检索结果-内蒙古大学图书馆

DeepReg: A deep learning toolkit for medical image registration

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Fu, Yunguan Brown, Nina Montaña Saeed, Shaheer U. Casamitjana, Adrià Baum, Zachary M.C. Delaunay, Rémi Yang, Qianye Grimwood, Alexander Min, Zhe Blumberg, Stefano B. Iglesias, Juan Eugenio Barratt, Dean C. Bonmati, Ester Alexander, Daniel C. Clarkson, Matthew J. Vercauteren, Tom Hu, Yipeng Wellcome/EPSRC Centre for Surgical and Interventional Sciences University College London London United Kingdom Centre for Medical Image Computing University College London London United Kingdom InstaDeep London United Kingdom Department of Surgical & Interventional Engineering King’s College London London United Kingdom Martinos Center for Biomedical Imaging Massachusetts General Hospital Harvard Medical School Boston United States Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology Boston United States

关键词： Deep learning

High-rate and high-capacity measurement-deviceindependent quantum key distribution with Fibonacci matrix coding in free space

学校读者我要写书评

暂无评论

science China(Information sciences) 2018年第6期61卷 227-237页

作者： Hong LAI Mingxing LUO Josef PIEPRZYK Jun ZHANG Lei PAN Mehmet A.ORGUN School of Computer and Information Science and Centre for Research and Innovation in Software Engineering (RISE) Southwest University Information Security and National Computing Grid Laboratory School of Information Science and TechnologySouthwest Jiaotong University School of Electrical Engineering and Computer Science Queensland University of Technology Institute of Computer Science Polish Academy of Sciences School of Information Technology Deakin University Department of Computing Macquarie University Faculty of Information Technology Macau University of Science and Technology

This paper proposes a high-rate and high-capacity measurement-device-independent quantum key distribution(MDI-QKD) protocol with Fibonacci-valued and Lucas-valued orbital angular momentum(OAM) entangled states in free space. In the existing MDI-OAM-QKD protocols, the main encoding algorithm handles encoded numbers in a bit-by-bit manner. To design a fast encoding algorithm, we introduce a Fibonacci matrix coding algorithm, by which, encoded numbers are separated into segments longer than one bit. By doing so, when compared to the existing MDI-OAM-QKD protocols, the new protocol can effectively increase the key rate and the coding capacity. This is because Fibonacci sequences are used in preparing OAM entangled states, reducing the misattribution errors(which slow down the execution cycle of the entire QKD) in QKD protocols. Moreover, our protocol keeps the data blocks as small as possible, so as to have more blocks in a given time interval. Most importantly, our proposed protocol can distill multiple Fibonacci key matrices from the same block of data, thus reducing the statistical fluctuations in the sample and increasing the final QKD rate. Last but not the least, the sender and the receiver can omit classical information exchange and bit flipping in the secure key distillation stage.

关键词： measurement-device-independent quantum key distribution Fibonacci-matrix coding free space orbital angular momentum bit flipping misattribution errors

Definition of Internet of Things (IoT) Cyber Risk – Discussion on a Transformation Roadmap for Standardization of Regulations, Risk Maturity, Strategy Design and Impact Assessment

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Radanliev, Petar de Roure, David Charles Nurse, Jason R.C. Burnap, Pete Anthi, Eirini Ani, Uchenna Maddox, La'Treall Santos, Omar Montalvo, Rafael Mantilla 1Oxford e-Research Centre Department of Engineering Sciences University of Oxford United Kingdom 2School of Computing University of Kent United Kingdom 3School of Computer Science and Informatics Cardiff University STEaPP Faculty of Engineering Science University College London 5Cisco Research Centre Research Triangle Park United States

The Internet-of-Things (IoT) enables enterprises to obtain profits from data but triggers data protection questions and new types of cyber risk. Cyber risk regulations for the IoT however do not exist. The IoT risk is not included in the cyber security assessment standards, hence, often not visible to cyber security experts. This is concerning, because companies integrating IoT devices and services need to perform a self-assessment of its IoT cyber security posture. The outcome of such self-assessment needs to define a current and target state, prior to creating a transformation roadmap outlining tasks to achieve the stated target state. In this article, a comparative empirical analysis is performed of multiple cyber risk assessment approaches, to define a high-level potential target state for company integrating IoT devices and/or services. Defining a high-level potential target state represent is followed by a high-level transformation roadmap, describing how company can achieve their target state, based on their current state. The transformation roadmap is used to adapt IoT risk impact assessment with a Goal-Oriented Approach and the Internet of Things Micro Mart model. Copyright © 2019, The Authors. All rights reserved.

