检索结果-内蒙古大学图书馆

A Markov Chain Monte Carlo approach for Pseudo-Input selection in Sparse Gaussian processes

IFAC-PapersOnLine 2023年第2期56卷 10515-10520页

作者： Anna Scampicchio Sanjay Chandrasekaran Melanie N. Zeilinger Institute for Dynamic Systems & Control Department of Mechanical & Process Engineering ETH Zürich Department of Information Technology & Electrical Engineering ETH Zürich

The effectiveness of non-parametric methods for regression comes at the price of high computational complexity. In fact, these methods scale as O(N 3 ), where N is the number of available data points. One possible option to address this issue consists in introducing a set of fictitious (pseudo-) inputs of size M ≪ N such that the computational effort is reduced to O(M 2 N). To estimate hyper-parameters and pseudo-inputs, a non-convex optimization problem needs to be solved. As opposed to the conventional gradient-based approach used in the literature, this paper proposes a stochastic scheme leveraging Markov Chain Monte Carlo methods. Numerical comparisons show that the latter returns a more efficient set of pseudo-inputs, leading to a superior performance in terms of mean squared error.

关键词： Non-parametric Methods Bayesian Statistics stochastic simulation Monte Carlo Methods

来源：评论

学校读者我要写书评

暂无评论

A Depression Level Classification Model Based on EEG and GCN Network with Domain Generalization

A Depression Level Classification Model Based on EEG and GCN...

引用

第43届中国控制会议

作者： Zhongyi Zhang Chenyang Xu Licheng Jin Huirang Hou Qinghao Meng Tianjin Key Laboratory of Process Measurement and Control Institute of Robotics and Autonomous Systems School of Electrical and Information Engineering Tianjin University

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

Electroencephalography(EEG) contains a wealth of information, including neuron activity, allowing for a partial understanding of the brain's state. As a reliable tool, EEG, combined with deep neural networks, has been increasingly utilized to assist in the detection of depression and has achieved satisfactory results. However, there are still some limitations in the current models. Firstly, it is worth noting that many existing models are binary classification models. These models can determine whether a subject is depressed or not, but they lack the capability to differentiate the severity of depression. Besides, the variations in EEG signals among various individuals have not been thoroughly taken into account, leading to subpar performance when applying the trained model to new subjects. To address the aforementioned issues, we suggest implementing a multi-classification model that utilizes a graph convolutional neural network(GCN) to identify levels of depression. Additionally,to mitigate the problem of imbalanced samples in multi-classification tasks, we introduce a penalty coefficient for the smaller categories. At the same time, the issue of signal discrepancies among subjects was taken into account, leading to the introduction of the domain generalization module. Finally, the depression level identification task on the MODMA and PRED+CT dataset achieved an accuracy of 75.47% and 77.97% respectively, surpassing the performance of the state-of-the-art(SOTA) model. In addition, numerous ablation experiments were conducted to validate the efficacy of each module.

关键词： Depression Level EEG Graph Convolution Network Domain Generalization

来源：评论

学校读者我要写书评

暂无评论

A dynamic methodology for analyzing energy transitional pathways

A dynamic methodology for analyzing energy transitional path...

引用

2022 IEEE Power and Energy Society General Meeting, PESGM 2022

作者： Li, Xiang Schnidrig, Jonas Souttre, Matthieu Marechal, Francois Industrial Process and Energy Systems Engineering Ecole Polytechnique Fédérale de Lausanne Lausanne Switzerland

ISBN: (数字)9781665408233

ISBN: (纸本)9781665408233

The energy system is becoming increasingly complex due to a surge of low carbon technologies driven by an intensified trend of carbon mitigation strategies. How to develop the energy technologies in a smooth and rapid way calls for flexible energy planning models, especially in the context of growing techno-economic-political uncertainties. We propose a novel modeling approach by conditional multi-stage optimization (CMSO) in order to reduce the computational complexity whist keeping the results of high plausibility. This approach allows to simulate the evolution of energy transitional pathways in a flexible way in case the evolution diverts from the planning a posterior. This model is applied onto Switzerland in order to explore the feasibility of energy autonomy and achieving -0.6 tCO2-eq. annual emission per capita in 2050. © 2022 IEEE.

关键词： Energy management

来源：评论

学校读者我要写书评

暂无评论

A Multi-Gas Detection System Based on Convolutional Neural Network

A Multi-Gas Detection System Based on Convolutional Neural N...

