检索结果-内蒙古大学图书馆

Journal of medical Internet research 2020年第3期22卷 e18362页

作者： Deborah L Johanson Ho Seok Ahn Bruce A MacDonald Byeong Kyu Ahn JongYoon Lim Euijun Hwang Craig J Sutherland Elizabeth Broadbent Department of Psychological Medicine Faculty of Medical and Health Sciences The University of Auckland Auckland New Zealand. Centre for Automation and Robotic Engineering Science The University of Auckland Auckland New Zealand. Department of Electrical Computer and Software Engineering Faculty of Engineering The University of Auckland Auckland New Zealand.

[This corrects the article DOI: 10.2196/13667.].

关键词：

Data and Physics Driven Learning Models for Fast MRI - Fundamentals and Methodologies from CNN, GAN to Attention and Transformers

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Huang, Jiahao Fang, Yingying Nan, Yang Wu, Huanjun Wu, Yinzhe Gao, Zhifan Li, Yang Wang, Zidong Lio, Pietro Rueckert, Daniel Eldar, Yonina C. Yang, Guang The National Heart and Lung Institute Imperial College London Guy Scadding Building Dovehouse St LondonSW3 6LY United Kingdom The Department of Bioengineering Imperial College London South Kensington LondonSW7 2AZ United Kingdom The School of Biomedical Engineering Sun Yat-Sen University Guangdong Guangzhou510006 China The School of Automation Sciences and Electrical Engineering Beihang University Beijing China The Department of Computer Science Brunel University London LondonUB8 3PH United Kingdom The Computer Laboratory University of Cambridge CambridgeCB3 0FD United Kingdom The Department of Computing Imperial College London South Kensington Campus LondonSW7 2AZ United Kingdom Technical University of Munich Munich80333 Germany Faculty of Mathematics and Computer Science Weizmann Institute of Science Rehovot7610001 Israel

Research studies have shown no qualms about using data driven deep learning models for downstream tasks in medical image analysis, e.g., anatomy segmentation and lesion detection, disease diagnosis and prognosis, and treatment planning. However, deep learning models are not the sovereign remedy for medical image analysis when the upstream imaging is not being conducted properly (with artefacts). This has been manifested in MRI studies, where the scanning is typically slow, prone to motion artefacts, with a relatively low signal to noise ratio, and poor spatial and/or temporal resolution. Recent studies have witnessed substantial growth in the development of deep learning techniques for propelling fast MRI. This article aims to (1) introduce the deep learning based data driven techniques for fast MRI including convolutional neural network and generative adversarial network based methods, (2) survey the attention and transformer based models for speeding up MRI reconstruction, and (3) detail the research in coupling physics and data driven models for MRI acceleration. Finally, we will demonstrate through a few clinical applications, explain the importance of data harmonisation and explainable models for such fast MRI techniques in multicentre and multi-scanner studies, and discuss common pitfalls in current research and recommendations for future research directions. © 2022, CC BY-NC-ND.

关键词： Signal to noise ratio

Label Cluster Chains for Multi-Label Classification

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Gatto, Elaine Cecília Nakano, Felipe Kenji Read, Jesse Ferrandin, Mauri Cerri, Ricardo Vens, Celine Department of Computer Science Federal University of São Carlos SP São Carlos13565-905 Brazil Faculty of Medicine Katholieke Universiteit Leuven West Flanders Kortrijk8500 Belgium École Polytechnique Polytechnic Institute of Paris Palaiseau Paris91120 France Department of Control Automation and Computing Engineering Federal University of Santa Catarina SC Blumenau89036-002 Brazil Institute of Mathematical and Computing Sciences University of São Paulo SP São Carlos13566-590 Brazil

Multi-label classification is a type of supervised machine learning that can simultaneously assign multiple labels to an instance. To solve this task, some methods divide the original problem into several sub-problems (local approach), others learn all labels at once (global approach), and others combine several classifiers (ensemble approach). Regardless of the approach used, exploring and learning label correlations is important to improve the classifier predictions. Ensemble of Classifier Chains (ECC) is a well-known multi-label method that considers label correlations and can achieve good overall performance on several multi-label datasets and evaluation measures. However, one of the challenges when working with ECC is the high dimensionality of the label space, which can impose limitations for fully-cascaded chains as the complexity increases regarding feature space expansion. To improve classifier chains, we propose a method to chain disjoint correlated label clusters obtained by applying a partition method in the label space. During the training phase, the ground truth labels of each cluster are used as new features for all of the following clusters. During the test phase, the predicted labels of clusters are used as new features for all the following clusters. Our proposal, called Label Cluster Chains for Multi-Label Classification (LCC-ML), uses multi-label Random Forests as base classifiers in each cluster, combining their predictions to obtain a final multi-label classification. Our proposal obtained better results compared to the original ECC. This shows that learning and chaining disjoint correlated label clusters can better explore and learn label correlations. © 2024, CC BY.

