检索结果-内蒙古大学图书馆

第37届中国控制会议

作者： Yawen Xiao Jun Wu Zongli Lin Xiaodong Zhao Department of Automation Shanghai Jiao Tong Universityand Key Laboratory of System Control and Information Processing of Ministry of Education The Center for Bioinformatics and Computational Biology Shanghai Key Laboratory of Regulatory Biologythe Institute of Biomedical Sciences and School of Life SciencesEast China Normal University Charles L.Brown Department of Electrical and Computer Engineering University of Virginia School of Biomedical Engineering Shanghai Jiao Tong University

Breast cancer is the most often detected cancer in women. At the same time, it is one of the most curable types of cancer if diagnosed early. With the development of the detection technology, a growing amount of clinical data and highdimensional features can be used for breast cancer diagnosis. The high-dimensional data contributes to advances in the diagnostic technology, but also incurs a large amount of computational redundancy. Thus, extracting important information and reducing the feature dimension is critical to effective prediction and an accurate treatment ***, the previous works for breast cancer diagnosis are mainly based on labeled data that is difficult to obtain. To address this issue, in this paper, we demonstrate a new scheme, which integrates a deep learning based unsupervised feature extraction algorithm, the stacked auto-encoders, with a support vector machine model（SAE-SVM）, for breast cancer diagnosis. The stacked auto-encoders with the greedy layerwise pre-training and an improved momentum update algorithm is applied to capture essential information and extract necessary features of the original data. Then, a support vector machine model is employed to classify the samples with new features into malignant or benign tumors. The proposed method was tested on the Wisconsin Diagnostic Breast Cancer data set. The performance is evaluated using various measures and compared with the previously published results. The comparison results show that the proposed SAE-SVM method improves the accuracy to 98.25% and outperforms the other methods. The deep learning based unsupervised feature extraction significantly improves the performance of classification and provides a promising approach to breast cancer diagnosis.

关键词： Deep learning auto-encoder feature extraction breast cancer diagnosis unlabeled data

来源：评论

学校读者我要写书评

暂无评论

Breast Cancer Diagnosis Using an Unsupervised Feature Extraction Algorithm Based on Deep Learning

Breast Cancer Diagnosis Using an Unsupervised Feature Extrac...

引用

Chinese control Conference

作者： Yawen Xiao Jun Wu Zongli Lin Xiaodong Zhao Department of Automation Key Laboratory of System Control and Information Processing of Ministry of Education Shanghai China The Center for Bioinformatics and Computational Biology East China Normal University Shanghai China Charles L. Brown Department of Electrical and Computer Engineering University of Virginia Charlottesville VA U.S.A School of Biomedical Engineering Shanghai Jiao Tong University Shanghai China

Breast cancer is the most often detected cancer in women. At the same time, it is one of the most curable types of cancer if diagnosed early. With the development of the detection technology, a growing amount of clinical data and high-dimensional features can be used for breast cancer diagnosis. The high-dimensional data contributes to advances in the diagnostic technology, but also incurs a large amount of computational redundancy. Thus, extracting important information and reducing the feature dimension is critical to effective prediction and an accurate treatment decision. However, the previous works for breast cancer diagnosis are mainly based on labeled data that is difficult to obtain. To address this issue, in this paper, we demonstrate a new scheme, which integrates a deep learning based unsupervised feature extraction algorithm, the stacked auto-encoders, with a support vector machine model (SAE-SVM), for breast cancer diagnosis. The stacked auto-encoders with the greedy layer-wise pre-training and an improved momentum update algorithm is applied to capture essential information and extract necessary features of the original data. Then, a support vector machine model is employed to classify the samples with new features into malignant or benign tumors. The proposed method was tested on the Wisconsin Diagnostic Breast Cancer data set. The performance is evaluated using various measures and compared with the previously published results. The comparison results show that the proposed SAE-SVM method improves the accuracy to 98.25% and outperforms the other methods. The deep learning based unsupervised feature extraction significantly improves the performance of classification and provides a promising approach to breast cancer diagnosis.

