检索结果-内蒙古大学图书馆

IEEE International Conference on systems, Man and Cybernetics

作者： Ruijie Xu Shichao Chen Wenqiao Sun Yisheng Lv Jialiang Luo Ying Tang The State Key Laboratory for Management and Control of Complex System State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences College of Information Science & Technology Beijing University of Chemical Technology Beijing China The State Key Laboratory for Management and Control of Complex System State Key Laboratory of Multimodal Artificial Intelligence Systems The Center of National Railway Intelligent Transportation System Engineering and Technology Institute of Automation Chinese Academy of Sciences China Academy of Railway Sciences Corporation Limited Beijing China China Academy of Railway Sciences Corporation Limited Transportation and Economics Research Institute and the Center of National Railway Intelligent Transportation System Engineering and Technology Beijing China The State Key Laboratory for Management and Control of Complex System State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China The State Key Laboratory for Management and Control of Complex System State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences School of Information Engineering China University of Geosciences Beijing Beijing China Department of Electrical and Computer Engineering Rowan University Glassboro USA

Global Navigation Satellite systems (GNSS) can provide real-time positioning information for outdoor users, but cannot for indoor scenarios or heavily occluded outdoor scenarios. Strap-down Inertial Navigation System (SINS) are widely used to locate people in complex interior or heavily occluded outdoor scenarios due to its light weight and low power consumption. However, IMU of SINS are noisy, and the sampling data error is large, which is a divergence of the error with time. Therefore, it will generate a positioning accumulation error, which affects the final positioning accuracy. The problem of cumulative IMU errors is usually dealt with by Zero-Velocity Update (ZUPT). The zero-velocity detection part of basic ZUPT method usually uses a single threshold to determine the gait of pedestrian, which often has the problem of gait misjudgment and omission. To address these problems, this paper proposes a composite conditional detection method to solve the problem of misjudgment in the zero-velocity interval. In addition, we redesign the zero-velocity update algorithm and uses the Cubature Kalman filter (CKF) for pedestrian positioning error correction. The experimental results demonstrate that the proposed ZUPT method based on dual-threshold detection can better detect the interval between pedestrian motion and stationery than ones with single threshold. The zero-velocity update algorithm based on CKF has higher performance than conventional EKF and UKF methods, which constrains the cumulative error of SINS to about 0.2% of the whole walking distance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cloud-based platform for intelligent healthcare monitoring and risk prevention in hazardous manufacturing contexts 14

Cloud-based platform for intelligent healthcare monitoring a...

引用

14th CIRP Conference on intelligent Computation in Manufacturing engineering, CIRP ICME 2020

作者： Simeone, Alessandro Caggiano, Alessandra Boun, Lev Grant, Rebecca Intelligent Manufacturing Key Laboratory of Ministry of Education Shantou University Shantou Guangdong515063 China Department of Industrial Engineering University of Naples Federico II Piazzale Tecchio 80 Naples80125 Italy Naples Italy Dynamic Computer Systems PoB 1341 Atlit30300 Israel Wolfson School of Mechanical Electrical and Manufacturing Engineering Loughborough University LoughboroughLE11 3TU United Kingdom

This paper presents an intelligent cloud-based platform for workers healthcare monitoring and risk prevention in potentially hazardous manufacturing contexts. The platform is structured according to sequential modules dedicated to data acquisition, processing and decision-making support. Several sensors and data sources, including smart wearables, machine tool embedded sensors and environmental sensors, are employed for data collection, comprising information on offline clinical background, operational and environmental data. The cloud data processing module is responsible for extracting relevant features from the acquired data in order to feed a machine learning-based decision-making support system. The latter provides a classification of workers' health status so that a prompt intervention can be performed in particularly challenging scenarios. © 2021 The Authors. Published by Elsevier B.V.