关键词：

The First Competition on Resource-Limited Infrared Small Target Detection Challenge: Methods and Results

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Boyang Ying, Xinyi Li, Ruojing Liu, Yongxian Shi, Yangsi Li, Miao Zhang, Xin Hu, Mingyuan Wu, Chenyang Zhang, Yukai Wei, Hui Tang, Dongli Zhao, Jian Jin, Lei Xiao, Chao Ling, Qiang Lin, Zaiping Sheng, Weidong Peng, Chenxu Ke, Wei He, Yuhang Yang, Huoren Liu, Lingjie Liu, Ziqi Shi, Zelin Liu, Yunpeng Yu, Chuang Zhao, Jinmiao Xiang, Heng Yang, Shan Li, You Wang, Guoqing Li, Tianyu Zhou, Minghang Xie, Dongyu Lan, Chenxi Qiao, Chaofan Gao, Yupeng Liu, Yongxu Feng, Wei Ma, Zhihao Chen, Deping Song, Xiaopeng Yang, Jiuping Qiu, Zhaobing Ni, Rixiang Lin, Ye Luo, Changhai Zheng, Shuyuan Huang, Baojin Zhou, Xiaoqi Guo, Qingshan Zhang, Xuyang Li, Xiuhong Wu, Dangxuan Ma, Jian Zeng, Haodong Wang, Luyao Fu, Qiang Dai, Yimian Kou, Renke Song, Jian Feng, Changfeng Xiao, Mengxuan Xiong, Zihao Huang, Hong Liu, Yingxu Zhao, Quanyi National University of Defense Technology China China Telecom Institute of AI China Northwestern Polytechnical University China Beijing University of Posts and Telecommunications China Zhejiang Supcon Information Co. Ltd. China School of Physics Xi’an Jiaotong University China College of Artificial Intelligence Faculty of Electronic and Information Engineering Xi’an Jiaotong University China School of Software Engineering Faculty of Electronic and Information Engineering Xi’an Jiaotong University China The Key Laboratory of Opto-Electronic Information Processing Chinese Academy of Sciences Shenyang110016 China The Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China The School of Computer Science and Technology University of Chinese Academy of Sciences Beijing100049 China Sichuan Zhongke Langxing Photoelectric Technology Co. Ltd. China Center for Future Media University of Electronic Science and Technology of China China Hangzhou Institute of Technology Xidian University China School of Electronic Engineering Xidian University China School of Mechanical Engineering and Automation Fuzhou University China Beijing Insitute of Technology Chongqing Innovation Center China Xinjiang University China Army Engineering University PLA Shijiazhuang Campus China Nanjing University of Science and Technology China Henan University of Technology China Chongqing University China

In this paper, we briefly summarize the first competition on resource-limited infrared small target detection (namely, LimitIRSTD). This competition has two tracks, including weakly-supervised infrared small target detection (Track 1) and lightweight infrared small target detection (Track 2). 46 and 60 teams successfully registered and took part in Tracks 1 and Track 2, respectively. The top-performing methods and their results in each track are described with details. This competition inspires the community to explore the tough problems in the application of infrared small target detection, and ultimately promote the deployment of this technology under limited resource. © 2024, CC BY-NC-SA.