引用

第43届中国控制会议

作者： Si-Wen Chen Hong-Yue Li Hui-Rang Hou Qing-Hao Meng Tianjin Key Laboratory of Process Measurement and Control Institute of Robotics and Autonomous Systems School of Electrical and Information Engineering Tianjin University

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

The emission of carbon oxides（COX）, nitrogen oxides（NOX）, sulfur compounds, and volatile organic compounds（VOCs） from vehicles has significantly impacted the air quality, thus posing threats to the environmental resources and human health. This work presents the development of a non-dispersive infrared（NDIR） multi-gas detection system featuring three broadband light sources, a sealed gas chamber, and three multi-channel pyroelectric detectors with a response time shorter than 32 ms. The proposed system is used for constructing an odor dataset comprising five target gases, including carbon dioxide（CO）,carbon monoxide（CO）, nitric oxide（NO）, sulfur dioxide（SO）, and propane（CH）. We perform odor recognition experiments using the traditional machine learning methods, as well as one-dimensional convolutional neural network（1D-CNN） and depthwise separable convolutional neural network（DS-CNN）. The results show that the proposed DS-CNN model achieves an accuracy of 94.75% in recognizing different odors, thus outperforming other classification algorithms. This work demonstrates that the proposed detection system exhibits rapid response and precise recognition, thus establishing it as an effective approach for analyzing the primary components of automobile exhaust.

关键词： Non-Dispersive Infrared Multi-gas Detection System Pattern Recognition Convolutional Neural Network

来源：评论

学校读者我要写书评

暂无评论

Nenofiltration for separation and purification of saccharides from biomass

引用

Frontiers of Chemical Science and engineering 2021年第4期15卷 837-853页

作者： Xianhui Li Sheng Tan Jianquan Luo Manuel Pinelo Process and Systems Engineering Center(PROSYS) Department of Chemical and Biochemical EngineeringTechnical University of DenmarkDK-2800 LyngbyDenmark State Key Laboratory of Biochemical Engineering Institute of Process EngineeringUniversity of Chinese Academy of SciencesChinese Academy of SciencesBeijing 100190China

Saccharide production is critical to the development of biotechnology in the field of food and *** extraction of saccharide from biomass-based hydrolysate mixtures has become a trend due to low cost and abundant biomass *** to conventional methods of fractionation and recovery of saccharides,nanofiltration(NF)has received considerable attention in recent decades because of its high selectivity and low energy consumption and environmental *** this review the advantages and challenges of NF based technology in the separation of saccharides are critically *** membrane processes,i.e.,combining NF with ultrafiltration,can complement each other to provide an efficient approach for removal of unwanted solutes to obtain higher purity ***,use of NF membrane separation technology is limited due to irreversible membrane fouling that results in high capital and operating *** development of NF membrane technology should therefore focus on improving material stability,antifouling ability and saccharide targeting selectivity,as well as on engineering aspects such as process optimisation and membrane module design.

关键词： saccharides nanofiltration membrane hybrid membrane process biomas

来源：评论

学校读者我要写书评

暂无评论

A Web-like Three-dimensional Binder for Silicon Anode in Lithium-ion Batteries

引用

Energy & Environmental Materials 2024年第1期7卷 21-27页

作者： Liyuan Li Tao Li Yifan Sha Baozeng Ren Lan Zhang Suojiang Zhang CAS Key Laboratory of Green Process and Engineering Beijing Key Laboratory of Ionic Liquids Clean ProcessState Key Laboratory of Multiphase Complex SystemsInstitute of Process EngineeringChinese Academy of SciencesBeijing 100190China School of Chemical Engineering Zhengzhou UniversityZhengzhou 450001China Langfang Green Industrial Technology Center Langfang 065001China Henan Key Laboratory of Energy Storage Materials and Processes Zhengzhou Institute of Emerging Industrial TechnologyZhengzhou 450003China

Si anode is of paramount importance for advanced energy-dense lithium-ion batteries(LIBs).However,the large volume change as well as stress generates during its lithiation-delithiation process poses a great challenge to the long-term cycling and hindering its *** this work,a composite binder is prepared with a soft component,guar gum(GG),and a rigid linear polymer,anionic polyacrylamide(APAM).Rich hydroxy,carboxyl,and amide groups on the polymer chains not only enable intermolecular crosslinking to form a web-like binder,A2G1,but also realize strong chemical binding as well as physical encapsulating to Si *** resultant electrode shows limited thickness change of merely 9%on lithiation and almost recovers its original thickness on *** demonstrates high reversible capacity of 2104.3 mAh g^(-1)after 100 cycles at a current density of 1800 mA g^(-1),and in constant capacity(1000 mAh g^(-1))test,it also shows a long life of 392 ***,this soft-hard combining web-like binder illustrates its great potential in the future applications.