关键词： Breast cancer Feature extraction Machine learning Support vector machines Electronic mail Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Topological-darkness-assisted phase regulation for atomically thin meta-optics

arXiv

引用

arXiv 2019年

作者： Wang, Yingwei Deng, Zi-Lan Hu, Dejiao Yuan, Jian Ou, Qingdong Qin, Fei Zhang, Yinan Ouyang, Xu Peng, Bo Cao, Yaoyu Guan, Bai-Ou Zhang, Yupeng He, Jun Qiu, Chengwei Bao, Qiaoliang Li, Xiangping Guangdong Provincial Key Laboratory of Optical Fiber Sensing and Communications Institute of Photonics Technology Jinan University Guangzhou510632 China Hunan Key Laboratory for Super-microstructure and Ultrafast Process School of Physics and Electronics Central South University 932 South Lushan Road Changsha Hunan410083 China College of Physics and Electronic Information Huaibei Normal University Huaibei235000 China Key Laboratory of Optoelectronic Devices and Systems of Ministry of Education and Guangdong Province College of Electronic Science and Technology Shenzhen University Shenzhen518060 China Monash University ClaytonVIC3800 Australia National Engineering Research Center of Electromagnetic Radiation Control Materials State Key Laboratory of Electronic Thin Films and Integrated Devices School of Microelectronics and Solid State Electronics University of Electronic Science and Technology of China Chengdu610054 China Department of Electrical and Computer Engineering National University of Singapore 4 Engineering Drive 3 117583 Singapore

Two-dimensional (2D) noble-metal dichalcogenides 1, 2 have emerged as a new platform for the realization of versatile flat optics with a considerable degree of miniaturization. However, light field manipulation at the atomic scale is widely considered unattainable since the vanishing thickness and intrinsic losses of 2D materials completely suppress both resonances and phase accumulation effects. Empowered by conventionally perceived adverse effects of intrinsic losses, we show that the structured PtSe2 films integrated with a uniform substrate can regulate nontrivial singular phase and realize atomic-thick meta-optics in the presence of topological darkness 3, 4. We experimentally demonstrate a series of atomic-thick binary meta-optics that allows angle-robust and high unit-thickness diffraction efficiency of 0.96%/nm in visible frequencies, given its thickness of merely 4.3 nm. Our results unlock the potential of a new class of 2D flat optics for light field manipulation at an atomic thickness. Copyright © 2019, The Authors. All rights reserved.

关键词： Platinum compounds

来源：评论

学校读者我要写书评

暂无评论

Near-real-time monitoring of global CO2 emissions reveals the effects of the COVID-19 pandemic (vol 11, 5172, 2020)

