检索结果-内蒙古大学图书馆

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

来源：评论

学校读者我要写书评

暂无评论

A Game Theoretic Approach to Design a Resilient Controller For a Nonlinear Discrete System

引用

IFAC-PapersOnLine 2017年第1期50卷 387-392页

作者： Salehghaffari H. Krishnamurthy P. Khorrami F. Control/Robotics Research Laboratory (CRRL) Department of Electrical and Computer Engineering NYU Tandon School of EngineeringNY 11201 United States

In this paper, the problem of designing a cyber-resilient controller is studied for a class of nonlinear discrete systems subject to actuator attacks. We develop a coupled control design approach, which incorporates interaction between the intrusion detection system (IDS) and the attacker, with the controller design in the physical layer. In the considered cyber-attack scenario, the attacker attempts to first bypass the IDS to spoof the system actuator and then deteriorate the controller performance in the physical layer. The optimal attack strategy to deceive the IDS is obtained based on a zero-sum game in the detection layer. In the physical layer, it is assumed that the system has a secure compensator along with the actuator to deal with the injected attack values. Therefore, the controller and the compensator are designed based on the results of the game in the detection layer, and stochastic stability analysis and Lyapunov function methods are used to prove boundedness of the system state in the probabilistic sense. Finally, through numerical analysis of a representative example, the proposed design procedure is illustrated and its efficacy in maintaining robust stability of the cyber-physical system under actuator attacks is demonstrated. © 2017

关键词： attack strategy control systems security Cyber-physical system resilient control stochastic stability zero-sum game

来源：评论

学校读者我要写书评

暂无评论

Efficient Inverse Kinematics for Redundant Manipulators with Collision Avoidance in Dynamic Scenes

Efficient Inverse Kinematics for Redundant Manipulators with...

引用

IEEE International Conference on robotics and Biomimetics

作者： Liangliang Zhao Jingdong Zhao Hong Liu Dinesh Manocha Department of Computer Science and Electrical & Computer Engineering University of Maryland at College Park MD USA State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin China

ISBN: (纸本)9781728103785;9781728103778

We present a novel iterative algorithm for inverse kinematics of redundant manipulators in dynamic environments. Our approach uses an iterative approach to generate valid configurations and selects an inverse kinematics solution using a rank-based selection strategy. To avoid the moving obstacles, we combine our inverse kinematics method with a collision avoidance scheme. We highlight the performance of our algorithm on different high DOF manipulators in a dynamic scene.

关键词： Kinematics Manipulator dynamics Collision avoidance Iterative methods End effectors Trajectory

来源：评论

学校读者我要写书评

暂无评论

Deep transfer learning based downlink channel prediction for FDD massive MIMO systems

arXiv

引用

arXiv 2019年

作者： Yang, Yuwen Gao, Feifei Zhong, Zhimeng Ai, Bo Alkhateeb, Ahmed Department of Automation Tsinghua University Beijing100084 China Huawei Technologies Ltd. Shanghai210206 China State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University Beijing100044 China School of Electrical Computer and Energy Engineering Arizona State University TempeAZ85287 United States

—Artificial intelligence (AI) based downlink channel state information (CSI) prediction for frequency division duplexing (FDD) massive multiple-input multiple-output (MIMO) systems has attracted growing attention recently. However, existing works focus on the downlink CSI prediction for the users under a given environment and is hard to adapt to users in new environment especially when labeled data is limited. To address this issue, we formulate the downlink channel prediction as a deep transfer learning (DTL) problem, where each learning task aims to predict the downlink CSI from the uplink CSI for one single environment. Specifically, we develop the direct-transfer algorithm based on the fully-connected neural network architecture, where the network is trained on the data from all previous environments in the manner of classical deep learning and is then fine-tuned for new environments. To further improve the transfer efficiency, we propose the meta-learning algorithm that trains the network by alternating inner-task and across-task updates and then adapts to a new environment with a small number of labeled data. Simulation results show that the direct-transfer algorithm achieves better performance than the deep learning algorithm, which implies that the transfer learning benefits the downlink channel prediction in new environments. Moreover, the meta-learning algorithm significantly outperforms the direct-transfer algorithm in terms of both prediction accuracy and stability, which validates its effectiveness and superiority. Copyright © 2019, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Dynamic contextualization and comparison as the basis of biologically inspired action understanding

引用

Paladyn 2018年第1期9卷 19-59页

作者： Alkurdi, Laith Busch, Christian Peer, Angelika Department of Electrical Electronic and Computer Engineering Technische Universität München München Germany Department of Electrical Electronic and Computer Engineering Technische Universität München München Germany Bristol Robotics Laboratory Faculty of Environment and Technology Department of Engineering Design and Mathematics University of the West of England Bristol United Kingdom

