检索结果-内蒙古大学图书馆

13th IEEE Data Driven Control and Learning systems Conference, DDCLS 2024

作者： Chen, Zhang Zhu, Wei Li, Jingsui Bian, Hanlin Pei, Chao School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing400065 China Chongqing University of Posts and Telecommunications Key Laboratory of Intelligent Analysis and Decision on Complex Systems Chongqing400065 China

ISBN: (纸本)9798350361674

Neural networks are capable function approximators for data, but their lack of interpretability poses challenges. Physical-informed Polynomial Neural Ordinary Differential Equations (PIPNODEs) are proposed. They combine the constraints of prior knowledge of the data with interpretable Polynomial Neural Ordinary Differential Equations (PolyNODEs) to discover or approximate the governing equations. In this work, Neural Ordinary Differential Equations (NODEs) are categorized into two layers: a physical-informed term, which represents the priori knowledge of the data, and a discrepancy term, which is derived from the approximation of PolyNODEs. Pruning strategies are also used to remove redundant terms with coefficients lower than a certain threshold. We demonstrate the effectiveness and flexibility of this framework in a series of numerical algorithms with varying levels of prior knowledge. We found that having correct but incomplete physical information accelerates training and approaching thresholds compared to having incorrect physical information. © 2024 IEEE.

关键词： data modeling discprepancy modeling interpretability Neural Ordinary Differential Equations physics-informed machine learning polynomial neural network

来源：评论

学校读者我要写书评

暂无评论

Parameter Inversion of High-Dimensional Chaotic systems Using Neural Ordinary Differential Equations 13

Parameter Inversion of High-Dimensional Chaotic Systems Usin...

引用

13th IEEE Data Driven Control and Learning systems Conference, DDCLS 2024

作者： Bian, Hanlin Zhu, Wei Chen, Zhang Jingsui, L. Pei, Chao Key Laboratory of Intelligent Analysis and Decision on Complex Systems Chongqing University of Posts and Telecommunications Chongqing400065 China School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing400065 China

ISBN: (纸本)9798350361674

High-dimensional chaotic systems possess complex structural characteristics, which have potential research value in fields like encrypted communication and chaos control. The inverse problem of parameters in high-dimensional chaotic systems is of significant importance for a profound understanding of the dynamic properties of such systems. This article takes a departure from neural ordinary differential equations and embeds the structural dynamics of the dynamical systems to the parameter inversion of high-dimensional chaotic systems. Numerical experiments on different high-dimensional chaotic systems indicate that neural ordinary differential equations perform exceptionally well in solving these inversion problems, with low errors and strong robustness. © 2024 IEEE.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Ce^(3+):Lu_(3)Al_(5)O_(12)–Al_(2)O_(3) optical nanoceramic scintillators elaborated via a low-temperature glass crystallization route

引用

Journal of Advanced Ceramics 2023年第2期12卷 268-278页

作者： Jie FU Shaowei FENG Yongchang GUO Ying ZHANG Cécile GENEVOIS Emmanuel VERON Mathieu ALLIX Jianqiang LI School of Materials Science and Engineering University of Science and Technology BeijingBeijing 100083China State Key Laboratory of Multiphase Complex Systems Institute of Process EngineeringChinese Academy of SciencesBeijing 100190China CNRS CEMHTI UPR 3079Universitéd’OrléansOrléans 45071France University of Chinese Academy of Sciences Beijing 100049China

Transparent Ce:lutetium aluminum garnet(Ce:Lu_(3)A_(l5)O_(12),Ce:LuAG)ceramics have been regarded as potential scintillator materials due to their relatively high density and atomic number(Zeff).However,the current Ce:LuAG ceramics exhibit a light yield much lower than the expected theoretical value due to the inevitable presence of LuAl antisite defects at high sintering *** work demonstrates a low-temperature(1100℃)synthetic strategy for elaborating transparent LuAG–Al_(2)O_(3) nanoceramics through the crystallization of 72 mol%Al_(2)O_(3)–28 mol%Lu_(2)O_(3)(ALu28)bulk *** biphasic nanostructure composed of LuAG and Al_(2)O_(3) nanocrystals makes up the whole ceramic *** of Al_(2)O_(3) is distributed among LuAG grains,and the rest is present inside the LuAG *** dense biphasic LuAG–Al_(2)O_(3) nanoceramics are highly transparent from the visible region to mid-infrared(MIR)region,and particularly the transmittance reaches 82%at 780 ***,LuAl antisite defect-related centers are completely undetectable in X-ray excited luminescence(XEL)spectra of Ce:LuAG–Al_(2)O_(3) nanoceramics with 0.3–1.0 at%*** light yield of 0.3 at%Ce:LuAG–Al_(2)O_(3) nanoceramics is estimated to be 20,000 ph/MeV with short 1μs shaping time,which is far superior to that of commercial Bi_(4)Ge_(3)O_(12)(BGO)single *** results show that a low-temperature glass crystallization route provides an alternative approach for eliminating the antisite defects in LuAG-based ceramics,and is promising to produce garnet-based ceramic materials with excellent properties,thereby meeting the demands of advanced scintillation applications.