引用

NATURE COMMUNICATIONS 2020年第1期11卷 5172页

作者： Liu, Zhu Ciais, Philippe Deng, Zhu Lei, Ruixue Davis, Steven J. Feng, Sha Zheng, Bo Cui, Duo Dou, Xinyu Zhu, Biqing Guo, Rui Ke, Piyu Sun, Taochun Lu, Chenxi He, Pan Wang, Yuan Yue, Xu Wang, Yilong Lei, Yadong Zhou, Hao Cai, Zhaonan Wu, Yuhui Guo, Runtao Han, Tingxuan Xue, Jinjun Boucher, Olivier Boucher, Eulalie Chevallier, Frederic Tanaka, Katsumasa Wei, Yiming Zhong, Haiwang Kang, Chongqing Zhang, Ning Chen, Bin Xi, Fengming Liu, Miaomiao Breon, Francois-Marie Lu, Yonglong Zhang, Qiang Guan, Dabo Gong, Peng Kammen, Daniel M. He, Kebin Schellnhuber, Hans Joachim Department of Earth System Science Tsinghua University Beijing China. zhuliu@***. Laboratoire des Sciences du Climat et de l'Environnement LSCE CEA CNRS UVSQ Centre d'Etudes Orme de Merisiers Gif-sur-Yvette France. Department of Earth System Science Tsinghua University Beijing China. Department of Meteorology and Atmospheric Science The Pennsylvania State University University Park PA USA. Department of Earth System Science University of California Irvine 3232 Croul Hall Irvine CA USA. Division of Geological and Planetary Sciences California Institute of Technology Pasadena CA USA. Jiangsu Key Laboratory of Atmospheric Environment Monitoring and Pollution Control Collaborative Innovation Center of Atmospheric Environment and Equipment Technology School of Environmental Science and Engineering Nanjing University of Information Science & Technology Nanjing China. Key Laboratory of Land Surface Pattern and Simulation Institute of Geographical Sciences and Natural Resources Research Chinese Academy of Sciences Beijing China. Climate Change Research Center Institute of Atmospheric Physics Chinese Academy of Sciences Beijing China. Key Laboratory of Middle Atmosphere and Global Environment Observation Institute of Atmospheric Physics Chinese Academy of Sciences Beijing China. School of Environment Tsinghua University Beijing China. School of Mathematical School Tsinghua University Beijing China. Department of Mathematical Sciences Tsinghua University Beijing China. Center of Hubei Cooperative Innovation for Emissions Trading System Wuhan China. Institut Pierre-Simon Laplace Sorbonne Université / CNRS Paris France. Université Paris Dauphine Place du Maréchal de Lattre de Tassigny 75016 Paris France. Center for Energy and Environmental Policy Research Beijing Institute of Technology Beijing China. Department of Electrical Engineering the State Key Lab of Control and Simulation of Power Systems and Generation Equipment Institute for National Governance and G

A Correction to this paper has been published: https://***/10.1038/s41467-020-20254-5

关键词： Climate sciences Atmospheric science Environmental sciences Environmental social sciences

来源：评论

学校读者我要写书评

暂无评论

Machine discovery of partial differential equations from spatiotemporal data

arXiv

引用

arXiv 2019年

作者： Yuan, Ye Li, Junlin Li, Liang Jiang, Frank Tang, Xiuchuan Zhang, Fumin Liu, Sheng Goncalves, Jorge Voss, Henning U. Li, Xiuting Kurths, Jürgen Ding, Han School of Artificial Intelligence and Automation State Key Laboratory of Digital Manufacturing Equipments and Technology Huazhong University of Science and Technology Wuhan430074 China School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan430074 China School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm11428 Sweden School of Mechanical Science and Engineering Huazhong University of Science and Technology Wuhan430074 China School of Electrical and Computer Engineering Georgia Institute of Technology Atlanta30332 United States School of Power and Mechanical Engineering Wuhan University Wuhan430074 China Department of Engineering University of Cambridge CambridgeCB2 1PZ United Kingdom Luxembourg Centre for Systems Biomedicine University of Luxembourg BelvauxL-4367 Luxembourg Citigroup Biomedical Imaging Center Weill Cornell Medical College New York10021 United States Research Domain IV - Transdisciplinary Concepts & Methods Potsdam Institute for Climate Impact Research Potsdam14473 Germany School of Mechanical Science and Engineering State Key Laboratory of Digital Manufacturing Equipments and Technology Huazhong University of Science and Technology Wuhan430074 China

The study presents a general framework for discovering underlying Partial Differential Equations (PDEs) using measured spatiotemporal data. The method, called Sparse Spatiotemporal System Discovery (S3d), decides which physical terms are necessary and which can be removed (because they are physically negligible in the sense that they do not affect the dynamics too much) from a pool of candidate functions. The method is built on the recent development of Sparse Bayesian Learning;which enforces the sparsity in the to-be-identified PDEs, and therefore can balance the model complexity and fitting error with theoretical guarantees. Without leveraging prior knowledge or assumptions in the discovery process, we use an automated approach to discover ten types of PDEs, including the famous Navier-Stokes and sine-Gordon equations, from simulation data alone. Moreover, we demonstrate our data-driven discovery process with the Complex Ginzburg-Landau Equation (CGLE) using data measured from a traveling-wave convection experiment. Our machine discovery approach presents solutions that has the potential to inspire, support and assist physicists for the establishment of physical laws from measured spatiotemporal data, especially in notorious fields that are often too complex to allow a straightforward establishment of physical law, such as biophysics, fluid dynamics, neuroscience or nonlinear optics. Copyright © 2019, The Authors. All rights reserved.