People exhibit a robust ability to understand the actions of others around them. In this work, we identify two biologically inspired mechanisms that we hypothesize to be central in the function of action understanding. The first module is a contextual predictor of the observed action, given the goal-directed movement towards objects, and the actions that are allowed to be performed on the object. The second module is a kinematic trajectory parser that validates the previous prediction against a set of learned templates. We model both mechanisms and link them to the environment using the cognitive framework of Dynamic Field Theory and present our first steps into integrating the aforementioned modules into a consistent framework for the purpose of action understanding. The two modules and the combined architecture as a whole are experimentally validated using a recording of an actor performing a series of intentional actions testing the ability of the architecture to understand context and parse actions dynamically. Our initial qualitative results show that action understanding benefits from the combination of the two modules, while any module alone would be insufficient to resolve ambiguity in the perceived actions. © 2018 De Gruyter Open Ltd. All rights reserved.

关键词： Ability testing

来源：评论

学校读者我要写书评

暂无评论

Sleep Disorder Classification Method based on Logistic Regression with Apnea-ECG Dataset 2019

Sleep Disorder Classification Method based on Logistic Regre...

引用

2019 International Conference on Artificial Intelligence and Advanced Manufacturing, AIAM 2019

作者： Cai, Liangming Chen, Chunqiang Wang, Xiaoling Yang, Xiong Lin, Shurui Huang, Jiefeng Jiang, Jinping Datta, Rituparna Du, Min Jiang, Haiyan Zhu, Minchen Huang, Jingshan College of Physics and Information Engineering Fuzhou University Fuzhou China Zhicheng College University of South Alabama United States HaiXi Institutes Chinese Academy of Science Fuzhou China Zhicheng College Fuzhou University Fuzhou China Department of Respiratory Medicine First Affiliated Hospital of Fujian Medical University Fuzhou China College of Electrical Engineering and Automation Fuzhou University Fuzhou China School of Computing University of South Alabama Mobile United States Provincial Key Laboratory of Eco-industrial Green Technology Wuyi College Wuyishan China College of Mathematics and Computer Science Fuzhou University Fuzhou China Fuzhou University Fuzhou China University of South Alabama United States

ISBN: (纸本)9781450372022

Adequate sleep is significant for human to actively pursue daily activity. On the other hand, insomnia is directly proportional to aging and health deterioration. Sleep disorder classification is important for medical scientists as well as machine learning researchers. In the paper, we have developed a sleep disorder classification method for Electrocardiogram (ECG) data. The data set have two labels;sleep disorder or not, which can be categorized as binary output. As a result, logistic regression is used as classification technique. For initial experimentation, an existing data set is used. The data set consists of every 10 second data up to 6000 seconds for 35 patients. We have used 70% data for training, and 30% data for testing purpose. Our results from logistic regression show that the logistic regression method is efficient to detect sleep disorders. The prediction result is found to be 59%. The future research in this direction would be to take data from hospitals and use our developed algorithm for sleep disorder classification and prediction. © 2019 Association for Computing Machinery.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

Robust semi-global leader-following practical consensus of a group of linear systems with imperfect actuators

引用

Science China(Information Sciences) 2017年第7期60卷 195-206页

作者： Liangren SHI Zhiyun ZHAO Zongli LIN Department of Automation Shanghai Jiao Tong University Key Laboratory of Advanced Control and Optimization for Chemical Processes(East China University of Science and Technology) Ministry of Education Charles L. Brown Department of Electrical and Computer Engineering University of Virginia

This paper considers the problem of semi-global leader-following consensus of a multi-agent system whose agent dynamics are represented by linear systems. The input output characteristics of the follower agent actuators, such as those of saturation and dead-zone, are imperfect, not precisely known, and subject to the effect of disturbances. Two consensus control algorithms, of the low-and-high gain feedback type and the low gain based variable structure control type, are proposed for solving the consensus problem. It is shown that both of these control algorithms achieve semi-global leader-following practical consensus in the presence of the imperfectness of the actuators when the communication topology among the follower agents is represented by a strongly connected and detailed balanced directed graph and the leader agent is a neighbor of at least one follower agent. The theoretical results are illustrated by numerical simulation.

