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

引用

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

来源：评论

学校读者我要写书评

暂无评论

On Biased Compression for Distributed Learning

arXiv

引用

arXiv 2020年

作者： Beznosikov, Aleksandr Horváth, Samuel Richtárik, Peter Safaryan, Mher Computer Electrical and Math. Sciences and Engineering Division King Abdullah University of Science and Technology Thuwal23955 Saudi Arabia Skolkovo Institute of Science and Technology Moscow121205 Russia School of Applied Mathematics and Informatics Moscow Institute of Physics and Technology Moscow141701 Russia

In the last few years, various communication compression techniques have emerged as an indispensable tool helping to alleviate the communication bottleneck in distributed learning. However, despite the fact biased compressors often show superior performance in practice when compared to the much more studied and understood unbiased compressors, very little is known about them. In this work we study three classes of biased compression operators, two of which are new, and their performance when applied to (stochastic) gradient descent and distributed (stochastic) gradient descent. We show for the first time that biased compressors can lead to linear convergence rates both in the single node and distributed settings. We prove that distributed compressed SGD method, employed with error feedback mechanism, enjoys the ergodic rate O ( δLexp[−µKδL ] + (CKµ+δD) ) , where δ ≥ 1 is a compression parameter which grows when more compression is applied, L and µ are the smoothness and strong convexity constants, C captures stochastic gradient noise (C = 0 if full gradients are computed on each node) and D captures the variance of the gradients at the optimum (D = 0 for over-parameterized models). Further, via a theoretical study of several synthetic and empirical distributions of communicated gradients, we shed light on why and by how much biased compressors outperform their unbiased variants. Finally, we propose several new biased compressors with promising theoretical guarantees and practical performance. Copyright © 2020, The Authors. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Scheduling algorithms in cellular MIMO systems

Scheduling algorithms in cellular MIMO systems

引用

Engineering and Telecommunication (En&T), International Conference

作者： Alexey Chernov Vladislav Matyukhin Maksim Zherebyatew Artem Teleluhin Yaroslav Bogdanov Julia Chernova MIPT-School of Applied Mathematics and Computer Science Moscow Institute of Physics and TechnologyMoscowRussian Federation MAOU Lyceum № 14 named. Honored Teacher of the Russian Federation A.M. Kuzmina Tambow Russian Federation Gymnasium 69 named after Sergei Yesenin Lipetsk Russian Federation Faculty of Mechanics and Mathematics Moscow State University Moscow Russian Federation

ISBN: (纸本)9781728183916

In this work, we study the resource allocation problem for downlink in 5G New Radio (NR) mobile networks in the case of orthogonal frequency-division multiple access (OFDMA). One of the key features of 5G mobile networks is the usage of antenna arrays that allows them to form beams in a specific direction and send data to several users at the same transmission time interval (TTI) via the same carrier or resource block (RB). Antenna arrays usually contain up to 64 single antennas. We have been modeled the process of the data transmission from the cell to the user device or user equipment (UE), have been formulated mathematical abstraction of the resource allocation problem, and have been proposed a lightweight algorithm that uses a proportional fair metric.

关键词： Measurement OFDM Transmitting antennas Clustering algorithms Search problems Resource management Arrays

来源：评论

学校读者我要写书评

暂无评论

A Bayesian framework for power system components identification

arXiv

引用

arXiv 2020年

作者： Mikhalev, Artem Emchinov, Alexander Chevalier, Samuel Maximov, Yury Vorobev, Petr School of Applied Mathematics and Informatics Moscow Institute of Physics and Technology Department of Mechanical Engineering Massachusetts Institute of Technology Center for Nonlinear Studies and Theoretical Division Los Alamos National Laboratory Center for Energy Science and Technology Skolkovo Institute of Science and Technology

Having actual models for power system components (such as generators and loads or auxiliary equipment) is vital to correctly assess the power system operating state and to establish stability margins. However, power system operators often have limited information about the actual values for power system component parameters. Even when a model is available, its operating parameters and control settings are time-dependent and subject to real-time identification. Ideally, these parameters should be identified from measurement data, such as phasor measurement unit (PMU) signals. However, it is challenging to do this from the ambient measurements in the absence of transient dynamics since the signal-to-noise ratio (SNR) for such signals is not necessarily large. In this paper, we design a Bayesian framework for on-line identification of power system component parameters based on ambient PMU data, which has reliable performance for SNR as low as five and for certain parameters can give good estimations even for unit SNR. We support the framework with a robust and time-efficient numerical method. We illustrate the approach efficiency on a synchronous generator example. Copyright © 2020, The Authors. All rights reserved.