关键词： Machine tools

来源：评论

学校读者我要写书评

暂无评论

Achievable Diversity Order of HARQ-Aided Downlink NOMA systems

arXiv

引用

arXiv 2022年

作者： Shi, Zheng Zhang, Chenmeng Fu, Yaru Wang, Hong Yang, Guanghua Ma, Shaodan The Institute of Physical Internet The School of Intelligent Systems Science and Engineering Jinan University Zhuhai519070 China The School of Telecommunications Engineering Xidian University Xi’an710000 China The Department of Information Systems Technology and Design Singapore University of Technology and Design Singapore The School of Communication and Information Engineering Nanjing University of Posts and Telecommunications Nanjing210003 China The National Mobile Communications Research Laboratory Southeast University Nanjing210096 China The State Key Laboratory of Internet of Things for Smart City The Department of Electrical and Computer Engineering University of Macau China

The combination between non-orthogonal multiple access (NOMA) and hybrid automatic repeat request (HARQ) is capable of realizing ultra-reliability, high throughput and many concurrent connections particularly for emerging communication systems. This paper focuses on characterizing the asymptotic scaling law of the outage probability of HARQ-aided NOMA systems with respect to the transmit power, i.e., diversity order. The analysis of diversity order is carried out for three basic types of HARQ-aided downlink NOMA systems, including Type I HARQ, HARQ with chase combining (HARQ-CC) and HARQ with incremental redundancy (HARQ-IR). The diversity orders of three HARQ-aided downlink NOMA systems are derived in closed-form, where an integration domain partition trick is developed to obtain the bounds of the outage probability specially for HARQ-CC and HARQ-IR-aided NOMA systems. The analytical results show that the diversity order is a decreasing step function of transmission rate, and full time diversity can only be achieved under a sufficiently low transmission rate. It is also revealed that HARQ-IR-aided NOMA systems have the largest diversity order, followed by HARQ-CC-aided and then Type I HARQ-aided NOMA systems. Additionally, the users’ diversity orders follow a descending order according to their respective average channel gains. Furthermore, we expand discussions on the cases of power-efficient transmissions and imperfect channel state information (CSI). Monte Carlo simulations finally confirm our analysis. © 2022, CC BY.

关键词： Monte Carlo methods

来源：评论

学校读者我要写书评

暂无评论

Chance Constrained Economic Dispatch Considering the Capability of Network Flexibility Against Renewable Uncertainties

arXiv

引用

arXiv 2021年

作者： Song, Yue Liu, Tao Hill, David J. The Department of Control Science and Engineering Tongji University Shanghai201804 China The National Key Laboratory of Autonomous Intelligent Unmanned Systems Shanghai201210 China The Frontiers Science Center for Intelligent Autonomous Systems Ministry of Education Shanghai200120 China Hong Kong The HKU Shenzhen Institute of Research and Innovation Shenzhen China The Department of Electrical and Computer Systems Engineering Monash University MelbourneVIC3000 Australia The Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong

This paper incorporates a continuous-type network flexibility into chance constrained economic dispatch (CCED). In the proposed model, both power generations and line susceptances are continuous variables to minimize the expected generation cost and guarantee a low probability of constraint violation in terms of generations and line flows under renewable uncertainties. From the analytical form of CCED, we figure out the mechanism of network flexibility against uncertainties-while renewable uncertainties shrink the usable line capacities and aggravate transmission congestion, network flexibility mitigates congestion by re-routing the base-case line flows and reducing the line capacity shrinkage caused by uncertainties. Further, we propose an alternate iteration solver for this problem. By duality theory, we set up a master problem in the form of second-order cone programming to optimize generation dispatch scheme and a subproblem in the form of linear programming to optimize line susceptances. A satisfactory solution can be obtained efficiently by alternately solving these two problems. The proposed method applies to both Gaussian uncertainty and non-Gaussian uncertainty by means of Gaussian mixture model. The case studies on the IEEE 14-bus system and IEEE 118-bus system suggest that network flexibility can significantly improve operational economy while ensuring security under uncertainties. © 2021, CC BY.