关键词： consensus leader-following actuator saturation dead-zone low-and-high gain feedback low gain based variable structure control

来源：评论

学校读者我要写书评

暂无评论

Shape Modeling of a Parallel Soft Panel Continuum Robot

Shape Modeling of a Parallel Soft Panel Continuum Robot

引用

IEEE International Conference on robotics and Biomimetics

作者： Long Li Yinjun Zhao Yingzhong Tian Wenbin Wang Wei Chen Zenggui Gao Yihao Lu Fengfeng Xi School of Mechatronic Engineering and Automation Shanghai Key Laboratory of Intelligent Manufacturing and Robotics Shanghai University Shanghai China School of mechanical and electrical engineering Shenzhen Polytechnic Shenzhen China Department of Aerospace and Industrial Engineering Canada Shanghai Key Laboratory of Intelligent Manufacturing and Robotics Shanghai University Shanghai China

ISBN: (纸本)9781728103785;9781728103778

Continuum robots have attracted a lot of attention in the robotic community due to their high dexterity, deformability, and reachability. However, Modeling of such robots could be very complex and challenging. This paper presents a novel continuum robot constructed with soft panels and its shape modeling approach. The Euler-Bernoulli beam theory in large deformation case is used to obtain the deformation curves of the panels. Then the constrained optimization model for the kinematics is established. By solving the model, not only the relationship between the length of panels and the position and orientation of moving platform can be obtained, but also the deformation shapes could be calculated. The good agreement between the simulation results and the experimental results shows that the modeling approach is very effective and accurate.

关键词： Robots Manufacturing Mechatronics automation Shape Strain Kinematics

来源：评论

学校读者我要写书评

暂无评论

Design of Series/Series-Parallel Compensated Inductive Power Transfer Converter as Wireless Grid to Vehicle Interface

Design of Series/Series-Parallel Compensated Inductive Power...

引用

IEEE Conference on Vehicle Power and Propulsion (VPPC)

作者： Zhicong Huang Zhijian Fang Chi-Seng Lam Pui-In Mak Rui P. Martins State Key Laboratory of Analog and Mixed-Signal VLSI University of Macau Macao China School of Automation China University of Geosciences (Wuhan) Wuhan China Institute of Microelectronics University of Macau Macao China Department of Electrical and Computer Engineering University of Macau Macao China Instituto Superior Técnico Universidade de Lisboa Lisbon Portugal

Inductive power transfer (IPT) converter is increasingly popular as a form of wireless grid to vehicle (G2V) interface. Compared with conventional plug-in interface, wireless G2V interface without physical contact is more user- friendly and preferable. An IPT converter usually connects to a vehicle's DC-link providing a voltage bus for on-board DC/DC converters. To maintain the voltage bus without using a voltage regulator, the IPT converter can work at its native load-independent voltage output point. However, high efficiency performance and low output sensitivity to misalignment are always conflicting, which poses difficulties to design of the IPT converter as a practical wireless G2V interface. In this paper, the relationship among compensation parameters, power efficiency and output voltage sensitivity of a series/series- parallel (S/SP) compensated IPT converter is studied. Detailed design methodology is theoretically illustrated and experimentally verified to optimize the power efficiency and restrict the output sensitivity to an acceptable level, thus satisfying requirements of a wireless G2V interface.

关键词： Wireless communication Wireless sensor networks Couplings Voltage control Sensitivity Transfer functions Capacitors

来源：评论

学校读者我要写书评

暂无评论

Learning to reconstruct and understand indoor scenes from sparse views

arXiv

引用

arXiv 2019年

作者： Yang, Jingyu Xu, Ji Li, Kun Lai, Yu-Kun Yue, Huanjing Lu, Jianzhi Wu, Hao Liu, Yebin School of Electrical and Information Engineering Tianjin University Tianjin300072 China Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin University Tianjin300350 China School of Computer Science and Informatics Cardiff University Wales United Kingdom 3vjia company Department of Automation Tsinghua University Beijing10084 China

This paper proposes a new method for simultaneous 3D reconstruction and semantic segmentation of indoor scenes. Unlike existing methods that require recording a video using a color camera and/or a depth camera, our method only needs a small number of (e.g., 3-5) color images from uncalibrated sparse views as input, which greatly simplifies data acquisition and extends applicable scenarios. Since different views have limited overlaps, our method allows a single image as input to discern the depth and semantic information of the scene. The key issue is how to recover relatively accurate depth from single images and reconstruct a 3D scene by fusing very few depth maps. To address this problem, we first design an iterative deep architecture, Iter-Net, that estimates depth and semantic segmentation alternately, so that they benefit each other. To deal with the little overlap and non-rigid transformation between views, we further propose a joint global and local registration method to reconstruct a 3D scene with semantic information from sparse *** also make available a new indoor synthetic dataset simultaneously providing photorealistic high-resolution RGB images, accurate depth maps and pixel-level semantic labels for thousands of complex layouts, useful for training and evaluation. Experimental results on public datasets and our dataset demonstrate that our method achieves more accurate depth estimation, smaller semantic segmentation errors and better 3D reconstruction results, compared with stateof-the-art methods. Copyright © 2019, The Authors. All rights reserved.

关键词： Cameras

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：