检索结果-内蒙古大学图书馆

Efficient Pyramid Channel Attention Network for Pathological Myopia Recognition

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Xiaoqing Zhao, Jilu Li, Yan Wu, Hao Zhou, Xiangtian Liu, Jiang Research Institute of Trustworthy Autonomous Systems Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China Center for High Performance Computing Shenzhen Key Laboratory of Intelligent Bioinformatics Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China National Clinical Research Center for Ocular Diseases Eye Hospital Wenzhou Medical University Wenzhou325027 China State Key Laboratory of Ophthalmology Optometry and Visual Science Eye Hospital Wenzhou Medical University Wenzhou325027 China Research Unit of Myopia Basic Research and Clinical Prevention and Control Chinese Academy of Medical Sciences Wenzhou325027 China Singapore Eye Research Institute 169856 Singapore

Pathological myopia (PM) is the leading ocular disease for impaired vision worldwide. Clinically, the characteristic of pathology distribution in PM is global-local on the fundus image, which plays a significant role in assisting clinicians in diagnosing PM. However, most existing deep neural networks focused on designing complex architectures but rarely explored the pathology distribution prior of PM. To tackle this issue, we propose an efficient pyramid channel attention (EPCA) module, which fully leverages the potential of the clinical pathology prior of PM with pyramid pooling and multi-scale context fusion. Then, we construct EPCA-Net for automatic PM recognition based on fundus images by stacking a sequence of EPCA modules. Moreover, motivated by the recent pretraining-and-finetuning paradigm, we attempt to adapt pre-trained natural image models for PM recognition by freezing them and treating the EPCA and other attention modules as adapters. In addition, we construct a PM recognition benchmark termed PM-fundus by collecting fundus images of PM from publicly available datasets. The comprehensive experiments demonstrate the superiority of EPCA-Net over state-of-the-art methods in the PM recognition task. For example, EPCA-Net achieves 97.56% accuracy and outperforms ViT by 2.85% accuracy on the PM-fundus dataset. The results also show that our method based on the pretraining-and-finetuning paradigm achieves competitive performance through comparisons to part of previous methods based on traditional fine-tuning paradigm with fewer tunable parameters, which has the potential to leverage more natural image foundation models to address the PM recognition task in limited medical data regime. Copyright © 2023, The Authors. All rights reserved.

关键词： Pathology

Fatigue strength simulation of natural porous structure

学校读者我要写书评

暂无评论

International Journal of the Society of Material engineering for Resources 2018年第2期23卷 167-172页

作者： Tanaka, Yohei Masuyama, Tomoya Takahashi, Takeshi Iizuka, Hiroshi Course of Mechanical and Control Engineering Department of Advanced Engineering Course National Institute of Technology Tsuruoka College 104 Ino-oka sawada TsuruokaYamagata997-8511 Japan Course of Mechanical Engineering Department of Creative Engineering National Institute of Technology Tsuruoka College Higashine Yamagata999-3716 Japan Sanwa Yushi Co.Ltd. Higashine Yamagata999-3716 Japan Department of Mechanical System Engineering Faculty of Engineering Yamagata University 4-3-16 Jonan Yonezawa Yamagata992-8510 Japan

Rice hull which is one of the agricultural wastes in Japan has been demanded to reuse as the industrial materials. Rice hull silica carbon (RHSC) material, made from rice hull is produced by mixing rice hull powder with a phenol resin, and then carbonizing and the mixture in the nitrogen gas atmosphere at high temperatures. The RHSC is a porous carbon material utilizing natural porous structure originated from the rice hull. Therefore, reduction in environmental pollution is expected by the RHSC which is inexpensive and unique. In addition, a core competence of low friction coefficient, lubrication free, and high water resistance was reported for the RHSC in previous research. However, the RHSC has low reliability of strength originated potentially from the porous structure. Since the reliability of the RHSC is evaluated by a fatigue test which is required several weeks, calculating the fatigue strength by simulation analysis is useful. In this study, fatigue strength simulation analysis in natural porous structure was figured out and the size effect which influences the strength of the material was investigated. ©2018 Soc. Mater. Eng. Resour. Japan