关键词： Parameter estimation

来源：评论

学校读者我要写书评

暂无评论

RECOMED: A Comprehensive Pharmaceutical Recommendation System

arXiv

引用

arXiv 2022年

作者： Zomorodi, Mariam Ghodsollahee, Ismail Martin, Jennifer H. Talley, Nicholas J. Salari, Vahid Plawiak, Pawel Rahimi, Kazem Acharya, U. Rajendra Department of Computer Science Faculty of Computer Science and Telecommunications Cracow University of Technology Krakow Poland Department of Computer Engineering Ferdowsi University of Mashhad Iran The University of Newcastle CallaghanNSW Australia Institute for Quantum Science and Technology Department of Physics and Astronomy University of Calgary Alberta Canada Institute of Theoretical and Applied Informatics Polish Academy of Sciences Gliwice Poland Deep Medicine Nuffield Department of Women’s and Reproductive Health University of Oxford Oxford United Kingdom School of Mathematics Physics and Computing University of Southern Queensland ToowoombaQLD Australia

OBJECTIVES: To build datasets containing useful information from drug databases and recommend a list of drugs to physicians and patients with high accuracy by considering features of a spectrum of people, diseases, and chemicals. METHODS: A comprehensive pharmaceutical recommendation system was designed based on the features of a spectrum of people, diseases, and medicines extracted from two major drug databases, a dataset of patients and drug information. Then the recommendation was given, and the response was analysed using patient and caregiver ratings and the knowledge obtained from drug specifications and interactions. Sentiment analysis was employed by natural language processing approaches in pre-processing, along with neural network-based methods and recommender system algorithms for modelling the system. Patient conditions and medicine features were used for making two models based on matrix factorisation. Then we used drug interaction criteria to filter drugs with severe or mild interactions with other drugs. We developed a deep learning model for recommending drugs by using data from 2304 patients as a training set, and then we used data from 660 patients as our validation set. We used knowledge from critical drug information and combined the model’s outcome into a knowledge-based system with the rules obtained from constraints on taking medicine. RESULTS: The results show that our recommendation system can recommend an acceptable combination of medicines according to the existing real-life prescriptions available. Compared with conventional matrix factorisation, our proposed model improves the accuracy, sensitivity, and hit rate by 26%, 34%, and 40%, respectively. In addition, it improves the accuracy, sensitivity, and hit rate by an average of 31%, 29%, and 28% compared to other machine learning methods. We have open-sourced our implementation in Python. CONCLUSION: Compared to conventional machine learning approaches, we obtained average accuracy, sens

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Experimental researches and testing of silica twisted six-GeO2-doped core microstructured optical fiber. Part I: fusion splicing with telecommunication optical fibers and differential mode delay map measurements

Experimental researches and testing of silica twisted six-Ge...

引用

Optical Technologies for Telecommunications 2022

作者： Bourdine, Anton V. Dashkov, Michael V. Evtushenko, Alexander S. Pchelkin, Grigori A. Sachuk, Konstantin P. Khadjaev, Mukhammadzoir S. Vasilets, Alexander A. Zaitseva, Elena S. Barashkin, Alexey Yu. Demidov, Vladimir V. Ter-Nersesyants, Egishe V. Dmitriev, Eugeniy V. Shishova, Nadezhda A. Semenov, Andrey B. Tiwari, Manish Bylina, Maria S. Glagolev, Sergey F. Polyakova, Elena V. Dukelskii, Konstantin V. Dept. of Communications Lines Povolzhskiy State University of Telecommunications and Informatics 77 Moscow av. Samara443090 Russia JSC "Scientific Production Association State Optical Institute Named after Vavilov S.I." 36/1 Babushkin str. St. Petersburg192171 Russia OptoFiber Lab" LLC Skolkovo Innovation Center 7 Nobel str. Moscow143026 Russia Dept. of Photonics and Communication Lines Saint Petersburg State University of Telecommunications named after M.A. Bonch-Bruevich 22 Bolshevikov av. St. Petersburg193232 Russia Dept. of Telecommunication Engineering Samarkand branch of Tashkent University of Information Technology named after Mukhammad al-Khwarizmi 2A Ibn Sino str. Samarkand140100 Uzbekistan Department of Physics and Mathematics Branches of Science and Information Technologies Volga Region State University of Physical Culture Sport and Tourism 35 Universiade Village Kazan420010 Russia Samara Branch Radio Research & Development Institute 217 Sovetskaya Armiya str. Samara443011 Russia Dept. of Multichannel Telecommunication Systems Moscow Technical University of Communications and Informatics 8a Aviamotornaya str. Moscow111024 Russia Dept. of Mechanization and Automation of Civil Engineering National Research University Moscow State University of Civil Engineering" 26 Yaroslavskoye av. Moscow129337 Russia Optoelectronics and Photonics Research Lab Department of Electronics and Communication Engineering Manipal University Jaipur303007 India Faculty of Photonics and Optical Information School of Photonics ITMO University bldg. A 49 Kronverksky alley St. Petersburg197101 Russia