关键词： glass crystallization garnet antisite defects Lu_(3)Al_(5)O_(12)-Al_(2)O_(3)(LuAG-Al_(2)O_(3))transparent ceramics nanoceramics scintillation

来源：评论

学校读者我要写书评

暂无评论

AI4S Based on DeSci: Reference Model and Research Issues

AI4S Based on DeSci: Reference Model and Research Issues

引用

2023 IEEE International Conference on systems, Man, and Cybernetics, SMC 2023

作者： Ding, Wenwen Li, Juanjuan Qin, Rui Guan, Sangtian Wang, Fei-Yue Institute of Automation Chinese Academy of Sciences The State Key Laboratory for Management and Control of Complex Systems The State Key Laboratory of Multimodal Artificial Intelligence Systems Beijing China Macau University of Science and Technology Faculty of Innovation Engineering Macau China Institute of Automation The State Key Laboratory for Management and Control of Complex Systems Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798350337020

The rise of Artificial Intelligence for science (AI4S) has highlighted the importance and urgency of ensuring open-ness, fairness, impartiality, diversity, and sustainability in scientific systems. Existing scientific systems, referred to as Centralized science (CeSci), are built on centralized organizational structures and top-down institutional frameworks, which are lagging behind the development and practical requirements of AI4S. To address these limitations, AI4S needs to embrace a new scientific organizational and operational paradigm, namely Decentralized science (DeSci). It can provide strong support to AI4S via effectively addressing issues such as information silos, biases, unfair distribution, and monopolies and promoting multidisciplinary, interdisciplinary, and trans disciplinary cooperation in science. Based on these considerations, this paper presents the framework of AI4S based on DeSci and explores its potential application scenarios and research issues. The research can provide effective guidance for the development of scientific systems. © 2023 IEEE.

关键词： Artificial Intelligence for science (AI4S) ChatGPT Decentralized Autonomous Organizations and Operations (DAOs) Decentralized science (De-Sci) Generative Artificial Intelligence (GAI) Intelligent science

来源：评论

学校读者我要写书评

暂无评论

Separation of chitin from shrimp shells enabled by transition metal salt aqueous solution and ionic liquid

引用

Chinese Journal of Chemical Engineering 2023年第1期53卷 133-141页

作者： Mi Feng Bin He Xinyan Chen Junli Xu Xingmei Lu Cai Jia Jian Sun Key Laboratory of Molecular Medicine and Biotherapy Ministry of Industry and Information TechnologySchool of Life SciencesBeijing Institute of TechnologyBeijing 100081China Key Laboratory of Medical Molecule Science and Pharmaceutics Engineering Ministry of Industry and Information TechnologyAdvanced Research Institute of Multidisciplinary ScienceBeijing Institute of TechnologyBeijing 100081China CAS Key Laboratory of Green Process and Engineering State Key Laboratory of Multiphase Complex SystemsState Key Laboratory of Biochemical EngineeringBeijing Key Laboratory of Ionic Liquids Clean ProcessInstitute of Process EngineeringChinese Academy of SciencesBeijing 100190China School of Chemical and Engineering University of Chinese Academy of SciencesBeijing 100049China Innovation Academy for Green Manufacture Chinese Academy of SciencesBeijing 100190China

Chitin is a widely used important industrial polymer mainly from shrimp shells, but its commercial preparation is under the great challenge of serious pollution due to the requirement of HCl and Na ***, we demonstrated that high purity chitin can be obtained from waste shrimp shells(WSSs) by cascade separation with transition metal salt aqueous solution and ionic liquid(IL). Firstly, calcium carbonate of WSSs was effectively removed in the metal salt aqueous solution driven by the ion exchange interaction. Subsequently, 1-butyl-3-methylimidazolium chloride([Bmim]Cl) had bifunctional abilities to remove residual protein and introduced metal salts simultaneously by hydrogen bonding and coordination interactions. The key experimental factors affecting the separation process were systematically studied, including the type of metal salts, temperature, and [Bmim]Cl loading. After sequential treatment with a 20%(mass) Ni SO4aqueous solution at 130 ℃ and [Bmim]Cl at 150 ℃, the purity of a-chitin can be up to 96.5%(mass) that meets commercial requirements. The use of metal salts with higher coordination ability makes the preparation of chitin no longer depend on the commonly acid-base reaction, which is conducive to the preservation of chitin structure.