关键词： Carbon

Mechanical Analysis and Performance Optimization for the Lunar Rover’s Vane-Telescopic Walking Wheel

学校读者我要写书评

暂无评论

engineering 2020年第8期6卷 936-943页

作者： Lu Yang Bowen Cai Ronghui Zhang Kening Li Zixian Zhang Jiehao Lei Baichao Chen Rongben Wang Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical EngineeringTianjin University of TechnologyTianjin 300384China National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin University of TechnologyTianjin 300384China Guangdong Key Laboratory of Intelligent Transportation System School of Intelligent Systems EngineeringSun Yat-sen UniversityGuangzhou 510275China College of Transportation Jilin UniversityChangchun 130025China Department of Mechanical Science and Engineering Tokyo Institute of TechnologyTokyo 152-8550Japan Armour College of Engineering Illinois Institute of TechnologyChicagoIL 60616USA China Academy of Space Technology Beijing 100029China

It is well-known that optimizing the wheel system of lunar rovers is ***,this is a difficult task due to the complex terrain of the moon and limited resources onboard lunar *** this study,an experimental prototype was set up to analyze the existing mechanical design of a lunar rover and improve its ***,a new vane-telescopic walking wheel was proposed for the lunar rover with a positive and negative quadrangle suspension,considering the complex terrain of the ***,the performance was optimized under the limitations of preserving the slope passage and minimizing power *** was achieved via analysis of the wheel force during ***,the effectiveness of the proposed method was demonstrated by several simulation *** newly designed wheel can protrude on demand and reduce energy consumption;it can be used as a reference for lunar rover development engineering in China.

关键词： Intelligent vehicle Vane-telescopic walking wheel Performance optimization Vane spring Lunar rover

A Stochastic Inventory Model with Two Queues and a Flexible Server

学校读者我要写书评

暂无评论

International Journal of Applied and Computational Mathematics 2019年第1期5卷 1-27页

作者： Jeganathan, K. Melikov, A.Z. Padmasekaran, S. Kingsly, S. Jehoashan Lakshmi, K. Prasanna Ramanujan Institute for Advanced Study in Mathematics University of Madras Chennai India Institute of Control Systems National Academy of Sciences Baku Azerbaijan Department of Mathematics Periyar University Salem India Department of Mathematics Adhiyamaan College of Engineering Hosur India Department of Mathematics with Computer Applications Ethiraj College for Women Chennai India

This paper focusses on a perishable inventory model with two stations, namely, station 1 and station 2 with two dedicated servers and one flexible server, where service rates are different with respect to stations and servers. By using matrix analysis method, the joint stationary distribution of the number of customers in station 1 and station 2, the status of the servers and the inventory level under steady state are investigated. Some significant measures of the system performance are obtained. Finally, some intrinsic numerical examples are given. © 2019, Springer Nature India Private Limited.

关键词： (s, Q) policy Additional service Balking and multiple vacations Continuous review Flexible server Heterogeneous servers Perishable commodity