ISBN: (纸本)9781510667150

This work presents results of test series, performed for earlier on designed and successfully fabricated silica few-mode microstructured optical fibers (MOF) with six GeO2-doped cores, induced twisting 100 revolutions per meter, typical "telecommunication" outer diameter 125 µm, core diameter 8.7 µm, air hole diameter 4.6 µm, pitch 7.2 µm, and core quasi-step / graded refractive index profiles with height 0.0360 / 0.0275, respectively. Part I introduces attempts for splicing of typical telecommunication optical fibers and fabricated samples of MOFs by commercially available field arc fusion splicer kits and results of differential mode delay map measurements, performed for laser excited large core (multimode) optical fibers with core diameters 50 and 100 µm, jointed via free space to described above 2 m long pilot samples of 6-GeO2-core MOFs at both receiving and transmitting ends under laser-excited gaussian optical pulse launching with precision offset conditions, while Part II is concerned with researches of spectral responses, measured for fiber Bragg gratings, recorded in these MOFs. © 2023 SPIE.

关键词： Silica

来源：评论

学校读者我要写书评

暂无评论

JUNO sensitivity on proton decay p→νK^(+)searches

引用

Chinese physics C 2023年第11期47卷 7-22页

作者： Angel Abusleme Thomas Adam Shakeel Ahmad Rizwan Ahmed Sebastiano Aiello Muhammad Akram 安丰鹏安琪 Giuseppe Andronico Nikolay Anfimov Vito Antonelli Tatiana Antoshkina Burin Asavapibhop João Pedro Athayde Marcondes de André Didier Auguste Nikita Balashov Wander Baldini Andrea Barresi Davide Basilico Eric Baussan Marco Bellato Antonio Bergnoli Thilo Birkenfeld Sylvie Blin David Blum Simon Blyth Anastasia Bolshakova Mathieu Bongrand Clément Bordereau Dominique Breton Augusto Brigatti Riccardo Brugnera Riccardo Bruno Antonio Budano Mario Buscemi Jose Busto Ilya Butorov Anatael Cabrera Barbara Caccianiga 蔡浩蔡啸蔡严克蔡志岩 Riccardo Callegari Antonio Cammi Agustin Campeny 曹传亚曹国富曹俊 Rossella Caruso Cédric Cerna 常劲帆 Yun Chang 陈平平 Po-An Chen 陈少敏陈旭荣 Yi-Wen Chen 陈义学陈羽陈长程捷程雅苹 Alexey Chetverikov Davide Chiesa Pietro Chimenti Artem Chukanov Gérard Claverie Catia Clementi Barbara Clerbaux Selma Conforti Di Lorenzo Daniele Corti Flavio Dal Corso Olivia Dalager Christophe De La Taille 邓智邓子艳 Wilfried Depnering Marco Diaz Xuefeng Ding 丁雅韵 Bayu Dirgantara Sergey Dmitrievsky Tadeas Dohnal Dmitry Dolzhikov Georgy Donchenko 董建蒙 Evgeny Doroshkevich Marcos Dracos Frédéric Druillole 杜然杜书先 Stefano Dusini Martin Dvorak Timo Enqvist Heike Enzmann Andrea Fabbri Ulrike Fahrendholz 范东华樊磊方建方文兴 Marco Fargetta Dmitry Fedoseev Li-Cheng Feng 冯启春 Richard Ford Amélie Fournier 甘浩男 Feng Gao Alberto Garfagnini Arsenii Gavrikov Marco Giammarchi Agnese Giaz Nunzio Giudice Maxim Gonchar 龚光华宫辉 Yuri Gornushkin Alexandre Göttel Marco Grassi Christian Grewing Vasily Gromov 顾旻皓谷肖飞古宇关梦云 Nunzio Guardone Maria Gul 郭聪郭竞渊郭万磊郭新恒郭宇航 Paul Hackspacher Caren Hagner 韩然 Yang Han Muhammad Sohaib Hassan 何苗何伟 Tobias Heinz Patrick Hellmuth 衡月昆 Rafael Herrera 贺远强侯少静 Yee Hsiung Bei-Zhen Hu 胡航胡健润胡俊胡守扬胡涛胡宇翔胡焯钧黄春豪黄桂鸿黄翰雄黄文昊黄鑫黄性涛黄永波惠加琪霍雷霍文驹 Cédric