检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Hering, Alessa Hansen, Lasse Mok, Tony C.W. Chung, Albert C.S. Siebert, Hanna Häger, Stephanie Lange, Annkristin Kuckertz, Sven Heldmann, Stefan Shao, Wei Vesal, Sulaiman Rusu, Mirabela Sonn, Geoffrey Estienne, Théo Vakalopoulou, Maria Han, Luyi Huang, Yunzhi Yap, Pew-Thian Brudfors, Mikael Balbastre, Yaël Joutard, Samuel Modat, Marc Lifshitz, Gal Raviv, Dan Lv, Jinxin Li, Qiang Jaouen, Vincent Visvikis, Dimitris Fourcade, Constance Rubeaux, Mathieu Pan, Wentao Xu, Zhe Jian, Bailiang De Benetti, Francesca Wodzinski, Marek Gunnarsson, Niklas Sjölund, Jens Grzech, Daniel Qiu, Huaqi Li, Zeju Thorley, Alexander Duan, Jinming Großbröhmer, Christoph Hoopes, Andrew Reinertsen, Ingerid Xiao, Yiming Landman, Bennett Huo, Yuankai Murphy, Keelin Lessmann, Nikolas van Ginneken, Bram Dalca, Adrian V. Heinrich, Mattias P. Institute of Medical Informatics Universität zu Lübeck Ratzeburger Allee 160 Lübeck23562 Germany Fraunhofer MEVIS Institute for Digital Medicine Lübeck23562 Germany Department of Radiology and Nuclear Medicine Radboud University Medical Center GA Nijmegen6525 Netherlands The Institute of Medical Informatics Universität zu Lübeck Lübeck23562 Germany The Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong The Fraunhofer MEVIS Institute for Digital Medicine Lübeck23562 Germany The Department of Radiology Stanford University StanfordCA94305 United States The Department of Urology Stanford University StanfordCA94305 United States The Université Paris-Saclay CentraleSupélec Mathématiques et Informatique pour la Complexité et les Systèmes Inria Saclay Gif-sur-Yvette 91190 France Université Paris-Saclay Institut Gustave Roussy Inserm Radiothérapie Moléculaire et Innovation Thérapeutique Villejuif94800 France The Université Paris-Saclay CentraleSupélec Mathématiques et Informatique pour la Complexité et les Systèmes Inria Saclay Gif-sur-Yvette91190 France The Department of Radiology and Nuclear Medicine Radboud University Medical Center Nijmegen6525 GA Netherlands The School of Automation Nanjing University of Information Science and Technology Nanjing210044 China The School of Biomedical Engineering and Imaging Sciences King’s College London London United Kingdom The Athinoula A. Martinos Center for Biomedical Imaging Massachusetts General Hospital United States Harvard Medical School Boston United States The King’s College London United Kingdom The Tel Aviv University The Britton Chance Center for Biomedical Photonics Wuhan National Laboratory for Optoelectronics-Huazhong University of Science and Technology Hubei Wuhan430074 China MoE Key Laboratory for Biomedical Photonics Collaborative Innovation Center for Biomedical Engineering School of Engineering Sciences Huazhong University of Sci

Image registration is a fundamental medical image analysis task, and a wide variety of approaches have been proposed. However, only a few studies have comprehensively compared medical image registration approaches on a wide range of clinically relevant tasks. This limits the development of registration methods, the adoption of research advances into practice, and a fair benchmark across competing approaches. The Learn2Reg challenge addresses these limitations by providing a multi-task medical image registration data set for comprehensive characterisation of deformable registration algorithms. A continuous evaluation will be possible at https://***. Learn2Reg covers a wide range of anatomies (brain, abdomen, and thorax), modalities (ultrasound, CT, MR), availability of annotations, as well as intra- and inter-patient registration evaluation. We established an easily accessible framework for training and validation of 3D registration methods, which enabled the compilation of results of over 65 individual method submissions from more than 20 unique teams. We used a complementary set of metrics, including robustness, accuracy, plausibility, and runtime, enabling unique insight into the current state-of-the-art of medical image registration. This paper describes datasets, tasks, evaluation methods and results of the challenge, as well as results of further analysis of transferability to new datasets, the importance of label supervision, and resulting bias. While no single approach worked best across all tasks, many methodological aspects could be identified that push the performance of medical image registration to new state-of-the-art performance. Furthermore, we demystified the common belief that conventional registration methods have to be much slower than deep-learning-based methods. © 2021, CC BY.