The 2024 Active Metamaterials Roadmap

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Pope, Simon A. Roth, Diane J. Bansal, Aakash Mousa, Mostafa Rezanejad, Ashkan Forte, Antonio E. Nash, Geoff.R. Singleton, Lawrence Langfeldt, Felix Cheer, Jordan Henthorn, Stephen Hooper, Ian R. Hendry, Euan Powell, Alex W. Souslov, Anton Plum, Eric Sun, Kai de Groot, C.H. Muskens, Otto L. Shields, Joe De Galarreta, Carlota Ruiz Wright, C. David Kocabas, Coskun Ergoktas, M. Said Xiao, Jianling Schulz, Sebastian A. Di Falco, Andrea Krasavin, Alexey V. Zayats, Anatoly V. Galiffi, Emanuele Department of Automatic Control and Systems Engineering The University of Sheffield Amy Johnson Building Portobello Street SheffieldS1 3JD United Kingdom Department of Physics London Centre for Nanotechnology King’s College London Strand WC2R 2LS United Kingdom Wolfson School of Mechanical Electrical and Manufacturing Engineering Loughborough University United Kingdom Department of Engineering King’s College London LondonWC2R 2LS United Kingdom Natural Sciences University of Exeter Harrison Building North Park Road Exeter United Kingdom Institute of Sound & Vibration Research University of Southampton University Road Southampton United Kingdom Department of Electronic and Electrical Engineering University of Sheffield Sheffield United Kingdom Centre for Metamaterial Research and Innovation University of Exeter Stoker Road ExeterEX4 4QL United Kingdom T.C.M. Group Cavendish Laboratory University of Cambridge CambridgeCB3 0HE United Kingdom Optoelectronics Research Centre Centre for Photonic Metamaterials University of Southampton Highfield SouthamptonSO17 1BJ United Kingdom School of Physics and Astronomy University of Southampton Southampton United Kingdom Electronics and Computer Science University of Southampton Southampton United Kingdom Institute of Materials Science of Barcelona Universitat Autònoma de Barcelona Bellaterra Barcelona08193 Spain Department of Materials National Graphene Institute University of Manchester United Kingdom Schoolof Physics and Astronomy University of St Andrews North Haugh Fife St. AndrewsKY16 9SS United Kingdom Department of Electrical and Computer Engineering University of Waterloo 200 University Avenue West WaterlooONN2L 3G1 Canada Photonics Initiative Advanced Science Research Centre City University of New York 85 St. Nicholas Terrace New YorkNY10027 United States

Active metamaterials are engineered structures that possess novel properties that can be changed after the point of manufacture. Their novel properties arise predominantly from their physical structure, as opposed to their chemical composition and can be changed through means such as direct energy addition into wave paths, or physically changing/morphing the structure in response to both a user or environmental input. Active metamaterials are currently of wide interest to the physics community and encompass a range of sub-domains in applied physics (e.g. photonic, microwave, acoustic, mechanical, etc.). They possess the potential to provide solutions that are more suitable to specific applications, or which allow novel properties to be produced which cannot be achieved with passive metamaterials, such as time-varying or gain enhancement effects. They have the potential to help solve some of the important current and future problems faced by the advancement of modern society, such as achieving net-zero, sustainability, healthcare and equality goals. Despite their huge potential, the added complexity of their design and operation, compared to passive metamaterials creates challenges to the advancement of the field, particularly beyond theoretical and lab -based experiments. This roadmap brings together experts in all types of active metamaterials and across a wide range of areas of applied physics. The objective is to provide an overview of the current state of the art and the associated current/future challenges, with the hope that the required advances identified create a roadmap for the future advancement and application of this field. Copyright © 2024, The Authors. All rights reserved.

