检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Cai, Tingting Zhou, Yangming Zheng, Hong School of Information Science and Engineering East China University of Science and Technology Shanghai200237 China Key Laboratory of Advanced Control and Optimization for Chemical Processes Ministry of Education China

Clinical Named Entity Recognition (CNER) aims to automatically identity clinical terminologies in Electronic Health Records (EHRs), which is a fundamental and crucial step for clinical research. To train a high-performance model for CNER, it usually requires a large number of EHRs with high-quality labels. However, labeling EHRs, especially Chinese EHRs, is time-consuming and expensive. One effective solution to this is active learning, where a model asks labelers to annotate data which the model is uncertain of. Conventional active learning assumes a single labeler that always replies noiseless answers to queried labels. However, in real settings, multiple labelers provide diverse quality of annotation with varied costs and labelers with low overall annotation quality can still assign correct labels for some specific instances. In this paper, we propose a Cost-Quality Adaptive Active Learning (CQAAL) approach for CNER in Chinese EHRs, which maintains a balance between the annotation quality, labeling costs, and the informativeness of selected instances. Specifically, CQAAL selects cost-effective instance-labeler pairs to achieve better annotation quality with lower costs in an adaptive manner. Computational results on the CCKS-2017 Task 2 benchmark dataset demonstrate the superiority and effectiveness of the proposed CQAAL. Copyright © 2020, The Authors. All rights reserved.

关键词： Records management

来源：评论

学校读者我要写书评

暂无评论

Robust static output feedback based ILC design with finite frequency specifications for batch processes with time-varying uncertainties

Robust static output feedback based ILC design with finite f...

引用

第三十九届中国控制会议

作者： Shoulin Hao Tao Liu Wojciech Paszke Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Dalian University ofTechnology Institute of Advanced Control Technology Dalian University of Technology Institute of Automation Electronic and Electrical Engineering University of Zielona Góra

For industrial batch processes with time-varying uncertainties, a robust output feedback based iterative learning control（ILC） design is proposed by introducing finite frequency specifications, based on only the output measurement. The integral of output tracking error in the time domain is incorporated into the ILC updating law to improve the tracking performance from batch to batch. Based on the generalized Kalman-Yakubovich-Popov lemma, robust stability of the resulting closed-loop ILC system along both time and batch directions is analyzed in the repetitive system framework. The corresponding ILC law can be determined from the established tractable linear matrix inequality conditions. Moreover, it is shown that the obtained stability condition can also guarantee the bounded output tracking error and system input in the presence of time-and/or batch-varying uncertainties. An illustrative example from the literature is adopted to demonstrate the effectiveness of the proposed design.

关键词： Batch process time-varying uncertainties iterative learning control output feedback finite frequency range specification

来源：评论

学校读者我要写书评

暂无评论

Real-time Updating Technology of Local Area Orthoimages Based on 3D Digital Earth

Real-time Updating Technology of Local Area Orthoimages Base...

引用

作者： Li Song Yugang Niu Baosong Deng Jing Li Xing Xia Yihang Gong Key Laboratory of Advanced Control and Optimization for Chemical Processes East China University of Science and Technology National Innovation Institute of Defense Technology Academy of Military Science School of Software Tianjin University

In order to solve the problems of poor real-time performance and single display method in traditional unmanned aerial vehicle(UAV) orthographic image mosaic, this paper proposes a real-time updating technology of local area orthoimages based on 3D digital earth, which can be widely used in the fields of emergency rescue, environmental monitoring and military *** technology is that in the process of UAV aerial photography, the server receives sequence aerial image in real time and synchronously completes orthographic image splicing, then automatically cuts them into regular image tiles and transmits the regular image tiles to the display terminal in an incremental manner. The display terminal software constructs a 3D digital earth based on quadtree LOD algorithm, and updates the terrain texture of the target range with the received high-definition orthographic image tiles, so as to realize real-time coverage monitoring of key areas. In this paper, the above work is verified by real aerial images, and the results prove the feasibility and effectiveness of the work.

关键词： Orthographic image mosaic Real-time update 3D digital earth

来源：评论

学校读者我要写书评

暂无评论

Effective Resource Allocation in Cooperative Co-evolutionary Algorithm for Large-Scale Fully-Separable Problems

Effective Resource Allocation in Cooperative Co-evolutionary...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Wei Du Le Tong Yang Tang Key Laboratory of Advanced Control and Optimization for Chemical Processes East China University of Science and Technology Shanghai China The College of Information Mechanical and Electrical Engineering Shanghai Normal University Shanghai China

ISBN: (数字)9781728185262

ISBN: (纸本)9781728185279

This paper investigates the effective computational resource allocation for large-scale fully-separable problems under the framework of a cooperative co-evolutionary algorithm called MLSoft. According to different subgroup sizes of the problems, we allocate different numbers of iterations to the subproblems in all the cycles. For high-dimensional subproblems, more iterations are needed during the optimization process; while for low-dimensional subproblems, fewer iterations will be assigned. The experimental results reveal that the proposed resource allocation scheme is simple but effective, which can enhance the performance of MLSoft in solving large-scale fully-separable problems. In addition, we conduct a group of experiments to evaluate the results if a higher weight is assigned to more recent performance in MLSoft. The results show that introducing weight to the latest reward affects very little on the performance of MLSoft.

