检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Zhao, Chaoqiang Yen, Gary G. Sun, Qiyu Zhang, Chongzhen Tang, Yang The Key Laboratory of Advanced Control and Optimization for Chemical Process Ministry of Education East China University of Science and Technology Shanghai200237 China The School of Electrical and Computer Engineering Oklahoma State University StillwaterOK74075 United States

Previous work has shown that adversarial learning can be used for unsupervised monocular depth and visual odometry (VO) estimation, in which the adversarial loss and the geometric image reconstruction loss are utilized as the mainly supervisory signals to train the whole unsupervised framework. However, the performance of the adversarial framework and image reconstruction is usually limited by occlusions and the visual field changes between frames. This paper proposes a masked generative adversarial network (GAN) for unsupervised monocular depth and ego-motion estimation. The MaskNet and Boolean mask scheme are designed in this framework to eliminate the effects of occlusions and impacts of visual field changes on the reconstruction loss and adversarial loss, respectively. Furthermore, we also consider the scale consistency of our pose network by utilizing a new scale-consistency loss, and therefore, our pose network is capable of providing the full camera trajectory over a long monocular sequence. Extensive experiments on the KITTI dataset show that each component proposed in this paper contributes to the performance, and both our depth and trajectory predictions achieve competitive performance on the KITTI and Make3D datasets. Copyright © 2020, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Cost-Quality Adaptive Active Learning for Chinese Clinical Named Entity Recognition

Cost-Quality Adaptive Active Learning for Chinese Clinical N...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

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

ISBN: (数字)9781728162157

ISBN: (纸本)9781728162164

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 issue is active learning, where a model asks labelers to annotate data which is beneficial to model performance improvement. 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 cost 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 cost and the informativeness of selected instances. Specifically, our proposed CQAAL method selects cost-effective instance-labeler pairs to achieve better annotation quality with lower cost in an adaptive manner. Computational results on the CCKS2017 dataset demonstrate the superiority and effectiveness of CQAAL.

关键词： Annotations Uncertainty Labeling Task analysis Entropy Manuals Neural networks

来源：评论

学校读者我要写书评

暂无评论

A Knowledge Base System for Operation optimization: Design and Implementation Practice for the Polyethylene process

引用

Engineering 2019年第6期5卷 1041-1048页

作者： Weimin Zhong Chaoyuan Li Xin Peng Feng Wan Xufeng An Zhou Tian Key Laboratory of Advanced Control and Optimization for Chemical Processes Ministry of EducationEast China University of Science and TechnologyShanghai 200237China

Setting up a knowledge base is a helpful way to optimize the operation of the polyethylene process by improving the performance and the ef ciency of reuse of information and knowledge two critical ele- ments in polyethylene smart manufacturing. In this paper, we propose an overall structure for a knowl- edge base based on practical customer demand and the mechanism of the polyethylene process. First, an ontology of the polyethylene process constructed using the seven-step method is introduced as a carrier for knowledge representation and sharing. Next, a prediction method is presented for the molecular weight distribution (MWD) based on a back propagation (BP) neural network model, by analyzing the relationships between the operating conditions and the parameters of the MWD. Based on this network, a differential evolution algorithm is introduced to optimize the operating conditions by tuning the MWD. Finally, utilizing a MySQL database and the Java programming language, a knowledge base system for the operation optimization of the polyethylene process based on a browser/server framework is realized.

关键词： Ontology Operation optimization Knowledge base system Polyethylene process

来源：评论

学校读者我要写书评

暂无评论

Quasi-Synchronization of Heterogeneous Lur'e Networks With Impulsive Feedback control

Quasi-Synchronization of Heterogeneous Lur'e Networks With I...

引用

第40届中国控制会议

作者： Chongfang Jin Sangli Shi Zhengxin Wang Wangli He Guo-Ping Jiang School of Science Nanjing University of Posts and Telecommunications Jiangsu Engineering Lab for IOT Intelligent Robots (IOTRobot) Nanjing University of Posts and Telecommunications The Key Laboratory of Advanced Control and Optimization for Chemical Processes Ministry of EducationEast China University of Science and Technology School of Automation Nanjing University of Posts and Telecommunications

The target of this paper is studying the quasi-synchronization problems of the heterogeneous Lur'e networks with impulsive feedback control. By introducing impulsive feedback control, the heterogeneous Lur'e network is analyzed. The sufficient condition for guaranteeing quasi-synchronization is derived by means of linear matrix inequality(LMI), the Schur complement and the principle of comparison. More over, the upper bound of exponential quasi-synchronization errors is further calculated. Finally, the numerical simulations are presented to illustrate the effectiveness of the control protocol and theoretical results.

