks is reduced threefold when compared with the method primarily used. To evaluate the results of the designed procedure, a measure of the reconstruction quality, without the information whether a given track is real or only a ghost, is additionally created and effectively applied. Illustrative interpretations make it easier to potentially employ the method elaborated here to research tasks of similar conditions.

关键词： data analysis LHCb experiment long-lived particle ghost-track elimination computational intelligence numerical algorithm

PySDM v1: Particle-based cloud modelling package for warm-rain microphysics and aqueous chemistry

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Bartman, Piotr Bulenok, Oleksii Górski, Kamil Jaruga, Anna Lazarski, Grzegorz Olesik, Michael Piasecki, Bartosz Singer, Clare E. Talar, Aleksandra Arabas, Sylwester Faculty of Mathematics and Computer Science Jagiellonian University Kraków Poland Department of Environmental Science and Engineering California Institute of Technology PasadenaCA United States Faculty of Chemistry Jagiellonian University Kraków Poland Faculty of Physics Astronomy and Applied Computer Science Jagiellonian University Kraków Poland University of Illinois at Urbana-Champaign UrbanaIL United States

PySDM is an open-source Python package for simulating the dynamics of particles undergoing condensational and collisional growth, interacting with a fluid flow and subject to chemical composition changes. It is intended to serve as a building block for process-level as well as computational-fluid-dynamics simulation systems involving representation of a continuous phase (air) and a dispersed phase (aerosol), with PySDM being responsible for representation of the dispersed phase. The PySDM package core is a Pythonic high-performance implementation of the Super-Droplet Method (SDM) Monte-Carlo algorithm for representing collisional growth, hence the name. PySDM has two alternative parallel number-crunching backends available: multi-threaded CPU backend based on Numba and GPU-resident backend built on top of ThrustRTC. The usage examples are built on top of four simple atmospheric cloud modelling frameworks: box, adiabatic parcel, single-column and 2D prescribed flow kinematic models. In addition, the package ships with tutorial code depicting how PySDM can be used from Julia and Matlab. Copyright © 2021, The Authors. All rights reserved.

关键词： Python

Machine Learning Classification of Sphalerons and Black Holes at the LHC

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Grefsrud, Aurora Singstad Buanes, Trygve Koutroulis, Fotis Lipniacka, Anna Maselek, Rafal Papaefstathiou, Andreas Sakurai, Kazuki Sjursen, Therese B. Slazyk, Igor Department of Computer Science Electrical Engineering and Mathematical Sciences Western Norway University of Applied Sciences Postbox 7030 Bergen5020 Norway Department of Physics and Technology University of Bergen Postboks 7803 BergenN-5020 Norway Institute of Theoretical Physics Faculty of Physics University of Warsaw ul. Pasteura 5 WarsawPL-02-093 Poland Department of Physics Kennesaw State University 830 Polytechnic Lane MariettaGA30060 United States Université Grenoble-Alpes CNRS IN2P3 53 Avenue des Martyrs GrenobleF-38026 France

In models with large extra dimensions, "miniature" black holes (BHs) might be produced in high-energy proton-proton collisions at the Large Hadron Collider (LHC). In the semi-classical regime, those BHs thermally decay, giving rise to large-multiplicity final states with jets and leptons. On the other hand, similar final states are also expected in the production of electroweak sphaleron/instanton-induced processes. We investigate whether one can discriminate these scenarios when BH or sphaleron-like events are observed in the LHC using machine learning (ML) methods. Classification among several BH scenarios with different numbers of extra dimensions and the minimal BH masses is also examined. In this study we consider three ML models: XGBoost algorithms with (1) high- and (2) low-level inputs, and (3) a Residual Convolutional Neural Network. In the latter case, the low-level detector information is converted into an input format of three-layer binned event images, where the value of each bin corresponds to the energy deposited in various detector subsystems. We demonstrate that only a small number of detected events are sufficient to effectively discriminate between the sphaleron and BH processes. Separation between BH scenarios with different minimal masses is possible with an order of 10 events passing the preselection. A sufficient number of events could be observed in combined Run-2 and -3 data, if the production cross section is not much smaller than the present limit ∼ 0.1 fb. We find, however, that a large number of events is needed to discriminate between BH hypotheses with the same minimal BH mass, but different numbers of extra dimensions. Copyright © 2023, The Authors. All rights reserved.

关键词： Stars

Factorial cumulants from global baryon number conservation

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Barej, Michal Bzdak, Adam AGH University of Science and Technology Faculty of Physics and Applied Computer Science Kraków30-059 Poland

The proton, antiproton and mixed proton-antiproton factorial cumulants originating from the global conservation of baryon number are calculated analytically up to the sixth order. Our results can be directly tested in... 详细信息

关键词： Hadrons