关键词： Image registration

来源：评论

学校读者我要写书评

暂无评论

MIMAMO Net: Integrating micro- and macro-motion for video emotion recognition

arXiv

引用

arXiv 2019年

作者： Deng, Didan Chen, Zhaokang Zhou, Yuqian Shi, Bertram Neuromorphic Interactive System Laboratory Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Kowloon Hong Kong Image Formation and Processing Group University of Illinois at Urbana-Champaign ChampaignIL United States

Spatial-temporal feature learning is of vital importance for video emotion recognition. Previous deep network structures often focused on macro-motion which extends over long time scales, e.g., on the order of seconds. We believe integrating structures capturing information about both micro- and macro-motion will benefit emotion prediction, because human perceive both micro- and macro-expressions. In this paper, we propose to combine micro- and macro-motion features to improve video emotion recognition with a two-stream recurrent network, named MIMAMO (Micro-Macro-Motion) Net. Specifically, smaller and shorter micro-motions are analyzed by a two-stream network, while larger and more sustained macro-motions can be well captured by a subsequent recurrent network. Assigning specific interpretations to the roles of different parts of the network enables us to make choice of parameters based on prior knowledge: choices that turn out to be optimal. One of the important innovations in our model is the use of interframe phase differences rather than optical flow as input to the temporal stream. Compared with the optical flow, phase differences require less computation and are more robust to illumination changes. Our proposed network achieves state of the art performance on two video emotion datasets, the OMG emotion dataset and the Aff-Wild dataset. The most significant gains are for arousal prediction, for which motion information is intuitively more informative. Source code is available at https://***/wtomin/MIMAMO-Net. Copyright © 2019, The Authors. All rights reserved.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Online Estimation of Rotor Temperature in Induction Motors Based on Parameter Identification

Online Estimation of Rotor Temperature in Induction Motors B...

引用

IEEE Energy Conversion Congress and Exposition

作者： Haisen Zhao Hassan H. Eldeeb Jinyu Wang Yang Zhan Guorui Xu Osama A. Mohammed State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources North China Electric Power University (NCEPU) Beijing China Department of Electrical and Computer Engineering Florida International University Miami FL USA

This study proposes an in-service induction machine (IM) rotor's temperature estimation method. The proposed method is based on the noninvasive measurements of current and potential sensors. First of all, using the rotor slot harmonics superimposed on the stator's current, the rotor speed is extracted. Secondly, the first few cycles of the IM's starting process is used to mimic the locked-rotor test condition while the IM is in-service. Using the aforementioned analogy, the initial value of the rotor's resistance is calculated directly. A merit of the proposed method is that it requires significantly less time to estimate the rotor's resistance compared to the traditional methods in literature, and convergence speed of the parameter identification can be improved significantly. Consequently, the rotor resistance can be on-line identified via the Model Reference Adaptive (MRA) method. Thereby, the rotor temperature is calculated by the resistance-temperature linear relation of metals. Experimental validation is performed on a 5.5kW motor, and the estimated results agreed with the tested ones.

关键词： Rotors Resistance Harmonic analysis Stators Temperature sensors Induction motors Parameter estimation

来源：评论

学校读者我要写书评

暂无评论

Machine learning for resource management in cellular and IoT networks: Potentials, current solutions, and open challenges

arXiv

引用

arXiv 2019年

作者： Hussain, Fatima Hassan, Syed Ali Hussain, Rasheed Hossain, Ekram Royal Bank of Canada Toronto Canada Islamabad Pakistan Networks and Blockchain Laboratory Institute of Information Security and Cyber-Physical System Innopolis University Innopolis Russia Department of Electrical and Computer Engineering University of Manitoba Winnipeg Canada