关键词： Exponential quasi-synchronization Lur'e network Feedback Impulsive control

来源：评论

学校读者我要写书评

暂无评论

A Dynamic Event-Triggered Approach to Multi-Agent Consensus

A Dynamic Event-Triggered Approach to Multi-Agent Consensus

引用

Chinese control Conference (CCC)

作者： Xianwei Li Yang Tang Shaoyuan Li Department of Automation Shanghai Jiao Tong University Shanghai China Key Laboratory of Advanced Control and Optimization for Chemical Processes East China University of Science and Technology Shanghai China

ISBN: (数字)9789881563903

ISBN: (纸本)9781728165233

This paper focuses on designing dynamic event-triggered (DET) protocols for consensus control of general linear multi-agent systems (MASs). Design algorithms are constructed for DET protocols with static and adaptive coupling, respectively. The designed event-triggering conditions involve internal dynamic variables that depend on the error information of the system, which provide more flexibility to reduce the number of triggered events than the existing results on linear MASs. The protocol with adaptive coupling is of the fully distributed nature. It is proved that the proposed protocols can ensure consensus and are not Zeno. A numerical example is provided to illustrate the effectiveness and advantages of the designed protocols.

关键词： Protocols Couplings Laplace equations Multi-agent systems Lyapunov methods Closed loop systems optimization

来源：评论

学校读者我要写书评

暂无评论

Cost-quality adaptive active learning for chinese clinical named entity recognition

arXiv

引用

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

Almost Sure Exponential Stability of Altafini Model with Multiplicative Noise for Opinion Dynamics

Almost Sure Exponential Stability of Altafini Model with Mul...

引用

第三十九届中国控制会议

作者： Fanli Yuan Ying Cui Haili Liang Zhao Zhou Shanghai Key Laboratory of Power Station Automation Technology School of Mechatronic Engineering and AutomationShanghai University Key Laboratory of Advanced Control and Optimization for Chemical Processes Ministry of EducationEast China University of Science and Technology

In this paper, we investigate the stability analysis of stochastic opinion dynamics in which the agents are interfered by multiplicative noise. We propose a stochastic Altafini model of opinion evolution in signed social networks with multiplicative noise and give the analysis of almost sure exponential stability(ASES). Compared with the deterministic opinion dynamic and stochastic opinion dynamics in additive noise environments, our results concern the effects of the agents' free will, i.e.,multiplicative noise, in signed social networks. We establish a sufficient condition with stochastic multiplicative noise which can guarantee the stochastic system is almost sure exponential stability(ASES) when the parameters of the strength of noise is limited by the conditions. Numerical simulations are given to illustrate the above theoretical results.

关键词： Signed Networks Opinion Dynamics Stability Stochastic Systems

来源：评论

学校读者我要写书评

暂无评论

Sliding Mode control for Interval Type-2 Fuzzy System Under Fading Channels

Sliding Mode Control for Interval Type-2 Fuzzy System Under ...

引用

International Conference on control and Automation (ICCA)

作者： Yekai Yang Yugang Niu Bei Chen Yuanyuan Zou Key Laboratory of Advanced Control and Optimization for Chemical Process (East China University of Science and Technology) Ministry of Education Shanghai China School of Electric and Electronic Engineering Shanghai University of Engineering Science Shanghai China Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9781728190938

ISBN: (纸本)9781728190945

This paper addresses the problem of sliding mode control for discrete-time interval type-2 fuzzy system subject to fading channels. The multiplicative fading model is established for reflecting the fluctuation of the transmitted signals. Meanwhile, the membership function-dependent sliding function involves the fading coefficient. By using the membership functions depending on the fading signals, the mismatched interval type-2 fuzzy sliding mode controller is designed such that the state trajectories can be driven into the neighborhood of the specified sliding surface. Moreover, the closed-loop fuzzy system is ensured to be mean-square asymptotically stable. Finally, the proposed control scheme is verified by a numerical example.

关键词： Fading channels Fuzzy systems Stability analysis Random variables Numerical models Hidden Markov models Closed loop systems

来源：评论

学校读者我要写书评

暂无评论

Sio2@Dsio2@Tio2 Core-Shell Stationary Phase with Uniform and Tunable Tio2 Thickness for Hplc Separation