关键词： Second-order cone programming

来源：评论

学校读者我要写书评

暂无评论

Natural Language Processing for Smart Healthcare

arXiv

引用

arXiv 2021年

作者： Zhou, Binggui Yang, Guanghua Shi, Zheng Ma, Shaodan The School of Intelligent Systems Science and Engineering Jinan University Zhuhai519070 China State Key Laboratory of Internet of Things for Smart City The Department of Electrical and Computer Engineering University of Macau 999078 China The State Key Laboratory of Internet of Things for Smart City University of Macau 999078 China The State Key Laboratory of Internet of Things for Smart City The Department of Electrical and Computer Engineering University of Macau 999078 China

Smart healthcare has achieved significant progress in recent years. Emerging artificial intelligence (AI) technologies enable various smart applications across various healthcare scenarios. As an essential technology powered by AI, natural language processing (NLP) plays a key role in smart healthcare due to its capability of analysing and understanding human language. In this work, we review existing studies that concern NLP for smart healthcare from the perspectives of technique and application. We first elaborate on different NLP approaches and the NLP pipeline for smart healthcare from the technical point of view. Then, in the context of smart healthcare applications employing NLP techniques, we introduce representative smart healthcare scenarios, including clinical practice, hospital management, personal care, public health, and drug development. We further discuss two specific medical issues, i.e., the coronavirus disease 2019 (COVID-19) pandemic and mental health, in which NLP-driven smart healthcare plays an important role. Finally, we discuss the limitations of current works and identify the directions for future works. Copyright © 2021, The Authors. All rights reserved.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Guidance Control for Parallel Parking Tasks

引用

IEEE/CAA Journal of Automatica Sinica 2020年第1期7卷 301-306页

作者： Jiyuan Tan Chunling Xu Li Li Fei-Yue Wang Dongpu Cao Lingxi Li Key Laboratory of Urban Intelligent Traffic Control Technology North China University of TechnologyBeijing 100144China Beijing Transport Institute Beijing 100073China Department of Automation BNRistTsinghua UniversityBeijing 100084China Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100080China Driver Cognition and Automated Driving Laboratory University of WaterlooWaterloo N2L 3G1Canada Department of Electrical and Computer Engineering Purdue School of Engineering and TechnologyIndiana University-Purdue University IndianapolisIndiana 46202-5132 USA

Parking into small berths remains difficult for unskilled drivers. Researchers had proposed different automatic parking systems to solve this problem. The first kind of strategies(called parking trajectory planning) designs a detailed reference trajectory that links the start and ending points of a special parking task and let the vehicle track this reference trajectory so as to park into the berth. The second kind of strategies(called guidance control) just characterizes several regimes of driving actions as well as the important switching points in certain rule style and let the vehicle follows the pre-selected series of actions so as to park into the berth. Parking guidance control is simpler than parking trajectory planning. However, no studies thoroughly validated parking guidance control before. In this paper, a new automatic parking method is presented, which could characterize the desired control actions directly. Then the feasibility is examined carefully. Tests show that a simple parking guidance control strategy can work in most parallel parking tasks, if the available parking berth is not too small. This finding helps to build more concise automatic parking systems that can efficiently guide human drivers.