关键词： Microwave acoustics

An Early Stage Researcher's Primer on systems Medicine Terminology

学校读者我要写书评

暂无评论

Network and Systems Medicine

Network and systems Medicine 2021年第1期4卷 2-50页

作者： Zanin, Massimiliano Aitya, Nadim A.A. Basilio, José Baumbach, Jan Benis, Arriel Behera, Chandan K. Bucholc, Magda Castiglione, Filippo Chouvarda, Ioanna Comte, Blandine Dao, Tien-Tuan Ding, Xuemei Pujos-Guillot, Estelle Filipovic, Nenad Finn, David P. Glass, David H. Harel, Nissim Iesmantas, Tomas Ivanoska, Ilinka Joshi, Alok Boudjeltia, Karim Zouaoui Kaoui, Badr Kaur, Daman Maguire, Liam P. McClean, Paula L. McCombe, Niamh De Miranda, João Luís Moisescu, Mihnea Alexandru Pappalardo, Francesco Polster, Annikka Prasad, Girijesh Rozman, Damjana Sacala, Ioan Sanchez-Bornot, Jose M. Schmid, Johannes A. Sharp, Trevor Solé-Casals, Jordi Spiwok, Vojtěch Spyrou, George M. Stalidzans, Egils Stres, Blaa Sustersic, Tijana Symeonidis, Ioannis Tieri, Paolo Todd, Stephen Van Steen, Kristel Veneva, Milena Wang, Da-Hui Wang, Haiying Wang, Hui Watterson, Steven Wong-Lin, Kongfatt Yang, Su Zou, Xin Schmidt, Harald H.H.W. Centro de Tecnología Biomédica Universidad Politécnica de Madrid Madrid Spain Intelligent Systems Research Centre School of Computing Engineering and Intelligent Systems Ulster University Ulster United Kingdom Center for Physiology and Pharmacology Institute of Vascular Biology and Thrombosis Research Medical University of Vienna Vienna Austria TUM School of Life Sciences Weihenstephan Technical University of Munich Freising Germany Holon Israel CNR National Research Council IAC Institute for Applied Computing Rome Italy Lab of Computing Medical Informatics and Biomedical Imaging Technologies School of Medicine Aristotle University of Thessaloniki Thessaloniki Greece Université Clermont Auvergne INRAE UNH Plateforme d'Exploration du Métabolisme MetaboHUB Clermont Clermont-Ferrand France Université de Technologie de Compiègne Compiègne France Labex MS2T Control of Technological Systems-of-Systems CNRS and Université de Technologie de Compiègne Compiègne France Faculty of Engineering University of Kragujevac Kragujevac Serbia Kragujevac Serbia Steinbeis Advanced Risk Technologies Institute Doo Kragujevac Kragujevac Serbia Pharmacology and Therapeutics School of Medicine Galway Neuroscience Centre National University of Ireland Galway Ireland School of Computing Ulster University Ulster United Kingdom Holon Israel Department of Mathematics and Natural Sciences Kaunas University of Technology Kaunas Lithuania Faculty of Computer Science and Engineering Ss. Cyril and Methodius University Skopje Macedonia Medicine Faculty Université Libre de Bruxelles CHU de Charleroi Charleroi Belgium Northern Ireland Centre for Stratified Medicine Biomedical Sciences Research Institute Ulster University Ulster United Kingdom Escola Superior de Tecnologia e Gestão Instituto Politécnico de Portalegre Portalegre Portugal Instituto Superior Técnico Universidade de Lisboa Lisboa Portugal Faculty of Automatic Control and Computers University Politehnica of B

Background: systems Medicine is a novel approach to medicine, that is, an interdisciplinary field that considers the human body as a system, composed of multiple parts and of complex relationships at multiple levels, and further integrated into an environment. Exploring systems Medicine implies understanding and combining concepts coming from diametral different fields, including medicine, biology, statistics, modeling and simulation, and data science. Such heterogeneity leads to semantic issues, which may slow down implementation and fruitful interaction between these highly diverse fields. Methods: In this review, we collect and explain more than100 terms related to systems Medicine. These include both modeling and data science terms and basic systems medicine terms, along with some synthetic definitions, examples of applications, and lists of relevant references. Results: This glossary aims at being a first aid kit for the systems Medicine researcher facing an unfamiliar term, where he/she can get a first understanding of them, and, more importantly, examples and references for digging into the topic. © Massimiliano Zanin et al., 2021;Published by Mary Ann Liebert, Inc. 2021.