关键词： Chitin Ionic liquids Transition metal salts Separation Sustainability

来源：评论

学校读者我要写书评

暂无评论

A Novel Modeling Method for Power Flow Calculation of Integrated Enegy Network 13

A Novel Modeling Method for Power Flow Calculation of Integr...

引用

2022 IEEE International Conference on Power systems technology, POWERCON 2022

作者： Tian, Liting Zhou, Xuyan Lin, Cheng Yin, Zheng Lin, Ende Equipment Tsinghua University State Key Laboratory of Control and Simulation of Power Systems and Generation Beijing China Institute of Science and Technology China Three Gorges Corporation State Key Laboratory of Control and Simulation of Power Systems Beijing China

ISBN: (数字)9781665417754

ISBN: (纸本)9781665417754

Multi-energy systems may contain integrated energy networks such as electrical, gas and heating networks. The differences in the physical characteristics of each energy network make it difficult to solve power flows of the integrated energy networks. Based on the concept of energy flow, this paper realizes the unified modeling of electrical, gas and heating network to describe the stable equilibrium relationship. The basic equations for energy flow calculation contains Kirchhoff's Current Law equations, Kirchhoff's Voltage Law equations, and energy flow efficiency equations. A weighted directed graph is used to model the total system with networks and energy hubs. The proposed model is used for the joint power flow solution of the multi-energy system with Newton-Raphson algorithm. Finally, the validity and accuracy of the model are verified in a test system. © 2022 IEEE.

关键词： Newton-Raphson method

来源：评论

学校读者我要写书评

暂无评论

Non-fragile Joint State and Fault Estimation for complex Networks with Missing Measurements and Switching Topology 41

Non-fragile Joint State and Fault Estimation for Complex Net...

引用

第41届中国控制会议

作者： Pingping Gao Jun Hu Chaoqing Jia Zhihui Wu Department of Mathematics Harbin University of Science and Technology School of Automation Harbin University of Science and Technology Heilongjiang Provincial Key Laboratory of Optimization Control and Intelligent Analysis for Complex Systems Harbin University of Science and Technology

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

In this paper,a non-fragile joint state and fault estimation problem is investigated for time-varying complex networks with switching topology and randomly occurring nonlinearities under the missing *** phenomena of the switching topology,randomly occurring nonlinearities and missing measurements are described by three mutually independent Bernoulli random variables,where the uncertain occurrence probabilities are *** addition,the parameter perturbations of the estimator gain matrix are characterized by a set of zero-mean multiplicative noises.A novel time-varying estimation method is designed and an upper bound of estimation error covariance matrix is obtained by solving two recursive matrix ***,the desired estimator gain matrix is parameterized by minimizing the trace of the obtained upper ***,a sufficient condition is given to ensure the boundedness of the upper bound matrix by using the mathematical induction ***,a simulation study is given to verify the feasibility of the proposed estimation scheme.

关键词： Time-varying complex networks switching topology randomly occurring nonlinearities missing measurements uncertain occurrence probabilities joint estimation

来源：评论

学校读者我要写书评

暂无评论

FedECCR: Federated Learning Method with Encoding Comparison and Classification Rectification 19th

FedECCR: Federated Learning Method with Encoding Comparison...

引用

19th EAI International Conference on Collaborative Computing: Networking, Applications and Worksharing, CollaborateCom 2023

作者： Zeng, Yan Zheng, Hui Wang, Xin Zhang, Beibei Zhou, Mingyao Zhang, Jilin Ren, YongJian School of Computer Science and Technology Hangzhou Dianzi University Hangzhou310018 China Key Laboratory for Modeling and Simulation of Complex Systems Ministry of Education Hangzhou310018 China Data Security Governance Zhejiang Engineering Research Center Hangzhou310018 China Zhejiang Lab Hangzhou311100 China Hangzhou Huawei Communication Technology Co. Ltd. Hangzhou310052 China

ISBN: (纸本)9783031545306

Federated learning is a distributed training method that integrates multi-party data information using privacy-preserving technologies through dispersed client data sets to jointly construct a global model under the coordination of a central server. However, in practical applications, there is a high degree of data distribution skewness among clients, which causes the optimization direction of the client models to diverge, resulting in model bias and reducing the accuracy of the global model. Existing methods require the calculation and transmission of much information to correct the optimization direction of the client models, or only roughly limit the deviation of the client models end-to-end, ignoring targeted processing of the internal structure of the model, resulting in unclear improvement effects. To address these problems, we propose a federated optimization algorithm FedECCR based on encoding contrast and classification correction. This algorithm divides the model into an encoder and a classifier. It utilizes prototype contrastive training of the model encoder and unbiased classification correction of the classifier. This approach notably improves the accuracy of the global model while maintaining low communication costs. We conducted experiments on multiple data sets to evaluate the validity of our method, and the quantified results showed that FedECCR can improve the global model classification accuracy by approximately 1% to 6% compared to FedAvg, FedProx, and MOON. © ICST Institute for Computer sciences, Social Informatics and Telecommunications Engineering 2024.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Tetris-Style Stacking Process to Tailor the Orientation of Carbon Fiber Scaffolds for Efficient Heat Dissipation