Internet-of-Things (IoT) refers to a massively heterogeneous network formed through smart devices connected to the Internet. In the wake of disruptive IoT with huge amount and variety of data, Machine Learning (ML) and Deep Learning (DL) mechanisms will play pivotal role to bring intelligence to the IoT networks. Among other aspects, ML and DL can play an essential role in addressing the challenges of resource management in large-scale IoT networks. In this article, we conduct a systematic and in-depth survey of the ML- and DL-based resource management mechanisms in cellular wireless and IoT networks. We start with the challenges of resource management in cellular IoT and low-power IoT networks, review the traditional resource management mechanisms for IoT networks, and motivate the use of ML and DL techniques for resource management in these networks. Then, we provide a comprehensive survey of the existing ML- and DL-based resource allocation techniques in wireless IoT networks and also techniques specifically designed for HetNets, MIMO and D2D communications, and NOMA networks. To this end, we also identify the future research directions in using ML and DL for resource allocation and management in IoT networks. Copyright © 2019, The Authors. All rights reserved.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Claimed detection of PH3 in the clouds of Venus is consistent with mesospheric SO2

arXiv

引用

arXiv 2021年

作者： Lincowski, Andrew P. Meadows, Victoria S. Crisp, David Akins, Alex B. Schwieterman, Edward W. Arney, Giada N. Wong, Michael L. Steffes, Paul G. Parenteau, M. Niki Domagal-Goldman, Shawn Department of Astronomy and Astrobiology Program University of Washington Box 351580 SeattleWA98195 United States NASA Nexus for Exoplanet System Science Virtual Planetary Laboratory Team University of Washington Box 351580 SeattleWA98195 United States Jet Propulsion Laboratory California Institute of Technology Earth and Space Sciences Division PasadenaCA91011 United States Jet Propulsion Laboratory California Institute of Technology Instruments Division PasadenaCA91011 United States Department of Earth and Planetary Sciences University of California RiversideCA92521 United States Blue Marble Space Institute of Science SeattleWA United States NASA/Goddard Space Flight Center GreenbeltMD20771 United States School of Electrical and Computer Engineering Georgia Institute of Technology AtlantaGA30332-0250 United States MS 239-4 Space Science Division NASA Ames Research Center Moffett FieldCA United States

The observation of a 266.94 GHz feature in the Venus spectrum has been attributed to PH3 in the Venus clouds, suggesting unexpected geological, chemical or even biological processes. Since both PH3 and SO2 are spectrally active near 266.94 GHz, the contribution to this line from SO2 must be determined before it can be attributed, in whole or part, to PH3. An undetected SO2 reference line, interpreted as an unexpectedly low SO2 abundance, suggested that the 266.94 GHz feature could be attributed primarily to PH3. However, the low SO2 and the inference that PH3 was in the cloud deck posed an apparent contradiction. Here we use a radiative transfer model to analyze the PH3 discovery, and explore the detectability of different vertical distributions of PH3 and SO2. We find that the 266.94 GHz line does not originate in the clouds, but above 80 km in the Venus mesosphere. This level of line formation is inconsistent with chemical modeling that assumes generation of PH3 in the Venus clouds. Given the extremely short chemical lifetime of PH3 in the Venus mesosphere, an implausibly high source flux would be needed to maintain the observed value of 20±10 ppb. We find that typical Venus SO2 vertical distributions and abundances fit the JCMT 266.94 GHz feature, and the resulting SO2 reference line at 267.54 GHz would have remained undetectable in the ALMA data due to line dilution. We conclude that nominal mesospheric SO2 is a more plausible explanation for the JCMT and ALMA data than PH3 © 2021, CC BY.

关键词： Radiative transfer

来源：评论

学校读者我要写书评

暂无评论

arXiv

引用

arXiv 2020年

作者： Li, Jiashuo Zhou, Sili Wei, Wendong Qi, Jianchuan Li, Yumeng Chen, Bin Zhang, Ning Guan, Dabo Qian, Haoqi Wu, Xiaohui Miao, Jiawen Chen, Long Liang, Sai Feng, Kuishuang Institute of Blue and Green Development Shandong University Weihai264209 State Key Laboratory of Coal Combustion School of Energy and Power Engineering Huazhong University of Science and Technology Wuhan430074 China School of International and Public Affairs Shanghai Jiao Tong University Shanghai200030 China State Key Joint Laboratory of Environment Simulation and Pollution Control School of Environment Beijing Normal University Beijing100875 China Laboratory of Anthropogenic Systems Ecology College of Engineering Peking University Beijing100871 China Department of Earth System Science Tsinghua University Beijing100871 China Institute for Global Public Policy Fudan University Shanghai200433 China School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai200093 China Key Laboratory of Geographic Information Science Ministry of Education School of Geographic Sciences East China Normal University Shanghai200241 China