关键词： anionic polyacrylamide lithium-ion batteries Si anode thickness change web-like binder

来源：评论

学校读者我要写书评

暂无评论

Hierarchically microporous membranes for highly energy-efficient gas separations

Industrial Chemistry & Materials

引用

Industrial Chemistry & Materials 2023年第3期1卷 376-387页

作者： Shuangjiang Luo Tianliang Han Can Wang Ying Sun Hongjun Zhang Ruilan Guo Suojiang 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 Sciences(CAS)Beijing 100190China State Key Laboratory of Particle Detection and Electronics University of Science and Technology of ChinaHefei 230026China Department of Chemical and Biomolecular Engineering University of Notre DameNotre DameIN 46556USA Longzihu New Energy Laboratory Zhengzhou 450000China Henan University Jinming RoadKaifeng475004China

The implementation of synthetic polymer membranes in gas separations,ranging from natural gas sweetening,hydrogen separation,helium recovery,carbon capture,oxygen/nitrogen enrichment,etc.,has stimulated the vigorous development of high-performance membrane ***,size-sieving types of synthetic polymer membranes are frequently subject to a trade-off between permeability and selectivity,primarily due to the lack of ability to boost fractional free volume while simultaneously controlling the micropore size ***,we review recent research progress on microporosity manipulation in high-free-volume polymeric gas separation membranes and their gas separation performance,with an emphasis on membranes with hourglass-shaped or bimodally distributed ***-of-the-art strategies to construct tailorable and hierarchically microporous structures,microporosity characterization,and microcavity architecture that govern gas separation performance are systematically summarized.

关键词： Gas separation membranes Hierarchical microporosity Micropore size distribution Configurational free volume Solution-diffusion mechanism

来源：评论

学校读者我要写书评

暂无评论

Effects of surface roughness on fatigue behavior of additively manufactured stainless steel 316L 8

Effects of surface roughness on fatigue behavior of additive...

引用

2022 8th International Forum on Manufacturing Technology and engineering Materials, IFEMMT 2022

作者： Zeng, Guowei Ye, Wanrong Liu, Lei Department of Engineering Mechanics Wuhan University of Science and Technology Wuhan430065 China Hubei Province Key Laboratory of Systems Science in Metallurgical Process Wuhan430081 China

Surface roughness plays an important role which affects the fatigue performance of additively manufactured metal components. Surface roughness generally contains micro-notches which form stress concentration and significantly deteriorate the fatigue life. Based on nonlinear elastoplasticity finite element (FE) analyses, the roughness model of additively manufactured stainless steel 316L (SS316L) was performed, and the cyclic behavior of surface notch root material under different fatigue stress loads was captured. The stress concentration factor on the selected critical surface position is calculated and the notch root strain analysis are proved by depending on the applied load level. Finally two distinct deformation modes are found: elastic shakedown and ratcheting deformation. © Published under licence by IOP Publishing Ltd.

关键词： Surface roughness

来源：评论

学校读者我要写书评

暂无评论

A Primal-Dual SGD Algorithm for Distributed Nonconvex Optimization

引用

IEEE/CAA Journal of Automatica Sinica 2022年第5期9卷 812-833页

作者： Xinlei Yi Shengjun Zhang Tao Yang Tianyou Chai Karl Henrik Johansson Division of Decision and Control Systems School of Electrical Engineering and Computer ScienceKTH Royal Institute of Technologyand also affiliated with the Digital FuturesStockholm 10044Sweden Department of Electrical Engineering University of North TexasDentonTX 76203 USA IEEE State Key Laboratory of Synthetical Automation for Process Industries Northeastern UniversityShenyang 110819China

The distributed nonconvex optimization problem of minimizing a global cost function formed by a sum of n local cost functions by using local information exchange is *** problem is an important component of many machine learning techniques with data parallelism,such as deep learning and federated *** propose a distributed primal-dual stochastic gradient descent(SGD)algorithm,suitable for arbitrarily connected communication networks and any smooth(possibly nonconvex)cost *** show that the proposed algorithm achieves the linear speedup convergence rate O(1/(√nT))for general nonconvex cost functions and the linear speedup convergence rate O(1/(nT)) when the global cost function satisfies the Polyak-Lojasiewicz(P-L)condition,where T is the total number of *** also show that the output of the proposed algorithm with constant parameters linearly converges to a neighborhood of a global *** demonstrate through numerical experiments the efficiency of our algorithm in comparison with the baseline centralized SGD and recently proposed distributed SGD algorithms.

关键词： Distributed nonconvex optimization linear speedup Polyak-Lojasiewicz(P-L)condition primal-dual algorithm stochastic gradient descent

来源：评论

学校读者我要写书评

暂无评论

An Interview with Federico Capasso

引用

ACS PHOTONICS 2024年第3期11卷 811-815页

作者： Quidant, Romain Aumiller, William Capasso, Federico Nanophotonic Systems Laboratory Department of Mechanical and Process Engineering ETH Zürich 8092 Zürich Switzerland American Chemical Society 1155 Sixteenth Street N.W. Washington D.C. 20036 United States John A. Paulson School of Engineering and Applied Sciences Harvard University Cambridge Massachusetts 02138 United States

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：