关键词： Semantics

Distributed linear equations over random networks

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Yi, Peng Lei, Jinlong Chen, Jie Hong, Yiguang Shi, Guodong Department of Control Science and Engineering Tongji University Shanghai201804 China Institute of Advanced Study Tongji University Shanghai201804 China Australian Centre for Field Robotics Sydney Institute for Robotics and Intelligent Systems University of Sydney NSW2006 Australia

Distributed linear algebraic equation over networks, where nodes hold a part of problem data and cooperatively solve the equation via node-to-node communications, is a basic distributed computation task receiving an increasing research attention. Communications over a network have a stochastic nature, with both temporal and spatial dependence due to link failures, packet dropouts or node recreation, etc. In this paper, we study the convergence and convergence rate of distributed linear equation protocols over a ∗-mixing random network, where the temporal and spatial dependencies between the node-to-node communications are allowed. When the network linear equation admits exact solutions, we prove the mean-squared exponential convergence rate of the distributed projection consensus algorithm, while the lower and upper bound estimations of the convergence rate are also given for independent and identically distributed (i.i.d.) random graphs. Motivated by the randomized Kaczmarz algorithm, we also propose a distributed randomized projection consensus algorithm, where each node randomly selects one row of local linear equations for projection per iteration, and establish an exponential convergence rate. When the network linear equation admits no exact solution, we prove that a distributed gradient-descent-like algorithm with diminishing step-sizes can drive all nodes' states to a least-squares solution at a sublinear rate. These results collectively illustrate that distributed computations may overcome communication correlations if the prototype algorithms enjoy certain contractive properties or are designed with suitable parameters. Copyright © 2020, The Authors. All rights reserved.

关键词： Graph theory

Fabry-perot lasers as enablers for parallel reservoir computing

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Bogris, Adonis Mesaritakis, Charis Deligiannidis, Stavros Li, Pu Department of Informatics and Computer Engineering University of West Attica Aghiou Spiridonos Egaleo Athens12243 Greece Department of Information & Communication Systems Engineering University of the Aegean 2 Palama & Gorgyras St. Karlovassi Samos83200 Greece Key Laboratory of Advanced Transducers and Intelligent Control System Ministry of Education Taiyuan University of Technology Taiyuan030024 China

We introduce the use of Fabry-Perot (FP) lasers as potential neuromorphic computing machines with parallel processing capabilities. With the use of optical injection between a master FP laser and a slave FP laser under feedback we demonstrate the potential for scaling up the processing power at longitudinal mode granularity and perform real-time processing for signal equalization in 25 Gbaud intensity modulation direct detection optical communication systems. We demonstrate the improvement of classification performance as the number of nodes increases and the capability of simultaneous processing of arbitrary data streams. Extensive numerical simulations show that up to 8 longitudinal modes in typical Fabry-Perot lasers can be leveraged so as to enhance classification performance. Copyright © 2020, The Authors. All rights reserved.

关键词： Recurrent neural networks

controlling a networked SIS model via a single input over undirected graphs

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Wang, Dan Liu, Ji Paré, Philip E. Chen, Wei Qiu, Li Beck, Carolyn L. Başar, Tamer Department of Electronic & Computer Engineering Hong Kong University of Science and Technology Clear Water Bay Kowloon Hong Kong Department of Electrical and Computer Engineering Stony Brook University NY11794 United States Division of Decision and Control Systems KTH Royal Institute of Technology Stockholm Sweden Department of Mechanics and Engineering Science Beijing Innovation Center for Engineering Science and Advanced Technology Peking University Beijing China Coordinated Science Laboratory University of Illinois at Urbana-Champaign IL61801 United States

This paper formulates and studies the problem of controlling a networked SIS model using a single input in which the network structure is described by a connected undirected graph. A necessary and sufficient condition on the values of curing and infection rates for the healthy state to be exponentially stable is obtained via the analysis of signed Laplacians when the control input is the curing budget of a single agent. In the case when the healthy state is stabilizable, an explicit expression for the minimum curing budget is provided. The utility of the algorithm is demonstrated using a simulation over a network of cities in the northeastern United States. Copyright © 2020, The Authors. All rights reserved.

关键词： Budget control