关键词： Nonlinear optics

来源：评论

学校读者我要写书评

暂无评论

Modeling and analysis of secondary controlled virtual synchronous generator with dynamic droop for microgrid

Modeling and analysis of secondary controlled virtual synchr...

引用

2017 IEEE Conference on Energy Internet and Energy System Integration, EI2 2017

作者： Yan, Weihang Gao, David Wenzhong Zhang, Fang Cheng, Lin Yan, Shijie Department of Electrical and Computer Engineering University of Denver Denver United States State Key Laboratory of Control and Simulation of Power Systems and Generation Equipment Tsinghua University Beijing China College of Information Science and Technology Northeastern University Shenyang China

ISBN: (纸本)9781538614273

In this paper, a dynamic droop mechanism is proposed to damp the synchronizing oscillation that exists in a virtual synchronous generator based distributed generator system without varying the steady-state active-power-loop droop coefficient. In order to eliminate the steady-state error introduced due to load changes or generator trips, a distributed secondary controller based on extremum seeking is employed so that microgrid frequency can be restored to nominal value. Besides, the small-signal model of virtual synchronous generator system is presented under d-q reference frame where virtual synchronous generator is deployed as a PV node. Moreover, the linearized system model of virtual synchronous generator with dynamic droop mechanism is derived and its advantage is discussed. Finally, a modified IEEE 14 bus microgrid system is established in Matlab/Simulink platform. Simulation results demonstrate the validity and feasibility of the proposed method. © 2017 IEEE.

关键词： Dynamics

来源：评论

学校读者我要写书评

暂无评论

Global control for a class of inherently nonlinear systems with uncertain measurements

引用

IFAC-PapersOnLine 2017年第1期50卷 11571-11576页

作者： Zha W. Qian C. Zhai J. Fei S. School of Mechanical Electronic & Information Engineering China University of Mining & Technology (Beijing) Beijing 100083 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing China 210096 China Department of Electrical and Computer Engineering The University of Texas at San Antonio San Antonio TX 78249 United States

This paper considers the problem of global stabilization for a class of high-order nonlinear systems whose states cannot be measured accurately and the uncertain parameters occur in the powers of the measurement functions. Based on the notion of homogeneity with monotone degrees (HWMD), the conditions on the uncertain measurement powers that are related to the system powers will be given so that the homogeneous weights and degrees can be determined to guarantee the solvability of this problem. By adopting the adding a power integrator technique, a measurement feedback controller is proposed to globally stabilize the nonlinear system under different sensors with certain conditions. © 2017

关键词： Adding a power integrator homogeneity with monotone degrees inherently nonlinear systems robust control uncertain measurements

来源：评论

学校读者我要写书评

暂无评论

Decentralized adaptive stabilization of large-scale active-passive modular systems

Decentralized adaptive stabilization of large-scale active-p...

引用

AIAA Guidance, Navigation, and control Conference, 2017

作者： Gruenwald, Benjamin C. Arabi, Ehsan Yucelen, Tansel Chakravarthy, Animesh McNeely, Drew Balakrishnan, S.N. Mechanical Engineering Department Laboratory for Autonomy Control Information and Systems University of South Florida TampaFL33620 United States Electrical Engineering and Computer Science Department Wichita State University WichitaKS67260 United States Mechanical and Aerospace Engineering Department Missouri University of Science and Technology RollaMO65409 United States

ISBN: (数字)9781624104503

ISBN: (纸本)9781624104503

Large-scale active-passive modular systems consist of physically interconnected modules, where local control signals can be applied only to a subset of these modules entitled as active modules and the rest of these modules entitled as passive modules are not subject to any control signal. This paper focuses on a new decentralized adaptive stabilization framework for large-scale active-passive modular systems such that guarantees on not only overall system stability but also practical (i.e., user-defined) performance of active modules are established. An illustrative numerical example is provided to demonstrate the efficacy of the proposed decentralized adaptive stabilization framework. © 2017, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.