关键词： Internet of things

Overcoming the disconnect between energy system and climate modelling

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Craig, Michael T. Wohland, Jan Stoop, Laurens P. Kies, Alexander Pickering, Bryn Bloomfield, Hannah C. Browell, Jethro De Felice, Matteo Dent, Chris J. Deroubaix, Adrien Frischmuth, Felix Gonzalez, Paula L.M. Grochowicz, Aleksander Gruber, Katharina Härtel, Philipp Kittel, Martin Kotzur, Leander Labuhn, Inga Lundquist, Julie K. Pflugradt, Noah van der Wiel, Karin Zeyringer, Marianne Brayshaw, David J. School for Environment and Sustainability University of Michigan United States Institute for Environmental Decisions ETH Zurich Switzerland Helmholtz-Zentrum Hereon Germany Information and Computing Science Copernicus Institute of Sustainable Development Utrecht University Netherlands TenneT TSO B.V. Arnhem Netherlands Royal Netherlands Meteorological Institute Netherlands Frankfurt Institute for Advanced Studies Germany Department of Electrical and Computer Engineering Aarhus University Denmark ETH Zürich Switzerland School of Geographical Sciences University of Bristol United Kingdom Department of Meteorology University of Reading United Kingdom University of Glasgow United Kingdom European Commission Joint Research Centre Netherlands School of Mathematics University of Edinburg United Kingdom The Alan Turing Institute United Kingdom Max Planck Institute Germany Fraunhofer Institute for Energy Economics and Energy System Technology Germany Department of Mathematics University of Oslo Norway University of Natural Resources and Life Sciences Austria German Institute for Economic Research Germany Institute of Energy and Climate Research Techno-economic Systems Analysis Germany University of Bremen Institute of Geography Germany Dept. of Atmospheric and Oceanic Science University of Colorado Boulder United States National Renewable Energy Laboratory United States Renewable and Sustainable Energy Institute United States Forschungszentrum Jülich Germany Department of Technology Systems University of Oslo Norway

Energy system models underpin decisions by energy system planners and operators. Energy system modelling faces a transformation: accounting for changing meteorological conditions imposed by climate change. To enable that transformation, a community of practice in energy-climate modelling has started to form that aims to better integrate energy system models with weather and climate models. Here, we evaluate the disconnects between the energy system and climate modelling communities, then lay out a research agenda to bridge those disconnects. In the near-term, we propose interdisciplinary activities for expediting uptake of future climate data in energy system modelling. In the long-term, we propose a transdisciplinary approach to enable development of (1) energy-system-tailored climate datasets for historical and future meteorological conditions and (2) energy system models that can effectively leverage those datasets. This agenda increases the odds of meeting ambitious climate mitigation goals by systematically capturing and mitigating climate risk in energy sector decision making. © 2022, CC BY-NC-ND.

关键词： Decision making

Geo-Cloudlet: Time and Power Efficient Geospatial Query Resolution using Cloudlet

学校读者我要写书评

暂无评论

Geo-Cloudlet: Time and Power Efficient Geospatial Query Reso...

