检索结果-内蒙古大学图书馆

Development and Validation of a Prognostic Risk Score System for COVID-19 Inpatients:A Multi-Center Retrospective Study in China

学校读者我要写书评

暂无评论

engineering 2022年第1期8卷 116-121页

作者： Ye Yuan Chuan Sun Xiuchuan Tang Cheng Cheng Laurent Mombaerts Maolin Wang Tao Hu Chenyu Sun Yuqi Guo Xiuting Li Hui Xu Tongxin Ren Yang Xiao Yaru Xiao Hongling Zhu Honghan Wu Kezhi Li Chuming Chen Yingxia Liu Zhichao Liang Zhiguo Cao Hai-Tao Zhang Ioannis Ch.Paschaldis Quanying Liu Jorge Goncalves Qiang Zhong Li Yan School of Artificial Intelligence and Automation Huazhong University of Science and TechnologyWuhan 430074China School of Mechanical Science and Engineering Huazhong University of Science and TechnologyWuhan 430074China Luxembourg Centre for Systems Biomedicine University of LuxembourgBelval L-4367Luxembourg Department of Plant Sciences University of CambridgeCambridge CB21TNUK Department of Emergency Tongji HospitalTongji Medical CollegeHuazhong University of Science and TechnologyWuhan 430030China AMITA Health Saint Joseph Hospital Chicago ChicagoIL 60657USA Department of Anesthesiology Tongji HospitalTongji Medical CollegeHuazhong University of Science and TechnologyWuhan 430030China Huazhong University of Science and Technology-Wuxi Research Institute Wuxi 214174China Division of Cardiology Department of Internal MedicineTongji HospitalTongji Medical CollegeHuazhong University of Science and TechnologyWuhan 430030China Institute of Health Informatics University College LondonLondon NW12DAUK Department of Biomedical Engineering Southern University of Science and TechnologyShenzhen 518055China Department of Infectious Diseases Shenzhen Key Laboratory of Pathogenic Microbiology and ImmunologyNational Clinical Research Center for Infectious DiseaseThe Third People’s Hospital of Shenzhen(Second Hospital Affiliated with the Southern University of Science and Technology)Shenzhen 518055China Department of Electrical and Computer Engineering&Division of Systems Engineering&Department of Biomedical Engineering Boston UniversityBostonMA 02215USA

Coronavirus disease 2019(COVID-19)has become a worldwide *** patients of COVID-19 suffer from a high mortality rate,motivating the development of convenient and practical methods that allow clinicians to promptly identify high-risk ***,we have developed a risk score using clinical data from 1479 inpatients admitted to Tongji Hospital,Wuhan,China(development cohort)and externally validated with data from two other centers:141 inpatients from Jinyintan Hospital,Wuhan,China(validation cohort 1)and 432 inpatients from The Third People’s Hospital of Shenzhen,Shenzhen,China(validation cohort 2).The risk score is based on three biomarkers that are readily available in routine blood samples and can easily be translated into a probability of *** risk score can predict the mortality of individual patients more than 12 d in advance with more than 90%accuracy across all ***,the Kaplan-Meier score shows that patients can be clearly differentiated upon admission as low,intermediate,or high risk,with an area under the curve(AUC)score of *** summary,a simple risk score has been validated to predict death in patients infected with severe acute respiratory syndrome coronavirus 2(SARS-CoV-2);it has also been validated in independent cohorts.