Huss Safeer Hussain Ara Ioannisian Roberto Isocrate Beatrice Jelmini Kuo-Lun Jen Ignacio Jeria 季筱璐吉星曌贾慧慧贾俊基蹇司玉蒋荻蒋炜江晓山金如意荆小平 Cécile Jollet Jari Joutsenvaara Sirichok Jungthawan Leonidas Kalousis Philipp Ka Pontificia Universidad Católica de Chile SantiagoChile IPHC Universitéde StrasbourgCNRS/IN2P3F-67037 StrasbourgFrance Pakistan Institute of Nuclear Science and Technology IslamabadPakistan INFN Catania and Dipartimento di Fisica e Astronomia dell Universitàdi Catania CataniaItaly East China University of Science and Technology ShanghaiChina University of Science and Technology of China HefeiChina Joint Institute for Nuclear Research DubnaRussia INFN Sezione di Milano and Dipartimento di Fisica dell Universitàdi Milano MilanoItaly Department of Physics Faculty of ScienceChulalongkorn UniversityBangkokThailand IJCLab UniversitéParis-SaclayCNRS/IN2P391405 OrsayFrance Department of Physics and Earth Science University of Ferrara and INFN Sezione di FerraraFerraraItaly INFN Milano Bicocca and University of Milano Bicocca MilanoItaly INFN Sezione di Padova PadovaItaly III.Physikalisches Institut B RWTH Aachen UniversityAachenGermany Eberhard Karls Universität Tübingen Physikalisches InstitutTübingenGermany Institute of High Energy Physics BeijingChina SUBATECH Universitéde NantesIMT AtlantiqueCNRS-IN2P3NantesFrance Univ.Bordeaux CNRSLP2IUMR 5797F-33170 GradignanFrance Department of Physics National Taiwan UniversityTaipei Dipartimento di Fisica e Astronomia dell’Universitàdi Padova and INFN Sezione di Padova PadovaItaly University of Roma Tre and INFN Sezione Roma Tre RomaItaly Aix Marseille Univ CNRS/IN2P3CPPMMarseilleFrance Wuhan University WuhanChina INFN Milano Bicocca and Politecnico of Milano MilanoItaly National United University Miao-Li Dongguan University of Technology DongguanChina Tsinghua University BeijingChina Institute of Modern Physics Chinese Academy of SciencesLanzhouChina Institute of Physics National Yang Ming Chiao Tung UniversityHsinchu North China Electric Power University BeijingChina Sun Yat-Sen University GuangzhouChina Beijing Institute of Spacecraft Environment Engineering BeijingChina Universidade Estadual de Londrina LondrinaBrazil INFN Sez

The Jiangmen Underground Neutrino Observatory(JUNO)is a large liquid scintillator detector designed to explore many topics in fundamental *** this study,the potential of searching for proton decay in the p→νK^(+)mode with JUNO is *** kaon and its decay particles feature a clear three-fold coincidence signature that results in a high efficiency for ***,the excellent energy resolution of JUNO permits suppression of the sizable background caused by other delayed *** on these advantages,the detection efficiency for the proton decay via p→νK^(+)is 36.9%±4.9%with a background level of 0.2±0.05(syst)±0.2(stat)events after 10 years of data *** estimated sensitivity based on 200 kton-years of exposure is 9.6×1033 years,which is competitive with the current best limits on the proton lifetime in this channel and complements the use of different detection technologies.