International Conference on Advanced computing, ICAC

作者： Jaydeep Das Anwesha Mukherjee Soumya K. Ghosh Rajkumar Buyya Advanced Technology Development Centre Indian Institute of Technology Kharagpur West Bengal India Department of Computer Science Mahishadal Raj College Purba Medinipur West Bengal India Department of Computer Science and Engineering Indian Institute of Technology Kharagpur West Bengal India Cloud Computing and Distributed Systems (CLOUDS) Lab School of Computing and Information Systems The University of Melbourne VIC Australia

ISBN: (数字)9781728152868

ISBN: (纸本)9781728152875

Geospatial data analysis is an emerging area of research today due to the potential to enable varied location-aware services. The existing centralized cloud-based analysis becomes time and computing-intensive for huge amount of geospatial data processing. This paper addresses the challenge of time and power-efficiency in QoS-aware geospatial query resolution. We propose a cloudlet based hierarchical paradigm, namely Geo-Cloudlet, where the cloudlets contain the geospatial data of the districts. The state and national level geospatial data are stored inside the state cloud and country cloud respectively. The query resolution is performed by either the cloudlet or by the state cloud or country cloud depending upon the geographical region related to the query. The experimental analysis illustrates that the proposed architecture Geo-Cloudlet reduces the latency up to 61.3% and power consumption up to 61.1% over the use of only remote cloud servers for geospatial query resolution.

关键词：

DFUC 2020: Analysis towards diabetic foot ulcer detection

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Cassidy, Bill Reeves, Neil D. Pappachan, Joseph M. Gillespie, David O'Shea, Claire Rajbhandari, Satyan Maiya, Arun G. Frank, Eibe Boulton, Andrew J.M. Armstrong, David G. Najafi, Bijan Wu, Justina Yap, Moi Hoon Department of Computing and Mathematics Faculty of Science and Engineering Manchester Metropolitan University ManchesterM1 5GD United Kingdom Research Centre for Musculoskeletal Science & Sports Medicine Faculty of Science and Engineering Manchester Metropolitan University ManchesterM1 5GD United Kingdom Lancashire Teaching Hospital PrestonPR2 9HT United Kingdom Waikato District Health Board New Zealand Manipal College of Health Professions India Department of Computer Science University of Waikato New Zealand School of Medical Sciences University of Manchester United Kingdom Keck School of Medicine University of Southern California United States Baylor College of Medicine Texas United States

Every 20 seconds, a limb is amputated somewhere in the world due to diabetes. This is a global health problem that requires a global solution. The MICCAI challenge discussed in this paper, which concerns the automated detection of diabetic foot ulcers using machine learning techniques, will accelerate the development of innovative healthcare technology to address this unmet medical need. In an effort to improve patient care and reduce the strain on healthcare systems, recent research has focused on the creation of cloud-based detection algorithms. These can be consumed as a service by a mobile app that patients (or a carer, partner or family member) could use themselves at home to monitor their condition and to detect the appearance of a diabetic foot ulcer (DFU). Collaborative work between Manchester Metropolitan University, Lancashire Teaching Hospital and the Manchester University NHS Foundation Trust has created a repository of 4,000 DFU images for the purpose of supporting research toward more advanced methods of DFU detection. Based on a joint effort involving the lead scientists of the UK, US, India and New Zealand, this challenge will solicit original work, and promote interactions between researchers and interdisciplinary collaborations. This paper presents a dataset description and analysis, assessment methods, benchmark algorithms and initial evaluation results. It facilitates the challenge by providing useful insights into state-of-the-art and ongoing research. This grand challenge takes on even greater urgency in a peri and post-pandemic period, where stresses on resource utilization will increase the need for technology that allows people to remain active, healthy and intact in their home. Copyright © 2020, The Authors. All rights reserved.

关键词： Hospitals

Ultra-fast MRI for dementia diagnosis and treatment eligibility: A prospective study