China has implemented retrofitting measures in coal-fired power plants (CFPPs) to reduce air pollution through small unit shutdown (SUS), the installation of air pollution control devices (APCDs) and power generation efficiency (PGE) improvement. The reductions in highly toxic Hg emissions and their related health impacts by these measures have not been well studied. To refine mitigation options, we evaluated the health benefits of reduced Hg emissions via retrofitting measures during China's 12th Five-Year Plan by combining plant-level Hg emission inventories with the China Hg Risk Source-Tracking Model. We found that the measures reduced Hg emissions by 23.5 tons (approximately 1/5 of that from CFPPs in 2010), preventing 0.0021 points of per-foetus intelligence quotient (IQ) decrements and 114 deaths from fatal heart attacks. These benefits were dominated by CFPP shutdowns and APCD installations. Provincial health benefits were largely attributable to Hg reductions in other regions. We also demonstrated the necessity of considering human health impacts, rather than just Hg emission reductions, in selecting Hg control devices. This study also suggests that Hg control strategies should consider various factors, such as CFPP locations, population densities and trade-offs between reductions of total Hg (THg) and Hg2+. Copyright © 2020, The Authors. All rights reserved.

关键词： Fossil fuel power plants

来源：评论

学校读者我要写书评

暂无评论

Frontoparietal connectivity neurofeedback training for promotion of working memory: An fNIRS study in healthy male participants

arXiv

引用

arXiv 2020年

作者： Xia, Meiyun Xu, Pengfei Yang, Yuanbin Jiang, Wenyu Wang, Zehua Gu, Xiaolei Yang, Mingxi Li, Deyu Li, Shuyu Dong, Guijun Wang, Ling Wang, Daifa School of Biological Science and Medical Engineering Beihang University Beijing100083 China College of Computer Science Sichuan Normal University Chengdu610101 China Beijing Advanced Innovation Center for Biomedical Engineering Beihang University Beijing100083 China State Key Laboratory of Virtual Reality Technology and System Beihang University Beijing100083 China Department of Rehabilitation Medicine Wangjing Hospital China Academy of Chinese Medical Sciences Beijing100102 China Department of Neurological Rehabilitation Guangxi Jiangbin Hospital Nanning530021 China School of Sports and Health Shandong Sport University Jinan250102 China

Neurofeedback cognitive training is a promising tool used to promote cognitive functions effectively and efficiently. In this study, we investigated a novel functional near-infrared spectroscopy (fNIRS)based frontoparietal functional connectivity (FC) neurofeedback training paradigm related to working memory, involving healthy adults. Compared with conventional cognitive training studies, we chose the frontoparietal network, a key brain region for cognitive function modulation, as neurofeedback, yielding a strong targeting effect. In the experiment, 10 participants (test group) received three cognitive training sessions of 15 min using fNIRS-based frontoparietal FC as neurofeedback, and another 10 participants served as the control group. Frontoparietal FC was significantly increased in the test group (p = 0.03), and the cognitive functions (memory and attention) were significantly promoted compared with the control group (accuracy of 3-back test: p = 0.0005, reaction time of 3-back test: p = 0.0009). After additional validations on long-term training effect and on different patient populations, the proposed method exhibited considerable potential to be developed as a fast, effective, and widespread training approach for cognitive function enhancement. Copyright © 2020, The Authors. All rights reserved.

关键词： Brain

来源：评论

学校读者我要写书评

暂无评论

Discriminative Marginalized Least Squares Regression for Hyperspectral Image Classification

Discriminative Marginalized Least Squares Regression for Hyp...

引用

Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS

作者： Yuxiang Zhang Wei Li Qian Du Xu Sun College of Information Science & Technology Beijing University of Chemical Technology School of Information and Electronics Beijing Institute of Technology Beijing China Department of Electrical and Computer Engineering Mississippi State University MS USA Key laboratory of Digital Earth Science Institute of Remote Sensing and Digital Earth Beijing China

ISBN: (纸本)9781728152950

Least squares regression (LSR)-based classifiers are rarely used for hyperspectral image classification. The reason is that their limited projections result in the loss of much discriminant information, and they focus only on exactly fitting samples to the label matrix while ignoring the problem of label overfitting. To solve this issue, discriminative marginalized least squares regression (DMLSR) is proposed to learn a more discriminative projection matrix with consideration of class separability and data reconstruction ability simultaneously. In the proposed method, Fisher criterion is employed to avoid the overfitting problem and enhance class separability; furthermore, a data-reconstruction constraint is imposed to preserve more discriminant information on limited projections, thereby enhancing classification performance. Experimental results on two hyperspectral datasets demonstrate that the proposed method significantly outperforms some state-of-the-art classifiers.