关键词： proton decay grand unified theories JUNO liquid scintillator detector

来源：评论

学校读者我要写书评

暂无评论

Science with the Global Cosmic-ray Observatory (GCOS) 38

Science with the Global Cosmic-ray Observatory (GCOS)

引用

38th International Cosmic Ray Conference, ICRC 2023

作者： Batista, Rafael Alves Ahlers, M. Alves Batista, R. Assis, P. Battisti, M. Bellido, J.A. Bhatnagar, S. Bismark, K. Bister, T. Bohacova, M. Caccianiga, L. Caruso, R. Carvalho, W. Castellina, A. Colalillo, R. Convenga, F. Dawson, B. De Mitri, I. de Palma, F. Deval, L. di Matteo, A. DuVernois, M. Engel, R. Eser, J. Fitoussi, T. Flaggs, B. Fujii, T. Garzelli, M.V. Gkika, V. Hamal, P. Hariharan, B. Haungs, A. Hnatyk, B. Hörandel, J. Horváth, P. Hrabovsky, M. Huege, T. Ikeda, D. Isar, P.G. James, R. Johnsen, J. Kampert, K.-H. Kleifges, M. Koundal, P. Liu, J. Longo, F. Mandat, D. Mariş, I.C. Matthews, J. Mayotte, E. Medina-Tanco, G. Mulrey, K. Muzio, M.S. Nellen, L. Niechciol, M. Ogio, S. Oikonomou, F. Ostrowski, M. Pont, B. Porcelli, A. Rautenberg, J. Rieger, F. Risse, M. Roth, M. Sako, T. Salamida, F. Santangelo, A. Santos, E. Sarazin, F. Saveliev, A. Schimp, M. Schmidt, D. Schröder, F. Sergijenko, O. Sigl, G. Soldin, D. Spiczak, G. Tameda, Y. Unger, M. van Vliet, A. Vorobiov, S. Wibig, T. Wundheiler, B. Yushkov, A. Zotov, M. Instituto de Física Teórica UAM-CSIC C Nicolás Cabrera 13-15 Madrid28049 Spain Departamento de Física Teórica Universidad Autónoma de Madrid M-15 Madrid28049 Spain Niels Bohr Institute Copenhagen Denmark Instituto de Física Teórica UAM-CSIC Madrid Spain Universidad Autónoma de Madrid Departamento de Física Teórica Madrid Spain Universidade de Lisboa Instituto Superior Técnico Lisboa Portugal Universidade de Lisboa Laboratório de Instrumentação e Física Experimental de Partículas Lisboa Portugal Université de Paris Astroparticule et Cosmologie Paris France The University of Adelaide Physics Department Adelaide Australia Dayalbagh Educational Institute Department of Physics and Computer Science Agra India Institute for Experimental Particle Physics Karlsruhe Germany Radboud University Institute for Mathematics Astrophysics and Particle Physics Nijmegen Netherlands Amsterdam Netherlands Institute of Physics The Czech Academy of Sciences Prague Czech Republic Sezione di Milano Milan Italy Department of Physics and Astronomy "E. Majorana" University of Catania Catania Italy Sezione di Catania Catania Italy Sezione di Torino Turin Italy Turin Italy Università degli Studi di Napoli "Federico II" Naples Italy Sezione di Napoli Naples Italy Università dell’Aquila Dipartimento di Scienze Fisiche e Chimiche L’Aquila Italy Laboratori Nazionali del Gran Sasso L’Aquila Assergi Italy Gran Sasso Science Institute L’Aquila Italy Università del Salento Dipartimento di Matematica e Fisica "E. De Giorgi" Lecce Italy Institute for Astroparticle Physics Karlsruhe Germany University of Wisconsin-Madison Department of Physics MadisonWI United States University of Wisconsin-Madison Wisconsin IceCube Particle Astrophysics Center MadisonWI United States The University of Chicago Department of Astronomy and Astrophysics ChicagoIL United States University of Delaware Bartol Research Institute NewarkDE United States Osaka Metropolitan Univers

The Global Cosmic-ray Observatory (GCOS) is a proposed large-scale observatory for studying ultra-high-energy cosmic particles, including ultra-high-energy cosmic rays (UHECRs), photons, and neutrinos. Its primary goal is to characterise the properties of the highest-energy particles in Nature with unprecedented accuracy, and to identify their elusive sources. With an aperture at least a ten-fold larger than existing observatories, this next-generation facility should start operating after 2030, when present-day detectors will gradually cease their activities. Here we briefly review the scientific case motivating GCOS. We present the status of the project, preliminary ideas for its design, and some estimates of its capabilities. © Copyright owned by the author(s) under the terms of the Creative Commons.