关键词： COVID-19 Risk score Mortality risk prediction

Optimal Sizing and Pricing of Renewable Power to Ammonia systems Considering the Limited Flexibility of Ammonia Synthesis

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Yu, Zhipeng Lin, Jin Liu, Feng Li, Jiarong Zhao, Yuxuan Song, Yonghua Song, Yanhua Zhang, XinZhen The State Key Laboratory of Control and Simulation of Power Systems and Generation Equipment Department of Electrical Engineering Tsinghua University Beijing100087 China Sichuan Energy Internet Reasearch Institute Tsinghua University Chengdu610213 China The Department of Electrical and Computer Engineering University of Macau 999078 China The Department of Electrical Engineering Tsinghua University Beijing100087 China Shenzhen Edo Renewable Co. Ltd Shenzhen518067 China

Converting renewable energy into ammonia has been recognized as a promising way to realize "green hydrogen substitution" in the chemical industry. However, renewable power to ammonia (RePtA) requires an essential investment in facilities to provide a buffer against the strong volatility of renewable energy and the limited flexibility of ammonia synthesis, which involves the three main stakeholders, namely, power, hydrogen, and ammonia. Therefore, the sizing and pricing of RePtA play a core role in balancing the interest demands of investors. This paper proposes an optimal sizing and pricing method for RePtA system planning. First, power to ammonia (P2A) is modeled as a flexible load, especially considering the limited flexibility of ammonia synthesis, which has been verified using real dynamic regulation data. Second, the multi-investor economic (MIE) model is established considering both external and internal trading modes. Then, a two-stage decomposed sizing and pricing method is proposed to solve the problem caused by the strong coupling of planning, operation, and trading, and information gap decision theory (IGDT) method is utilized to handle the uncertainty of renewable generation. Finally, real data from a real-life system in Inner Mongolia are utilized to verify the proposed approach. The results show that the system proposed has a yield of 8.15%. Copyright © 2022, The Authors. All rights reserved.

关键词： Costs

State Derivative Normalization for Continuous-Time Deep Neural Networks

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Weigand, Jonas Beintema, Gerben I. Ulmen, Jonas Görges, Daniel Tóth, Roland Schoukens, Maarten Ruskowski, Martin Chair of Machine Tools and Control Systems RPTU Kaiserslautern The German Research Center for Artificial Intelligence Kaiserslautern Germany Group The Department of Electrical Engineering Eindhoven University of Technology Netherlands The Systems and Control Laboratory The Institute for Computer Science and Control Budapest Hungary Institute for Electromobility RPTU Kaiserslautern Germany

The importance of proper data normalization for deep neural networks is well known. However, in continuous-time state-space model estimation, it has been observed that improper normalization of either the hidden state or hidden state derivative of the model estimate, or even of the time interval can lead to numerical and optimization challenges with deep learning based methods. This results in a reduced model quality. In this contribution, we show that these three normalization tasks are inherently coupled. Due to the existence of this coupling, we propose a solution to all three normalization challenges by introducing a normalization constant at the state derivative level. We show that the appropriate choice of the normalization constant is related to the dynamics of the to-be-identified system and we derive multiple methods of obtaining an effective normalization constant. We compare and discuss all the normalization strategies on a benchmark problem based on experimental data from a cascaded tanks system and compare our results with other methods of the identification literature. © 2024, CC BY-SA.

关键词： Ordinary differential equations

Approaches on multi-sensor fusion under time-evolving conditions

学校读者我要写书评

暂无评论

Approaches on multi-sensor fusion under time-evolving condit...

IEEE International Symposium on Intelligent Control (ISIC)

作者： R.C. Luo W.S. Yang M.-H. Lin Robotics and Intelligent Systems Laboratory Electrical and Computer Engineering Department North Carolina State University Raleigh NC USA Dept. of Electr. & Comput. Eng. North Carolina State Univ. Raleigh NC USA

A paradigm for optimum estimation of fused multiple sensor data is developed in order to best use the sensor information in the time evolving environment. Two basic approaches have been developed: dynamic moving quadratic curve fitting and weighted least mean square error. These two approaches are shown to be advantageous in terms of accuracy, speed, and versatility. The theoretical frameworks presented are supported by sets of simulation data.< >

关键词： Sensor fusion Robot sensing systems Intelligent robots Intelligent sensors Sensor systems Uncertainty Military aircraft Machine intelligence Mobile robots Sensor phenomena and characterization

Mixture Gaussian Distribution-Based Collaborative Reinforcement Learning for 3D UAV Localization Optimization Against Jamming Attacks

学校读者我要写书评

暂无评论

Mixture Gaussian Distribution-Based Collaborative Reinforcem...