关键词：

Developing a prototype concurrent design tool for composite topside structures

学校读者我要写书评

暂无评论

NAVAL ENGINEERS JOURNAL 1997年第3期109卷 279-290页

作者： Dirlik, S Hambric, S Azarm, S Marquardt, M Hellman, A Bartlett, S Castelli, V Steve Dirlik:began his career at the Naval Surface Warfare Center Carderock Division in 1981 as an aerospace engineer co-op student. He completed his bachelor of science degree in aeropace and ocean engineering from Virginia Polytechnic Institute and State University in 1985 and his master of science degree in aerospace engineering from the University of Maryland in 1990. Mr. Dirlik recently completed a master of science program in applied physics at The Johns Hopins University and currently works in the Radar Cross Section and Target Physics Branch of the Signatures Directorate at the Naval Surface Warfare Center Corderoke Division. He has worked on Navy low observable programs since 1990. Stephen Hambric:is a research associate at the Applied Research Laboratory at The Pennsylvania State University. He received his B. S. and M.S. degree in mechanical engineering from Virginia Polytechnic Institute and State University and his D. Sc. in mechnical engineering from the George Washington University. He has worked on several computer aided multidiscikplinary design and optimization projects over the years including an automated propeller design system and a structural acoustic optimization capability. Dr. Shpour Azarm:is currently working as an associate professor with the Design and Manufacturing Group of the Department of Mechanical Engineering at the University of maryland at College Park. Dr Azarm's expertise is in the areas of optimization-based designed and concurrent design and optimization of multidisciplinary systems. He was a consultant at Black & Decker Corporation (summer 1996) and worked as a Navy senior summer faculty fellow (summer 1995) and a NASA summer faculty fellow (summer 1994). He was a visiting scientist at NASA Langley Research Center for Multidisciplinary Analysis and Applied Structural Optimzatiom at the University of Siegen in Germany (spring 1992) and the Design Institute of the Technical University of Denmark (summer 1990). Dr Azarm was an associate technical editor of the ASME Jour

A prototype concurrent engineering tool has been developed for the preliminary design of composite topside structures for modern navy warships. This tool, named GELS for the Concurrent engineering of Layered Structures, provides designers with an immediate assessment of the impacts of their decisions on several disciplines which are important to the performance of a modern naval topside structure, including electromagnetic interference effects (EMI), radar cross section (RCS), structural integrity, cost, and weight. Preliminary analysis modules in each of these disciplines are integrated to operate from a common set of design variables and a common materials database. Performance in each discipline and an overall fitness function for the concept are then evaluated. A graphical user interface (GUI) is used to define requirements and to display the results from the technical analysis modules. Optimization techniques, including feasible sequential quadratic programming (FSQP) and exhaustive search are used to modify the design variables to satisfy all requirements simultaneously. The development of this tool, the technical modules, and their integration are discussed noting the decisions and compromises required to develop and integrate the modules into a prototype conceptual design tool.

关键词： Warships

ASCAPE: An open AI ecosystem to support the quality of life of cancer patients

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Lampropoulos, Konstantinos Kosmidis, Thanos Autexier, Serge Savić, Miloš Athanatos, Manos Kokkonidis, Miltiadis Koutsouri, Tzortzia Vizitiu, Anamaria Valachis, Antonios Padron, Miriam Quintero Department of Electrical & Computer Engineering University of Patras Patras Greece CareAcross Research CareAcross LTD London United Kingdom Bremen Germany Division of Informatics Faculty of Sciences University of Novi Sad Novi Sad Serbia Institute of Computer Science Foundation for Research and Technology – Hellas Heraklion Crete Greece Research & Innovation Development INTRASOFT International S.A. Luxembourg Luxembourg SPHYNX Research SPHYNX Technology Solutions AG Zug Switzerland Department of Automation and Information Technology Transilvania University of Brasov Brasov Romania Advanta Siemens SRL Brasov Romania Department of Oncology Faculty of Medicine and Health Örebro University Örebro Sweden Atos Research Innovation Atos S.A.E Madrid Spain

The latest cancer statistics indicate a decrease in cancer-related mortality. However, due to the growing and ageing population, the absolute number of people living with cancer is set to keep increasing. This paper presents ASCAPE, an open AI infrastructure that takes advantage of the recent advances in Artificial Intelligence (AI) and Machine Learning (ML) to support cancer patients’ quality of life (QoL). With ASCAPE health stakeholders (e.g. hospitals) can locally process their private medical data and then share the produced knowledge (ML models) through the open AI infrastructure. Copyright © 2023, The Authors. All rights reserved.

关键词： Intelligent systems

C²F²: Cross-Task Cross-Domain Feature Fusion for Semi-Supervised Change Detection

学校读者我要写书评

暂无评论

IEEE Geoscience and Remote Sensing Letters 2024年 21卷

作者： Dongjie Zhang Yuting Hong Xiaojie Qiu Li Dong Diqun Yan Chengbin Peng Faculty of Electrical Engineering and Computer Science and the Key Laboratory of Mobile Network Application Technology of Zhejiang Province Ningbo University Ningbo China Zhejiang Cowain Automation Technology Company Ltd. Ningbo China

Semi-supervised learning for change detection (CD), which significantly reduces the labor costs associated with data annotation, has recently garnered substantial attention. In this study, we propose to enhance traditional semi-supervised learning frameworks by leveraging cross-task cross-domain (CTCD) models, which generate complementary features that differ from standard hidden features. The procedure is as follows. First, the standard features obtained from a traditional encoding–decoding structure are fused with attention-augmented complementary features. Second, a secondary decoder maps the fused heterogeneous features into the label space to obtain high-quality pseudo-labels, offering more precise guidance for semi-supervised learning on traditional structures. This approach improves pseudo-labels by leveraging the strength of CTCD models, including large pretrained models, to enhance the semi-supervised learning process of domain-specific and task-specific models. Experimental results on benchmark datasets demonstrate that our proposed approach surpasses state-of-the-art methods.