关键词： Cosmic rays

来源：评论

学校读者我要写书评

暂无评论

NUMERICAL SIMULATION OF PHOTOSPHERIC EMISSION IN LONG GAMMA-RAY BURSTS: PROMPT CORRELATIONS, SPECTRAL SHAPES, AND POLARIZATIONS

arXiv

引用

arXiv 2023年

作者： Ito, Hirotaka Matsumoto, Jin Nagataki, Shigehiro Warren, Donald C. Barkov, Maxim V. Yonetoku, Daisuke Cluster for Pioneering Research RIKEN Saitama351-0198 Japan RIKEN Saitama351-0198 Japan Keio Institute of Pure and Applied Sciences Keio University Yokohama223-8522 Japan RIKEN Saitama351-0198 Japan 1919-1 Tancha Onna-son Kunigami-gun Okinawa904-0495 Japan Florida Institute of Technology 150 W. University Blvd MelbourneFL32901 United States Institute of Astronomy Russian Academy of Sciences Moscow119017 Russia Space Research Institute Russian Academy of Sciences Moscow117997 Russia College of Science and Engineering School of Mathematics and Physics Kanazawa University Kakuma Ishikawa Kanazawa920-1192 Japan

We explore the properties of photospheric emission in the context of long gamma-ray bursts (LGRBs) using three numerical models that combine relativistic hydrodynamical simulations and Monte Carlo radiation transfer calculations in three dimensions. Our simulations confirm that the photospheric emission gives rise to correlations between the spectral peak energy and luminosity that agree with the observed Yonetoku, Amati, and Golenetskii correlations. It is also shown that the spectral peak energy and luminosity correlate with the bulk Lorentz factor, as indicated in the literature. On the other hand, synthetic spectral shapes tend to be narrower than those of the observations. The result indicates that an additional physical process that can provide non-thermal broadening is needed to reproduce the spectral features. Furthermore, the polarization analysis finds that, while the degree of polarization is low for the emission from the jet core (Π ◦), which may be compatible with those inferred in observations. A notable energy dependence of the polarization property is another characteristic feature found in the current study. Particularly, the difference in the position angle among different energy bands can be as large as ∼ 90◦ Copyright © 2023, The Authors. All rights reserved.

关键词： Luminance

来源：评论

学校读者我要写书评

暂无评论

Enhancing Global Sensitivity and Uncertainty Quantification in Medical Image Reconstruction with Monte Carlo Arbitrary-Masked Mamba

arXiv

引用

arXiv 2024年

作者： Huang, Jiahao Yang, Liutao Wang, Fanwen Nan, Yang Wu, Weiwen Wang, Chengyan Shi, Kuangyu Aviles-Rivero, Angelica I. Schönlieb, Carola-Bibiane Zhang, Daoqiang Yang, Guang Department of Bioengineering and Imperial-X Imperial College London London United Kingdom National Heart and Lung Institute Imperial College London London United Kingdom Cardiovascular Research Centre Royal Brompton Hospital London United Kingdom College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China School of Biomedical Engineering Shenzhen Campus of Sun Yat-sen University Guangdong China Human Phenome Institute Fudan University Shanghai China Department of Nuclear Medicine Inselspital University of Bern Bern Switzerland Department of Informatics Technical University of Munich Munich Germany Department of Applied Mathematics and Theoretical Physics University of Cambridge Cambridge United Kingdom

Deep learning has been extensively applied in medical image reconstruction, where Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) represent the predominant paradigms, each possessing distinct advantages and inherent limitations: CNNs exhibit linear complexity with local sensitivity, whereas ViTs demonstrate quadratic complexity with global sensitivity. The emerging Mamba has shown superiority in learning visual representation, which combines the advantages of linear scalability and global sensitivity. In this study, we introduce MambaMIR, an Arbitrary-Masked Mamba-based model with wavelet decomposition for joint medical image reconstruction and uncertainty estimation. A novel Arbitrary Scan Masking (ASM) mechanism "masks out" redundant information to introduce randomness for further uncertainty estimation. Compared to the commonly used Monte Carlo (MC) dropout, our proposed MC-ASM provides an uncertainty map without the need for hyperparameter tuning and mitigates the performance drop typically observed when applying dropout to low-level tasks. For further texture preservation and better perceptual quality, we employ the wavelet transformation into MambaMIR and explore its variant based on the Generative Adversarial Network, namely MambaMIR-GAN. Comprehensive experiments have been conducted for multiple representative medical image reconstruction tasks, demonstrating that the proposed MambaMIR and MambaMIR-GAN outperform other baseline and state-of-the-art methods in different reconstruction tasks, where MambaMIR achieves the best reconstruction fidelity and MambaMIR-GAN has the best perceptual quality. In addition, our MC-ASM provides uncertainty maps as an additional tool for clinicians, while mitigating the typical performance drop caused by the commonly used dropout. Copyright © 2024, The Authors. All rights reserved.

关键词： Generative adversarial networks

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：