关键词： Adaptive systems Conferences Resource management optimization

来源：评论

学校读者我要写书评

暂无评论

Opportunities and Challenges of Artificial Intelligence for Green Manufacturing in the Process Industry

引用

Engineering 2019年第6期5卷 995-1002页

作者： Shuai Mao Bing Wang Yang Tang Feng Qian Key Laboratory of Advanced Control and Optimization for Chemical Processes Ministry of EducationEast China University of Science and TechnologyShanghai 200237China

Smart manufacturing is critical in improving the quality of the process industry. In smart manufacturing, there is a trend to incorporate different kinds of new-generation information technologies into process- safety analysis. At present, green manufacturing is facing major obstacles related to safety management, due to the usage of large amounts of hazardous chemicals, resulting in spatial inhomogeneity of chemical industrial processes and increasingly stringent safety and environmental regulations. Emerging informa- tion technologies such as arti cial intelligence (AI) are quite promising as a means of overcoming these dif culties. Based on state-of-the-art AI methods and the complex safety relations in the process industry, we identify and discuss several technical challenges associated with process safety: ① knowledge acquisition with scarce labels for process safety;② knowledge-based reasoning for process safety;③ accurate fusion of heterogeneous data from various sources;and ④ effective learning for dynamic risk assessment and aided decision-making. Current and future works are also discussed in this context.

关键词： Process industry Smart manufacturing Green manufacturing Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Anti-windup Disturbance Rejection control Design for Sampled Systems with Output Delay and Asymmetric Actuator Saturation Constraint ⁎

引用

IFAC-PapersOnLine 2020年第2期53卷 1349-1354页

作者： Xinpeng Geng Zhencai Wang Shoulin Hao Tao Liu Zoltan Kalman Nagy Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Dalian University of Technology Dalian 116024 China Institute of Advanced Control Technology Dalian University of Technology Dalian 116024 China Davidson School of Chemical Engineering Purdue University West Lafayette Indiana 47907 United States

A novel anti-windup disturbance rejection control design is proposed for industrial sampled systems with output delay and asymmetric actuator saturation constraint. To deal with the asymmetric actuator saturation constraint as often encountered in engineering practice, the input constraint is equivalently transformed into a symmetric actuator saturation constraint for the convenience of control design. Based on the equivalent system description, a model-based extended state observer (MESO) is designed to simultaneously estimate the system state and disturbance, which becomes an anti-windup compensator when the actuator saturation occurs. In order to compensate for the delay mismatch in MESO, a generalized predictor is utilized to estimate the undelayed system output. Accordingly, a pole placement approach is given to design the feedback controller. A set-point pre-filter is designed to ensure no steady-state output tracking error, in terms of a desired transfer function for the set-point tracking. Based on the delay-dependent sector condition and generalized free-weighting-matrix (GFWM), a sufficient condition guaranteeing the stability of the closed-loop system is established in terms of linear matrix inequalities (LMIs). An illustrative example from the literature is used to demonstrate the effectiveness and advantage of the proposed control method.

关键词： Sampled systems Asymmetric actuator saturation Output delay Anti-windup design Extended state observer (ESO)

来源：评论

学校读者我要写书评

暂无评论

Optimal stationary state estimation over multiple markovian packet drop channels

arXiv

引用

arXiv 2021年

作者： Xu, Jiapeng Gu, Guoxiang Gupta, Vijay Tang, Yang Key Laboratory of Advanced Control and Optimization for Chemical Processes Ministry of Education East China University of Science and Technology Shanghai200237 China School of Electrical Engineering and Computer Science Louisiana State University Baton RougeLA70803 United States Department of Electrical Engineering University of Notre Dame Notre DameIN46556 United States

In this paper, we investigate the state estimation problem over multiple Markovian packet drop channels. In this problem setup, a remote estimator receives measurement data transmitted from multiple sensors over individual channels. By the method of Markovian jump linear systems, an optimal stationary estimator that minimizes the error variance in the steady state is obtained, based on the mean-square (MS) stabilizing solution to the coupled algebraic Riccati equations. An explicit necessary and sufficient condition is derived for the existence of the MS stabilizing solution, which coincides with that of the standard Kalman filter. More importantly, we provide a sufficient condition under which the MS detectability with multiple Markovian packet drop channels can be decoupled, and propose a locally optimal stationary estimator but computationally more tractable. Analytic sufficient and necessary MS detectability conditions are presented for the decoupled subsystems subsequently. Finally, numerical simulations are conducted to illustrate the results on the MS stabilizing solution, the MS detectability, and the performance of the optimal and locally optimal stationary estimators. © 2021, CC BY.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Stabilization of Linear Systems with Aperiodic Sampled-Data control

Stabilization of Linear Systems with Aperiodic Sampled-Data ...