关键词： System stability

来源：评论

学校读者我要写书评

暂无评论

A deep learning-based remaining useful life prediction approach for bearings

arXiv

引用

arXiv 2018年

作者： Cheng, Cheng Ma, Guijun Zhang, Yong Sun, Mingyang Teng, Fei Ding, Han Yuan, Ye The Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China The State Key Laboratory of Digital Manufacturing Equipment and Technology Huazhong University of Science and Technology Wuhan430074 China The School of Mechanical Science and Engineering Huazhong University of Science and Technology Wuhan430074 China School of Information Science and Engineering Wuhan University of Science and Technology Wuhan430081 China The College of Control Science and Engineering Zhejiang University Hangzhou310007 China The Department of Electrical & Electronic Engineering Imperial College London LondonSW7 2AZ United Kingdom

In industrial applications, nearly half the failures of motors are caused by the degradation of rolling element bearings (REBs). Therefore, accurately estimating the remaining useful life (RUL) for REBs is of crucial importance to ensure the reliability and safety of mechanical systems. To tackle this challenge, model-based approaches are limited by the complexity of mathematical modeling. Conventional data-driven approaches, on the other hand, require massive efforts to extract the degradation features and construct the health index. In this paper, a novel data-driven framework is proposed to exploit the adoption of deep convolutional neural networks (CNN) in predicting the RULs of bearings. More concretely, raw vibrations of training bearings are first processed using the Hilbert-Huang transform to construct a novel nonlinear degradation energy indicator which can be used as the training label. The CNN is then employed to identify the hidden pattern between the extracted degradation energy indicator and the raw vibrations of training bearings, which makes it possible to estimate the degradation of the test bearings automatically. Finally, testing bearings’ RULs are predicted through using a ǫ-support vector regression model. The superior performance of the proposed RUL estimation framework, compared with the state-of-the-art approaches, is demonstrated through the experimental results. The generality of the proposed CNN model is also validated by performance test on other bearings undergoing different operating conditions. Copyright © 2018, The Authors. All rights reserved.

关键词： Hilbert-Huang transform

来源：评论

学校读者我要写书评

暂无评论

Data based reconstruction of complex multiplex networks

arXiv

引用

arXiv 2018年

作者： Ma, Chuang Chen, Han-Shuang Li, Xiang Lai, Ying-Cheng Zhang, Hai-Feng School of Mathematical Science Anhui University Hefei230601 China School of Physics and Material Science Anhui University Hefei230601 China Adaptive Networks and Control Laboratory Department of Electronic Engineering Center of Smart Networks and Systems School of Information Science and Engineering Fudan University Shanghai200433 China School of Electrical Computer and Energy Engineering Arizona State University TempeAZ85287 United States Department of Communication Engineering North University of China Taiyuan Shanxi030051 China

It has been recognized that many complex dynamical systems in the real world require a description in terms of multiplex networks, where a set of common, mutually connected nodes belong to distinct network layers and play a different role in each layer. In spite of recent progress towards data based inference of single-layer networks, to reconstruct complex systems with a multiplex structure remains largely open. We articulate a mean-field based maximum likelihood estimation framework to solve this outstanding and challenging problem. We demonstrate the power of the reconstruction framework and characterize its performance using binary time series from a class of prototypical duplex network systems that host two distinct types of spreading dynamics. In addition to validating the framework using synthetic and real-world multiplex networks, we carry out a detailed analysis to elucidate the impacts of structural and dynamical parameters as well as noise on the reconstruction accuracy and robustness. Copyright © 2018, The Authors. All rights reserved.

关键词： Network layers

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：