关键词： Automatic parking guidance control trajectory planning

来源：评论

学校读者我要写书评

暂无评论

A Domain-Agnostic Approach for Characterization of Lifelong Learning systems

arXiv

引用

arXiv 2023年

作者： Baker, Megan M. New, Alexander Aguilar-Simon, Mario Al-Halah, Ziad Arnold, Sébastien M.R. Ben-Iwhiwhu, Ese Brna, Andrew P. Brooks, Ethan Brown, Ryan C. Daniels, Zachary Daram, Anurag Delattre, Fabien Dellana, Ryan Eaton, Eric Fu, Haotian Grauman, Kristen Hostetler, Jesse Iqbal, Shariq Kent, Cassandra Ketz, Nicholas Kolouri, Soheil Konidaris, George Kudithipudi, Dhireesha Learned-Miller, Erik Lee, Seungwon Littman, Michael L. Madireddy, Sandeep Mendez, Jorge A. Nguyen, Eric Q. Piatko, Christine Pilly, Praveen K. Raghavan, Aswin Rahman, Abrar Ramakrishnan, Santhosh Kumar Ratzlaff, Neale Soltoggio, Andrea Stone, Peter Sur, Indranil Tang, Zhipeng Tiwari, Saket Vedder, Kyle Wang, Felix Xu, Zifan Yanguas-Gil, Angel Yedidsion, Harel Yu, Shangqun Vallabha, Gautam K. Johns Hopkins University Applied Physics Laboratory 11100 Johns Hopkins Rd. LaurelMD20723 United States Teledyne Scientific Company Intelligent Systems Laboratory 19 T.W. Alexander Drive NC27709 United States Department of Computer Science University of Texas at Austin AustinTX United States Department of Computer Science University of Southern California Los AngelesCA United States Department of Computer Science Loughborough University Loughborough United Kingdom Department of Electrical Engineering and Computer Science University of Michigan Ann ArborMI United States SRI International 201 Washington Rd PrincetonNJ United States University of Texas at San Antonio San AntonioTX United States Department of Computer Science University of Massachusetts Amherst AmherstMA United States Sandia National Laboratories AlbuquerqueNM United States Department of Computer and Information Science University of Pennsylvania PhiladelphiaPA United States Department of Computer Science Brown University ProvidenceRI United States Information and Systems Sciences Laboratory HRL Laboratories 3011 Malibu Canyon Road MalibuCA90265 United States Department of Computer Science Vanderbilt University NashvilleTN United States Argonne National Laboratory 9700 S Cass Ave LemontIL United States

Despite the advancement of machine learning techniques in recent years, state-of-the-art systems lack robustness to "real world" events, where the input distributions and tasks encountered by the deployed systems will not be limited to the original training context, and systems will instead need to adapt to novel distributions and tasks while deployed. This critical gap may be addressed through the development of "Lifelong Learning" systems that are capable of 1) Continuous Learning, 2) Transfer and Adaptation, and 3) Scalability. Unfortunately, efforts to improve these capabilities are typically treated as distinct areas of research that are assessed independently, without regard to the impact of each separate capability on other aspects of the system. We instead propose a holistic approach, using a suite of metrics and an evaluation framework to assess Lifelong Learning in a principled way that is agnostic to specific domains or system techniques. Through five case studies, we show that this suite of metrics can inform the development of varied and complex Lifelong Learning systems. We highlight how the proposed suite of metrics quantifies performance trade-offs present during Lifelong Learning system development - both the widely discussed Stability-Plasticity dilemma and the newly proposed relationship between Sample Efficient and Robust Learning. Further, we make recommendations for the formulation and use of metrics to guide the continuing development of Lifelong Learning systems and assess their progress in the future. Copyright © 2023, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Creating Own AI Datasets from Different Language Sources Efficiently: Advantages, Disadvantages and Best Pracitces to Make Own Datasets

Creating Own AI Datasets from Different Language Sources Eff...

引用

International IEEE Conference and Workshop: Óbuda on electrical and Power engineering (CANDO-EPE)

作者： György Molnár József Cserkó Enikő Nagy Zoltán Balogh Kandó Kálmán Faculty of Electrical Engineering Óbuda University Budapest Hungary János Csere Apáczai Faculty Széchenyi University Győr Hungary GAMF Faculty of Engineering and Computer Science John Von Neumann University Kecskemét Hungary Széchenyi University Doctoral School of Multidisciplinary Engineering Sciences (MMTDI) Győr Hungary Antal Bejczy Center for Intelligent Robotics John von Neumann Faculty Institute of Cyberphysical Systems Óbuda University Budapest Hungary Department of Informatics Faculty of Natural Sciences and Informatics Constantine the Philosopher University in Nitra Nitra Slovakia

Artificial Intelligence (AI) has become a ubiquitous technology that has the potential to revolutionize many industries. However, AI requires access to vast amounts of data to achieve its full potential. By understanding these data sources and the best practices for working with them, we can unlock the full potential of AI and create groundbreaking solutions that benefit society as a whole. Data sources can be utilized to train AI algorithms, including structured and unstructured data, but finding relevant datasets is challenging. The main problem is the international sources. Most of the datasets are available only in English or other common languages. However these are good sources, but translating them is expensive and time-consuming. This paper shows how to generate own datasets from open-source data with translation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Surface Charging Phenomena on HVDC Spacers for Compressed SF_(6) Insulation and Charge Tailoring Strategies