SSRN

引用

SSRN 2022年

作者： Wang, Dian Wan, Xiang Wang, Jiafei Mangelings, Debby Sun, Yuanshe Li, Tong Xu, Qin Xie, Fazhi Li, Weihua Qu, Qishu Key Laboratory of Functional Molecule Design and Interface Process Anhui Province Engineering Laboratory of Advanced Building Materials School of Materials Science and Chemical Engineering Anhui Jianzhu University Hefei230601 China Department of Analytical Chemistry Applied Chemometrics and Molecular Modelling Vrije Universiteit Brussel Laarbeeklaan Brussels103-B-1090 Belgium Dalian Elite Analytical Instruments Co. Ltd. Dalian116023 China College of Chemistry and Chemical Engineering Yangzhou University Yangzhou225002 China Anhui Provincial Key Laboratory of Environmental Pollution Control and Resource Reuse School of Environment and Energy Engineering Anhui Jianzhu University Hefei230601 China

In this work, SiO2@dSiO2 core-shell spheres with radial pore structure are used as the support and tetrabutyl orthotitanate (TBOT) is used as the Ti source to coat TiO2 into the pores of the SiO2@dSiO2 shell. Then, by simply prolonging the reaction time, a TiO2 layer with uniform and controllable thickness is obtained on the surface of SiO2@dSiO2 by Ostwald ripening. The thickness of the TiO2 layer can be achieved by controlling the reaction time or controlling the amount of TBOT. When the amount of TBOT is 0.5 mL (0.06 mol L-1), the thickness of the TiO2 layer can be tunable from 15 to about 44 nm by changing the reaction time. When the amount of TBOT is 0.7 mL (0.08 mol L-1), the thickness of the TiO2 layer can be tunable from 21 to about 71 nm by changing the reaction time. C18-derived core-shell spheres with TiO2 layer thicknesses of 40 nm (C18-S@S@TiO2-0.5-60) and 70 nm (C18-S@S@TiO2-0.7-30) were prepared under the conditions of 0.5 mL TBOT for 60 min reaction time and 0.7 mL TBOT for 0.5 h reaction time, respectively. They were used as packings to evaluate the effect of TiO2 layer thickness on chromatographic separation performance. The separation performance of C18-S@S@TiO2-0.5-60 is better than that of C18-S@S@TiO2-0.7-30. The separation efficiency of C18-S@S@TiO2-0.5-60 to fluorene is 115112 plates m-1, and that of C18-S@S@TiO2-0.7-30 is 83189 plates m-1. The two TiO2-modified core-shell packings have good peak symmetry for basic samples, and the asymmetry factors are both less than 1.11. However, the column efficiency of C18-S@S@TiO2-0.5-60 is higher than that of C18-S@S@TiO2-0.7-30. The separation efficiency of C18-S@S@TiO2-0.5-60 for N, N-dimethylaniline is 46714 plates m-1, while that of C18-S@S@TiO2-0.7-30 is only 34685 plates m-1. © 2022, The Authors. All rights reserved.

关键词： Titanium dioxide

来源：评论

学校读者我要写书评

暂无评论

Experimental verification of group non-membership in optical circuits

引用

Photonics Research 2021年第9期9卷 1745-1751页

作者： KAI SUN ZI-JIAN ZHANG FEI MENG BIN CHENG ZHU CAO JIN-SHI XU MAN-HONG YUNG CHUAN-FENG LI GUANG-CAN GUO CAS Key Laboratory of Quantum Information University of Science and Technology of ChinaHefei 230026China CAS Center for Excellence in Quantum Information and Quantum Physics University of Science and Technology of ChinaHefei 230026China Department of Physics Southern University of Science and TechnologyShenzhen 518055China Department of Computer Science The University of Hong KongPokfulamHong Kong SARChina Centre for Quantum Software and Information Faculty of Engineering and Information TechnologyUniversity of Technology SydneySydneyNSW 2007Australia Key Laboratory of Advanced Control and Optimization for Chemical Processes of Ministry of Education East China University of Science and TechnologyShanghai 200237China Shenzhen Institute for Quantum Science and Engineering Southern University of Science and TechnologyShenzhen 518055China Shenzhen Key Laboratory of Quantum Science and Engineering Southern University of Science and TechnologyShenzhen 518055China

The class quantum Merlin–Arthur(QMA),as the quantum analog of nondeterministic polynomial time,contains the decision problems whose YES instance can be verified efficiently with a quantum *** problem of deciding the group non-membership(GNM)of a group element is conjectured to be a member of *** works on the verification of GNM,which still lacks experimental demonstration,required a quantum circuit with O(n~5)group oracle ***,we provide an efficient way to verify GNM problems,in which each quantum circuit only contains O(1)group of oracle calls,and the number of qubits in each circuit is reduced by *** on this protocol,we then experimentally demonstrate the new verification process with a four-element group in an all-optical *** new protocol is validated experimentally by observing a significant completeness-soundness gap between the probabilities of accepting elements in and outside the *** work efficiently simplifies the verification of GNM and is helpful in constructing more quantum protocols based on the near-term quantum devices.

关键词： quantum element polynomial

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：