关键词： Standards Feature extraction Decoding Training Accuracy Semisupervised learning Supervised learning

Study of tau neutrinos and non-unitary neutrino mixing with the first six detection units of KM3NeT/ORCA

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Aiello, S. Albert, A. Alhebsi, A.R. Alshamsi, M. Garre, S. Alves Ambrosone, A. Ameli, F. Andre, M. Aphecetche, L. Ardid, M. Ardid, S. Aublin, J. Bailly-Salins, L. Bardačová, Z. Baret, B. Bariego-Quintana, A. Becherini, Y. Gualandi, F. Benfenati Benhassi, M. Bennani, M. Benoit, D.M. Berbee, E. Bertin, V. Biagi, S. Boettcher, M. Bonanno, D. Bouasla, A.B. Boumaaza, J. Bouta, M. Bouwhuis, M. Bozza, C. Bozza, R.M. Brânzaş, H. Bretaudeau, F. Breuhaus, M. Bruijn, R. Brunner, J. Bruno, R. Buis, E. Buompane, R. Busto, J. Caiffi, B. Calvo, D. Capone, A. Carenini, F. Carretero, V. Cartraud, T. Cecchini, V. Celli, S. Cerisy, L. Chabab, M. Chen, A. Cherubini, S. Chiarusi, T. Circella, M. Clark, R. Cocimano, R. Coelho, J.A.B. Coyle, P. Creusot, A. Wasseige, G. De Decoene, V. Rosso, I. Del Mauro, L.S. Di Palma, I. Di Díaz, A.F. Diego-Tortosa, D. Distefano, C. Donzaud, C. Drakopoulou, E. Drouhin, D. Ducoin, J.-G. Duverne, P. Eberl, T. Eckerová, E. Eddymaoui, A. Eff, M. Bojaddaini, I. El Hedri, S. El Ellajosyula, V. Enzenhöfer, A. Ferrara, G. Filipović, M.D. Filippini, F. Franciotti, D. Fusco, L.A. Gagliardini, S. Gal, T. Méndez, J. García Soto, A. Garcia Oliver, C. Gatius Geißelbrecht, N. Genton, E. Ghaddari, H. Gialanella, L. Gibson, B.K. Giorgio, E. Goos, I. Gracia, R. Guidi, C. Guillon, B. Gutiérrez, M. Haack, C. van Haren, H. Heijboer, A. Hennig, L. Hernández-Rey, J.J. Idrissi, A. Ibnsalih, W. Idrissi Illuminati, G. Joly, D. de Jong, M. de Jong, P. Jung, B.J. Kalaczynski, P. Kikvadze, V. Kistauri, G. Kopper, C. Kouchner, A. Kovalev, Y.Y. Krupa, L. Kueviakoe, V. Kulikovskiy, V. Kvatadze, R. Labalme, M. Lahmann, R. Lamoureux, M. Larosa, G. Lastoria, C. Lazar, J. Lazo, A. Le Stum, S. Lehaut, G. Lemaître, V. Leonora, E. Lessing, N. Levi, G. Clark, M. Lindsey Magnani, F. Majumdar, J. Malerba, L. Mamedov, F. Manfreda, A. Manousakis, A. Marconi, M. Margiotta, A. Marinelli, A. Markou, C. Martin, L. Via Santa Sofia 64 Catania95123 Italy Université de Strasbourg CNRS IPHC UMR 7178 StrasbourgF-67000 France Khalifa University of Science and Technology Department of Physics PO Box 127788 Abu Dhabi United Arab Emirates Aix Marseille Univ CNRS IN2P3 CPPM Marseille France c/Catedrático José Beltrán 2 Valencia Paterna46980 Spain INFN Sezione di Napoli Complesso Universitario di Monte S. Angelo Via Cintia ed. G Napoli80126 Italy Università di Napoli "Federico II" Dip. Scienze Fisiche "E. Pancini" Complesso Universitario di Monte S. Angelo Via Cintia ed. G Napoli80126 Italy INFN Sezione di Roma Piazzale Aldo Moro 2 Roma00185 Italy Universitat Politècnica de Catalunya Laboratori d’Aplicacions Bioacústiques Centre Tecnològic de Vilanova i la Geltrú Avda. Rambla Exposició s/n Vilanova i la Geltrú08800 Spain Subatech IMT Atlantique IN2P3-CNRS Nantes Université 4 rue Alfred Kastler - La Chantrerie BP Nantes20722 44307 France Universitat Politècnica de València Instituto de Investigación para la Gestión Integrada de las Zonas Costeras C/ Paranimf 1 Gandia46730 Spain Université Paris Cité CNRS Astroparticule et Cosmologie ParisF-75013 France Università di Genova Via Dodecaneso 33 Genova16146 Italy INFN Sezione di Genova Via Dodecaneso 33 Genova16146 Italy LPC CAEN Normandie Univ ENSICAEN UNICAEN CNRS IN2P3 6 boulevard Maréchal Juin Caen14050 France Czech Technical University in Prague Institute of Experimental and Applied Physics Husova 240/5 Prague110 00 Czech Republic Comenius University in Bratislava Department of Nuclear Physics and Biophysics Mlynska dolina F1 Bratislava842 48 Slovakia INFN Sezione di Bologna v.le C. Berti-Pichat 6/2 Bologna40127 Italy Università di Bologna Dipartimento di Fisica e Astronomia v.le C. Berti-Pichat 6/2 Bologna40127 Italy Università degli Studi della Campania"Luigi Vanvitelli" Dipartimento di Matematica e Fisica viale Lincoln 5 Caserta81100 Italy LPC Campus des Cézeaux 24 av