关键词： Training Hyperspectral imaging Image classification Image reconstruction Support vector machines Fitting

来源：评论

学校读者我要写书评

暂无评论

Image reconstruction with low-rankness and self-consistency of k-space data in parallel MRI

arXiv

引用

arXiv 2019年

作者： Zhang, Xinlin Guo, Di Huang, Yiman Chen, Ying Wang, Liansheng Huang, Feng Qu, Xiaobo Department of Electronic Science Fujian Provincial Key Laboratory of Plasma and Magnetic Resonance School of Electronic Science and Engineering National Model Microelectronics College Xiamen University Xiamen361005 China School of Computer and Information Engineering Fujian Provincial University Key Laboratory of Internet of Things Application Technology Xiamen University of Technology Xiamen361024 China Department of Computer Science School of Information Science and Engineering Xiamen University Xiamen361005 China Neusoft Medical System Shanghai200241 China

Parallel magnetic resonance imaging has served as an effective and widely adopted technique for accelerating scans. The advent of sparse sampling offers aggressive acceleration, allowing flexible sampling and better reconstruction. Nevertheless, faithfully reconstructing the image from limited data still poses a challenging task. Recent low-rank reconstruction methods exhibit superiority in providing a high-quality image. However, none of them employ the routinely acquired calibration data for improving image quality in parallel magnetic resonance imaging. In this work, an image reconstruction approach named STDLR-SPIRiT was proposed to explore the simultaneous two-directional low-rankness (STDLR) in the k-space data and to mine the data correlation from multiple receiver coils with the iterative self-consistent parallel imaging reconstruction (SPIRiT). The reconstruction problem was then solved with a singular value decomposition-free numerical algorithm. Experimental results of phantom and brain imaging data show that the proposed method outperforms the state-of-the-art methods in terms of suppressing artifacts and achieving the lowest error. Moreover, the proposed method exhibits robust reconstruction even when the auto-calibration signals are limited in parallel imaging. Overall the proposed method can be exploited to achieve better image quality for accelerated parallel magnetic resonance imaging. Copyright © 2019, The Authors. All rights reserved.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Study on Subsynchronous Resonance Damping Control for Series-Compensated DFIG-Based Wind Farm

Study on Subsynchronous Resonance Damping Control for Series...

引用

Sustainable Power and Energy Conference (iSPEC)

作者： Chao Luo Qi Guo Xiangning Xiao A.M Gole Mengjun Liao State Key Laboratory of HVDC Electric Power Research Institute State Key Laboratory for Alternate Electrical Power System with Renewable Energy Sources North China Electric Power University Beijing China Electrical and Computer Engineering Department University of Manitoba Winnipeg Canada

ISBN: (纸本)9781728149318

Subsynchronous Resonance (SSR) is a potential threat for long distance power transmission from doubly fed induction generator (DFIG) based wind farms with fixed series compensation (FSC). In this paper, subsynchronous resonance damping control (SSRDC) strategy based on shunt voltage source converter is proposed. Taking account of different series compensation levels and wind speeds, several potential inputs to the SSRDC are investigated. SSRDC control parameters are determined via root locus techniques to ensure the system stability of subsynchronous modes. Considering implementation feasibility in practical project and stability of supersynchronous modes, an enhanced SSRDC is proposed. Impact of transmission line and DFIG parameters and the reactive power compensation to the mitigation effect is investigated. Time domain simulation using PSCAD/EMTDC are carried out to validate the effectiveness of the SSRDC.

关键词： Doubly fed induction generator (DFIG) fixed series capacitor compensation (FSC) Subsynchronous Resonance (SSR) voltage source converter (VSC) Subsynchronous Resonance damping controller Wind farms subsynchronous resonance damped control system stability power transmission reactive compensation series compensation double-fed induction generator TIME-DOMAIN Transmission Lines Compensation depth

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：