学校读者我要写书评

暂无评论

Alzheimer's & Dementia 2025年第6期21卷 e70341页

作者： Miguel Rosa-Grilo Haroon R. Chughtai David L. Thomas Daniel C. Alexander Millie Beament Christopher R. S. Belder H. Rolf Jäger Emma A. Lim Nicholas Magill Dermot Mallon Jennifer M. Nicholas Owen Nicholas Floey Urban Geoff J. M. Parker Frederik Barkhof Catherine J. Mummery Nick C. Fox Dementia Research Centre UCL Queen Square Institute of Neurology University College London London UK UCL Hawkes Institute University College London London UK Department of Medical Physics and Biomedical Engineering University College London Malet Place Engineering Building London UK Advanced Research Computing (ARC) Centre University College London London UK Neuroradiological Academic Unit Department of Brain Repair and Rehabilitation UCL Queen Square Institute of Neurology University College London London UK Department of Computer Science University College London London UK Neurology Department Royal Adelaide Hospital and Queen Elizabeth Hospital Adelaide Australia Adelaide Medical School The University of Adelaide Adelaide Australia Department of Imaging Imperial College Healthcare NHS Trust London UK Lysholm Department of Neuroradiology National Hospital for Neurology and Neurosurgery Queen Square London UK Department of Medical Statistics London School of Hygiene & Tropical Medicine London UK Department of Statistical Science University College London London UK Bioxydyn Limited St James Tower Manchester UK Department of Radiology and Nuclear Medicine Amsterdam UMC Vrije Universiteit Amsterdam The Netherlands

INTRODUCTION Magnetic resonance imaging (MRI) is crucial for dementia diagnosis and a pre-requisite for amyloid-lowering therapies in Alzheimer's disease. Despite guidelines, many patients never undergo MRI due to limited scanner availability. Shorter scan times would reduce costs and patient burden. We developed and tested a fast MRI protocol incorporating highly accelerated sequences. METHODS We compared blinded neuroradiologist assessments of a fast protocol with the standard-of-care protocol in a prospective real-world study. We estimated agreement coefficients to evaluate reliability. RESULTS The fast protocol cut scan times by 63% and showed non-inferior reliability measures for diagnosis, visual scale ratings, and disease-modifying therapy eligibility assessment. Between scan-type, intra-rater reliability for diagnosis was greater than inter-rater reliability on the standard-of-care protocol (ratio of 1.37, 95% confidence interval: 1.21–1.58). DISCUSSION This study proposed and applied a way of showing non-inferiority of a highly accelerated dementia protocol. Ultra-fast protocols could improve MRI access and patient equity and support the implementation of disease-modifying therapies. Highlights The fast dementia protocol with four core sequences reduced acquisition time by 63%. The fast scan showed non-inferior reliability for diagnosis and visual ratings. Assessment for disease-modifying therapy eligibility was similar between scan types. Fast protocols may improve access to magnetic resonance imaging and diagnosis in dementia.

关键词： advanced parallel imaging Alzheimer's disease dementia diagnosis eligibility for disease-modifying therapies in Alzheimer's disease MRI acceleration techniques structural MRI wave-CAIPI

Foundation models and intelligent decision-making: Progress, challenges, and perspectives