Oscillations of atmospheric muon and electron neutrinos produce tau neutrinos with energies in the GeV range, which can be observed by the ORCA detector of the KM3NeT neutrino telescope in the Mediterranean Sea. First measurements with ORCA6, an early subarray corresponding to about 5% of the final detector, are presented. A sample of 5828 neutrino candidates has been selected from the analysed exposure of 433 kton-years. The ντ normalisation, defined as the ratio between the number of observed and expected tau neutrino events, is measured to be Sτ = 0.48+0−0.335 . This translates into a ντ charged-current cross section measurement of στmeas = (2.5+2−1.68) × 10−38 cm2 nucleon−1 at the median ντ energy of 20.3 GeV. The result is consistent with the measurements of other experiments. In addition, the current limit on the non-unitarity parameter affecting the τ-row of the neutrino mixing matrix was improved, with α33 > 0.95 at the 95% confidence level. Copyright © 2025, The Authors. All rights reserved.

关键词： Neutrons

Advances in Intelligent Systems and Computing

学校读者我要写书评

暂无评论

Preface

Advances in Intelligent Systems and Computing 2018年 733卷 v-vi页

作者： Peng, Sheng-Lung Wang, Shiuh-Jeng Balas, Valentina Emilia Zhao, Ming Department of Computer Science and Information Engineering National Dong Hwa University Hualien Taiwan Department of Information Management Central Police University Taoyuan Taiwan Department of Automation and Applied Informatics Faculty of Engineering Aurel Vlaicu University of Arad Arad Romania School of Computer Technology Jingzhou China

Application of proper orthogonal decomposition and radial basis functions for crack size estimation using particle swarm optimization

学校读者我要写书评

暂无评论

Journal of Physics: Conference Series 2017年第1期842卷

作者： B Benaissa M Köppen M Abdel Wahab S Khatir LEMI Department of Mechanical Engineering University M'hamed Bougara of Boumerdes. Algeria. Faculty of Computer Science and Systems Engineering Department of Creative Informatics Kyushu Institute of Technology. Japan. Department of Electrical Energy Systems and Automation Faculty of Engineering and Architecture Ghent University. Belgium.

Complex engineering problems require simulations, which are computationally expensive in cases of inverse identification tasks since they commonly requires hundreds of thousands of simulations. This paper propose a method based on model reduction for crack size estimation, combining the proper orthogonal decomposition method with radial basis functions. The reduced model is validated by comparing the obtained boundary displacements with the corresponding results from a finite element model. This inverse procedure is formulated as the minimization of the difference between the measured and computed values of displacement at selected boundary nodes, called sensor points, using particle swarm optimization algorithm. Convex and a non-convex specimens have been considered for investigations of crack presence, and identification of its size, different crack sizes have been tested to demonstrate the efficiency of the proposed approach.

关键词：