IEEE Conference on Global Communications (GLOBECOM)

作者： Yujiao Zhu Mingzhe Chen Sihua Wang Yuchen Liu Gaolei Li Changchuan Yin Tony Q.S. Quek Beijing Laboratory of Advanced Information Network Beijing University of Posts and Telecommunications Beijing China Information Systems Technology and Design Pillar Singapore University of Technology and Design Singapore Department of Electrical and Computer Engineering and Institute for Data Science and Computing University of Miami Coral Gables FL USA Department of Computer Science North Carolina State University Raleigh NC USA School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University China

ISBN: (数字)9798350351255

ISBN: (纸本)9798350351262

In this paper, the optimization of unmanned aerial vehicle (UAV) localization under jamming attacks is studied. In the considered network, a base station (BS) collaborates with an active UAV to localize a target UAV. During this positioning process, a jamming UAV transmits discontinuous signals to passive UAVs to interfere the distance information measurement. To localize the target UAV under jamming attacks, the BS jointly use two localization methods: 1) generative adversarial network (GAN)-based positioning method and 2) time difference of arrival (TDOA)-based positioning method. Since GAN-based positioning method cannot defense in a strong jamming signal while TDOA-based positioning method may consume more energy and sacrifice localization accuracy, the BS must select an appropriate positioning method (GAN-based or TDOA-based methods) and four distance measurement information of passive UAVs to estimate the position of the target UAV. This problem is formulated as an optimization problem whose goal is to minimize the positioning error between the estimated and the ground truth positions of the target UAV while considering jamming attacks and the trajectory of passive UAVs. To solve this problem, we propose a mixture Gaussian distribution model-based collaborative reinforcement learning (RL) method which enables the active UAV to determine its transmit power and trajectory, and enables the BS to select the most appropriate subsets of distance measurement information and the optimal positioning method according to the movement of passive UAVs and the unknown jamming attack pattern of the jamming UAV. Simulation results show the proposed method can reduce the positioning error of the target UAV by up to 36.5% compared to the method that does not consider the GAN-based positioning method.

关键词： Location awareness Simulation Collaboration Reinforcement learning Gaussian distribution Autonomous aerial vehicles Distance measurement Trajectory Jamming Optimization

Primal-dual Accelerated Mirror-Descent Method for Constrained Bilinear Saddle-Point Problems

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Weijian Zeng, Xianlin Pavel, Lacra The Department of Electrical and Computer Engineering University of Toronto TorontoONM5S 3G4 Canada The Key Laboratory of Intelligent Control and Decision of Complex Systems School of Automation Beijing Institute of Technology Beijing100081 China

We develop a first-order accelerated algorithm for a class of constrained bilinear saddle-point problems with applications to network systems. The algorithm is a modified time-varying primal-dual version of an accelerated mirror-descent dynamics. It deals with constraints such as simplices and convex set constraints effectively, and converges with a rate of O(1/t2). Furthermore, we employ the acceleration scheme to constrained distributed optimization and bilinear zero-sum games, and obtain two variants of distributed accelerated algorithms. Copyright © 2024, The Authors. All rights reserved.