学校读者我要写书评

暂无评论

Innovation 2025年第6期6卷 100948页

作者： Huang, Jincai Xu, Yongjun Wang, Qi Wang, Qi [Cheems] Liang, Xingxing Wang, Fei Zhang, Zhao Wei, Wei Zhang, Boxuan Huang, Libo Chang, Jingru Ma, Liantao Ma, Ting Liang, Yuxuan Zhang, Jie Guo, Jian Jiang, Xuhui Fan, Xinxin An, Zhulin Li, Tingting Li, Xuefei Shao, Zezhi Qian, Tangwen Sun, Tao Diao, Boyu Yang, Chuanguang Yu, Chenqing Wu, Yiqing Li, Mengxian Zhang, Haifeng Zeng, Yongcheng Zhang, Zhicheng Zhu, Zhengqiu Lv, Yiqin Li, Aming Chen, Xu An, Bo Xiao, Wei Bai, Chenguang Mao, Yuxing Yin, Zhigang Gui, Sheng Su, Wentao Zhu, Yinghao Gao, Junyi He, Xinyu Li, Yizhou Jin, Guangyin Ao, Xiang Zhai, Xuehao Tan, Haoran Yun, Lijun Shi, Hongquan Li, Jun Fan, Changjun Huang, Kuihua Harrison, Ewen Leung, Victor C.M. Qiu, Sihang Dong, Yanjie Zheng, Xiaolong Wang, Gang Zheng, Yu Wang, Yuanzhuo Guo, Jiafeng Wang, Lizhe Cheng, Xueqi Wang, Yaonan Yang, Shanlin Fu, Mengyin Fei, Aiguo Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Department of Automation Tsinghua University Beijing100084 China Huazhong University of Science and Technology Wuhan430074 China School of Automation Beijing Institute of Technology Beijing100081 China School of Information Science and Engineering Dalian Polytechnic University Dalian116034 China National Engineering Research Center for Software Engineering Peking University Beijing100871 China Department of Oral Implantology Peking University School and Hospital of Stomatology Beijing100081 China Guangzhou511453 China College of Information and Electrical Engineering China Agricultural University Beijing100083 China IDEA Research International Digital Economy Academy Shenzhen518057 China Institute of Automation Chinese Academy of Sciences Beijing100190 China The State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China College of Science National University of Defense Technology Changsha410073 China Center for Systems and Control College of Engineering Peking University Beijing100871 China Gaoling School of Artificial Intelligence Renmin University of China Beijing100872 China College of Systems Engineering National University of Defense Technology Changsha410073 China Laboratory for Big Data and Decision National University of Defense Technology Changsha410073 China College of Computing and Data Science Nanyang Technological University Singapore639798 Singapore School of Electrical Engineering Chongqing University Chongqing400044 China Department of Mathematics The University of Hong Kong Hong Kong SAR999077 China School of Food Science and Technology Dalian Polytechnic University Dalian116034 China Centre for Medical Informatics University of Edinburgh EdinburghEH16 4UX United Kingdom Department of Stomatology Peking Union Medical College Hospital Chinese Academ

Intelligent decision-making (IDM) is a cornerstone of artificial intelligence (AI) designed to automate or augment decision processes. Modern IDM paradigms integrate advanced frameworks to enable intelligent agents to make effective and adaptive choices and decompose complex tasks into manageable steps, such as AI agents and high-level reinforcement learning. Recent advances in multimodal foundation-based approaches unify diverse input modalities—such as vision, language, and sensory data—into a cohesive decision-making process. Foundation models (FMs) have become pivotal in science and industry, transforming decision-making and research capabilities. Their large-scale, multimodal data-processing abilities foster adaptability and interdisciplinary breakthroughs across fields such as healthcare, life sciences, and education. This survey examines IDM's evolution, advanced paradigms with FMs and their transformative impact on decision-making across diverse scientific and industrial domains, highlighting the challenges and opportunities in building efficient, adaptive, and ethical decision systems. © 2025 The Authors

关键词： Reinforcement learning

CACA-UAN: A context-aware communication approach to efficient and reliable underwater acoustic sensor networks

学校读者我要写书评

暂无评论

CACA-UAN: A context-aware communication approach to efficien...

作者： Liu, Qi Chen, Xuedong Liu, Xiaodong Linge, Nigel Jiangsu Collaborative Innovation Centre of Atmospheric Environment and Equipment Technology School of Computer and Software Nanjing University of Information Science and Technology Nanjing210044 China School of Computer and Software Jiangsu Engineering Centre of Network Monitoring Nanjing University of Information Science and Technology Nanjing210044 China School of Computing Edinburgh Napier University 10 Clinton Road EdinburghEH10 5DT United Kingdom School of Computing Science and Engineering University of Salford Salford Greater ManchesterM5 4WT United Kingdom

Underwater acoustic sensor networks (UANs) have emerged as a promising technology recently, which can be applied in many areas such as military and civil, where the communication between devices is crucial and challenging owing to the unique characteristics of underwater acoustic-based environment, such as high latency and low bandwidth. In this paper, context awareness is applied to the design of an underwater communication approach, called context-aware communication approach for a UAN (CACA-UAN), which aims to improve the overall performance of the underwater communication. According to the results, the proposed CACA-UAN can increase the efficiency and reliability of the underwater communication system. © Copyright 2018 Inderscience Enterprises Ltd.

关键词： Efficiency