引用

CSEE Journal of Power and Energy systems 2020年第1期6卷 83-99页

作者： Chuanyang Li Yuan Xu Chuanjie Lin Geng Chen Youping Tu Yao Zhou Zhipeng Lei Tao Han Simone Vincenzo Suraci Jian Wang Weidong Liu M.Tariq Nazir Shun He Andrea Cavallini Giovanni Mazzanti Davide Fabiani Jinliang He Electrical Insulation Research Center Institute of Materials ScienceElectrical and Computer EngineeringUniversity of ConnecticutStorrsCT 06269USA. China Electric Power Research Institute Beijing 100192China Department of Electrical Electronicand Information Engineering“Guglielmo Marconi”University of BolognaViale Risorgimento 2Bologna40136Italy State Key Laboratory of Power Systems Department of Electrical EngineeringTsinghua UniversityBeijing 100084China Beijing Area Major Laboratory of High Voltage and Electromagnetic Compatibility North China Electric Power UniversityBeijing 102206China Shanxi Key Laboratory of Mining Electrical Equipment and Intelligent Control National and Provincial Joint EngineeringTaiyuan University of TechnologyTaiyuan 030024China Key Laboratory of Smart Grid of Education Ministry School of Electrical and Information EngineeringTianjin UniversityTianjin 300072China School of Mechanical and Manufacturing Engineering University of New South Wales SydneyNSW 2052Australia Electric Power Research Institute Yunnan Electric Power Grid Co.ltd.KunmingYunnan 650217China

Surface flashover of spacers is a key factor limiting the application of HVDC GIS/GIL,while the charge accumula-tion on the surface of the spacer could have a potential adverse effect on the surface flashover *** paper discusses the laws regarding distribution patterns of surface charges and the related *** field-dependent property is discussed in detail to comprehensively illustrate the charge transport mecha-nism and explain the research differences regarding different surface charge patterns obtained by previous *** addition,the main surface charge control methods for epoxy resin are summarized and *** potential research directions of charge control methods and key points in manufacturing of spacers used in HVDC GIS/GIL are also explored.

关键词： GIL HVDC insulator SF6 surface charge accumulation surface flashover

来源：评论

学校读者我要写书评

暂无评论

Weak value picture on quantum observables: Gauge-invariant vector potentials

arXiv

引用

arXiv 2020年

作者： Yu, Sunkyu Piao, Xianji Park, Namkyoo Photonic Systems Laboratory Department of Electrical and Computer Engineering Seoul National University Seoul08826 Korea Republic of Intelligent Wave Systems Laboratory Department of Electrical and Computer Engineering Seoul National University Seoul08826 Korea Republic of

The conservation of physical quantities under coordinate transformations, known as gauge invariance, has been the foundation of theoretical frameworks in both quantum and classical theory. The finding of gauge-invariant quantities has enabled the geometric and topological interpretations of quantum phenomena with the Berry phase, or the separation of quark and gluon contributions in quantum chromodynamics. Here, with an example of quantum geometric quantities-Berry connection, phase, and curvature-we extract a new gauge-invariant quantity by applying a "weak value picture". By employing different pre- and post-selections in the derivation of the Berry phase in the context of weak values, we derive the gauge-invariant vector potential from the Berry connection that is originally gauge-dependent, and show that the obtained vector potential corresponds to the weak value of the projected momentum operator. The local nature of this quantity is demonstrated with an example of the Aharonov-Bohm effect, proving that this gauge-invariant vector potential can be interpreted as the only source of the Berry curvature in the magnetic field. This weak value decomposition approach will lead to the extraction of new measurable quantities from traditionally unobservable quantities. Copyright © 2020, The Authors. All rights reserved.

关键词： Gages

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：