关键词： Mirrors

Visual pattern recognition using morphological methods

学校读者我要写书评

暂无评论

Visual pattern recognition using morphological methods

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： I.N.M. Papadakis J.G. Reisman S.C.A. Thomopoulos Dept. of Electr. & Comput. Eng. Pennsylvania State Univ. University Park PA USA Decision and Control Systems Laboratory Department of Electrical and Computer Engineering Pennsylvania State University University Park PA USA

An effective method for visual pattern recognition using morphological techniques is presented. It is shown that it can be successfully used for the recognition of deformed letters. The method extracts morphological information by the successive dilation of an idealized letter set. At each stage a properly defined similarity index is computed. The maximum values of the similarity index for each stored letter are compared and are used for the classification decision. Classification results are presented for a set of deformed capital English letters with a realistic level of deformation. Skeletonization of the deformed pattern is shown to improve the performance of the classification method. The described method can be easily implemented using a parallel architecture.< >

关键词： Pattern recognition Artificial neural networks Feature extraction Clocks Control systems Laboratories Data mining parallel architectures Character recognition Tiles

Low latency optical-based mode tracking with machine learning deployed on FPGAs on a tokamak

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wei, Yumou Forelli, Ryan F. Hansen, Chris Levesque, Jeffrey P. Tran, Nhan Agar, Joshua C. Di Guglielmo, Giuseppe Mauel, Michael E. Navratil, Gerald A. Department of Applied Physics and Applied Mathematics Columbia University New YorkNY10027 United States Real-time Processing Systems Division Fermi National Accelerator Laboratory BataviaIL60510 United States Department of Electrical and Computer Engineering Lehigh University BethlehemPA18015 United States Department of Electrical and Computer Engineering Northwestern University EvanstonIL60208 United States Department of Mechanical Engineering and Mechanics Drexel University PhiladelphiaPA19104 United States Microelectronics Division Fermi National Accelerator Laboratory BataviaIL60510 United States

Active feedback control in magnetic confinement fusion devices is desirable to mitigate plasma instabilities and enable robust operation. Optical high-speed cameras provide a powerful, non-invasive diagnostic and can be suitable for these applications. In this study, we process high-speed camera data, at rates exceeding 100 kfps, on in situ field-programmable gate array (FPGA) hardware to track magnetohydrodynamic (MHD) mode evolution and generate control signals in real-time. Our system utilizes a convolutional neural network (CNN) model which predicts the n=1 MHD mode amplitude and phase using camera images with better accuracy than other tested non-deep-learning-based methods. By implementing this model directly within the standard FPGA readout hardware of the high-speed camera diagnostic, our mode tracking system achieves a total trigger-to-output latency of 17.6 µs and a throughput of up to 120 kfps. This study at the High Beta Tokamak-Extended Pulse (HBT-EP) experiment demonstrates an FPGA-based high-speed camera data acquisition and processing system, enabling application in real-time machine-learning-based tokamak diagnostic and control as well as potential applications in other scientific domains. Copyright © 2023, The Authors. All rights reserved.

关键词： Tokamak devices

Integrated Web enabled control system design methodology

学校读者我要写书评

暂无评论

Integrated Web enabled control system design methodology

IEEE International Workshop on Factory Communication systems (WFCS)

作者： A.P. Kalogeras A. Prayati C. Schwab M. Tangermann L. Ferrarini G. Papadopoulos Industrial Systems Institute Rio-Patras Greece Applied Electronics Laboratory Department of Electrical and Computer Engineering University of Patras Rio-Patras Greece Center Distributed Systems University of Magdeburg Magdeburg Germany Dip. di Elettronica e Informazione Politecnico di Milano Milan Italy

The ubiquity of the Internet infrastructure has revolutionized the industrial enterprise environment enabling the provision of advanced services, such as Web enabled configuration, maintenance and management of the industrial manufacturing processes. Thus the trend towards distributed systems is further enhanced. In order to best exploit the Web infrastructure in the industrial environment an integrated control system design methodology is needed. This paper presents a proposed architecture in the industrial environment comprising function blocks for code distribution, a special model for devices, an integrated environment for the Web enabled functionalities as well as an associated methodology.

关键词： Control systems electrical equipment industry Communication industry computer industry Manufacturing industries Electronics industry Environmental management Industrial control Application software Information technology