引用

IEEE Conference on Decision and control

作者： Wenbing Zhang Wei Xing Zheng Yang Tang Yunlei Zou School of Mathematical Sciences Yangzhou University Yangzhou P. R. China School of Computer Data and Mathematical Sciences Western Sydney University Sydney NSW Australia Key Laboratory of Advanced Control and Optimization for Chemical Processes Ministry of Education East China University of Science and Technology Shanghai P. R. China

ISBN: (纸本)9781665436601

This paper is concerned with the sampled-data stabilization problem for a class of linear systems. Different from the input-delay approach that has been widely used in analyzing the stabilization problem of sampled-data systems, an extended form of the celebrated Halanay inequality is developed for sampled-data systems so as to study the stabilization problem of linear systems under aperiodic sampled-data control. Based on the extended Halanay inequality, the stabilization problem is solved for linear sampled-data systems, where it is required that the gain should be strictly less than the decay rate and then the upper bound of the sampling intervals can be estimated. In order to enlarge the upper bound of the sampling intervals, a further extension of the developed Halanay inequality is made. Then some new conditions are derived to ensure the exponential stability of linear sampleddata systems, where the upper bound of the sampling intervals is allowed to violate the condition of the Halanay inequality. Subsequently, the obtained results are applied to deal with the consensus problem of linear multi-agent systems.

关键词： Linear systems Sufficient conditions Upper bound Conferences Sampled data systems Stability analysis control theory

来源：评论

学校读者我要写书评

暂无评论

Multi-objective optimization of steam system based on GPU acceleration

引用

IFAC-PapersOnLine 2018年第21期51卷 183-188页

作者： Zhao, Liang Ye, Zhencheng Du, Wenli Key Laboratory of Advanced Control and Optimization for Chemical Processes East China University of Science and Technology Shanghai200237 China

The steam system is an important part of the utility systems in process industry. The energy consumption and operation cost of the existing plant were increased due to the inefficient configuration of the steam system. Meanwhile, the fossil fuels such as coal and oil were used to produce steam for the process industry, and the poisonous gases released from the burning process caused a lot of damage to the environments. Therefore, it is of great practical significance to reduce the operation cost and pollutant emissions simultaneously. This paper proposes an evolutionary multi-objective optimization (EMOO) algorithm to deal with this problems. But because of the complexity, higher dimension and rigid constraint conditions of the process industry, the computation time of EMOO algorithm can not meet the requirements of real-time optimization. Thus, Graphics Processing Unit (GPU) computing, which was running on the CUDA platform was introduced to shorten the running time of the algorithm. A constraint handling mechanism was presented to improve the performance of the algorithm. The case study indicates that the proposed GPU-based EMOO algorithm can obtain the Pareto optimal solution of the steam system in a minute-level time. © 2018

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Real-time Online UAV Images Mosaic with Robustness to Cumulative Errors

Real-time Online UAV Images Mosaic with Robustness to Cumula...

引用

作者： Xing Xia Bei Wang Jing Li Li Song Yi Hang Gong Bao Song Deng Key Laboratory of Advanced Control and Optimization for Chemical Processes East China University of Science and Technology National Innovation Institute of Defense Technology Academy of Military Science Tianjin Artificial Intelligence Innovation Center

In this paper, a novel real-time online UAV image mosaic algorithm is proposed to meet the real-time, robustness and accuracy requirements of practical application. First, the algorithm adopts GPS and track planning information to locate the adjacent images. Instead of the 8-DOF(degrees of freedom) homography transformation, the 4-DOF similarity transformation is estimated to more robustly register the UAV images and reduce their perspective errors. Second, a new method of local registration is developed to reduce the cumulative errors and calculation costs. Meanwhile, the real-time mosaic process is used to register images and update the panoramic image. Finally, the effectiveness of the proposed approach is evaluated by a group of experiments on 4 K images taken by quadrotor drones. According to the comparison of experiments, the proposed algorithm is robust to cumulative errors and obtains high-quality panorama. Additionally, through the analysis on stitching time and practical application, frame-by-frame mosaic synthesis is online updated in real-time.

关键词： Real-Time Image Mosaic Similarity Transformation Local Registration

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：