引用

Nano-Micro Letters 2023年第9期15卷 310-324页

作者： Shida Han Yuan Ji Qi Zhang Hong Wu Shaoyun Guo Jianhui Qiu Fengshun Zhang The State Key Laboratory of Polymer Materials Engineering Sichuan Provincial Engineering Laboratory of Plastic/Rubber Complex Processing TechnologyPolymer Research Institute of Sichuan UniversityChengdu 610065People’s Republic of China Department of Mechanical Engineering Faculty of Systems Science and TechnologyAkita Prefectural University015-0055AkitaJapan Institute of Chemical Materials China Academy of Engineering PhysicsMianyang 621900People’s Republic of China

As the miniaturization of electronic devices and complication of electronic packaging,there are growing demands for thermal interfacial materials with enhanced thermal conductivity and the capability to direct the heat toward heat sink for highly efficient heat ***-based carbon fiber(CF)with ultrahigh axial thermal conductivity and aspect ratios exhibits great potential for developing thermally conductive composites as ***,it is still hard to fabricate composites with aligned carbon fiber in a general approach to fully utilize its excellent axial thermal conductivity in specific ***,three types of CF scaffolds with different oriented structure were developed via magnetic field-assisted Tetris-style stacking and carbonization *** regulating the magnetic field direction and initial stacking density,the self-supporting CF scaffolds with horizontally aligned(HCS),diagonally aligned and vertically aligned(VCS)fibers were *** embedding the polydimethylsiloxane(PDMS),the three composites exhibited unique heat transfer properties,and the HCS/PDMS and VCS/PDMS composites presented a high thermal conductivity of 42.18 and 45.01 W m^(−1)K^(−1)in fiber alignment direction,respectively,which were about 209 and 224 times higher than that of *** excellent thermal conductivity is mainly ascribed that the oriented CF scaffolds construct effective phonon transport pathway in the *** addition,fishbone-shaped CF scaffold was also produced by multiple stacking and carbonization process,and the prepared composites exhibited a controlled heat transfer path,which can allow more versatility in the design of thermal management system.

关键词： Carbon fiber Magnetic field Thermal management Thermally conductive composites

来源：评论

学校读者我要写书评

暂无评论

The effect of protic ionic liquids incorporation on CO_(2) separation performance of Pebax-based membranes

引用

Chinese Journal of Chemical Engineering 2022年第3期35卷 169-176页

作者： Haiyan Jiang Lu Bai Bingbing Yang Shaojuan Zeng Haifeng Dong Xiangping Zhang CAS Key Laboratory of Green Process and Engineering State Key Laboratory of Multiphase Complex SystemsBeijing Key Laboratory of Ionic Liquids Clean ProcessInstitute of Process EngineeringChinese Academy of SciencesBeijing 100190China School of Future Technology University of Chinese Academy of SciencesBeijing 100049China Advanced Energy Science and Technology Guangdong Laboratory Huizhou 516003China

The separation of carbon dioxide(CO_(2))is of great importance for environment protection and gas resource *** ionic liquids(ILs)-based gas separation membrane provides a new chance for efficient CO_(2)separation,while high permeability and selectivity of membranes is a great *** this study,the influence of two protic ILs with different anion([TMGH][Im]and[TMGH][PhO])on the CO_(2)separation performance of the prepared ILs/Pebax blended membranes were systematically investigated at different *** results showed the CO_(2)permeability exhibits the rising trend for ILs/Pebax blended membranes with the increment of IL ***,the[TMGH][Im]with low viscosity and high CO_(2)absorption capacity leads to the blended membranes showing better CO_(2)permeability and ideal CO_(2)selectivity than that of membranes with[TMGH][PhO]at high IL ***,with operating temperature increasing,the gas permeability of 20%(mass)[TMGH][Im]/Pebax blended membrane increases due to the decreasing viscosity of IL and the rising chain mobility of ***,the gas selectivity shows decreasing trend because CO_(2)absorption capacity obviously decreased at higher temperature.

关键词： CO_(2) Protic ionic liquids Membranes Pebax

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：