检索结果-南通市图书馆

Data-driven Wasserstein distributionally robust chance-constrained optimization for crude oil scheduling under uncertainty

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Chemical Engineering 2024年第5期69卷 152-166页

作者： xin Dai Liang zhao Renchu He Wenli du Weimin Zhong Zhi Li Feng Qian Key Laboratory of Smart Manufacturing in Energy Chemical Process Ministry of EducationEast China University of Science and TechnologyShanghai 200237China Engineering Research Center of Process System Engineering Ministry of EducationEast China University of Science and TechnologyShanghai 200237China

Crude oil scheduling optimization is an effective method to enhance the economic benefits of oil *** uncertainties,including uncertain demands of crude distillation units(Cdus),might make the production plans made by the traditional deterministic optimization models infeasible.A data-driven Wasserstein distributionally robust chance-constrained(WDRCC)optimization approach is proposed in this paper to deal with demand uncertainty in crude oil ***,a new deterministic crude oil scheduling optimization model is developed as the basis of this *** Wasserstein distance is then used to build ambiguity sets from historical data to describe the possible realizations of probability distributions of uncertain demands.A cross-validation method is advanced to choose suitable radii for these ambiguity *** deterministic model is reformulated as a WDRCC optimization model for crude oil scheduling to guarantee the demand constraints hold with a desired high probability even in the worst situation in ambiguity *** proposed WDRCC model is transferred into an equivalent conditional value-at-risk representation and further derived as a mixed-integer nonlinear programming *** case studies from a real-world refinery are conducted to show the effectiveness of the proposed ***-of-sample tests demonstrate that the solution of the WDRCC model is more robust than those of the deterministic model and the chance-constrained model.

关键词： Distributions Model Optimization Crude oil scheduling Wasserstein distance Distributionally robust chance constraints

Principal components of nuclear mass models

在线全文

学校读者我要写书评

暂无评论

Science China(Physics,Mechanics & Astronomy) 2024年第7期67卷 65-71页

作者： xin-Hui Wu Pengwei zhao Department of Physics Fuzhou UniversityFuzhou 350108China State Key Laboratory of Nuclear Physics and Technology School of PhysicsPeking UniversityBeijing 100871China

Principal component analysis(PCA)is employed to extract the principal components(PCs)present in nuclear mass models for the first *** effects from different nuclear mass models are reintegrated and reorganized in the extracted *** PCs are recombined to build new mass models,which achieve better accuracy than the original theoretical mass *** comparison indicates that using the PCA approach,the effects contained in different mass models can be collaborated to improve nuclear mass predictions.

关键词： nuclear mass principal component analysis nuclear models statistical methods

A sub-grid scale model for Burgers turbulence based on the artificial neural network method

在线全文

学校读者我要写书评

暂无评论

Theoretical & Applied Mechanics Letters 2024年第3期14卷 162-165页

作者： xin zhao Kaiyi Yin Department of Mechanics Beijing Institute of TechnologyBeijing 100081China

The present study proposes a sub-grid scale model for the one-dimensional Burgers turbulence based on the neuralnetwork and deep learning *** filtered data of the direct numerical simulation is used to establish thetraining data set,the validation data set,and the test data *** artificial neural network(ANN)methodand Back Propagation method are employed to train parameters in the *** developed ANN is applied toconstruct the sub-grid scale model for the large eddy simulation of the Burgers turbulence in the *** proposed model well predicts the time correlation and the space correlation of the Burgers turbulence.

关键词： Artificial neural network Back propagation method Burgers turbulence Large eddy simulation Sub-grid scale model

A Modeling Study Recurrent Tuberculosis Towards End TB Strategy—China,2025-2035

在线全文

学校读者我要写书评

暂无评论

China CDC weekly 2024年第35期6卷 885-890页

作者： Tao Li xin du Zhongwei Jia Yanlin zhao Department of Epidemiology and Biostatistics School of Public HealthPeking UniversityBeijingChina Chinese Center for Disease Control and Prevention BeijingChina National Key Laboratory of Intelligent Tracking and Forecasting for Infectious Diseases Chinese Center for Disease Control and PreventionBeijingChina Center for Intelligent Public Health Institute for Artificial IntelligencePeking UniversityBeijingChina Department of Global Health School of Public HealthPeking UniversityBeijingChina Center for Drug Abuse Control and Prevention National Institute of Health Data SciencePeking UniversityBeijingChina

Summary What is already known about this topic?The recurrence of tuberculosis(TB)following successful treatment presents a significant *** is added by this report?Achieving the global End TB Strategy milestones and targets with the current strategies in China is ***,interventions following recovery to prevent recurrence,in conjunction with preventive treatment for latent TB infection(LTBI),will aid in meeting these objectives.

关键词： Strategy tuberculosis treatment

Quantum self-attention neural networks for text classification

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第4期67卷 301-313页

作者： Guangxi LI Xuanqiang zhao xin WANG Institute for Quantum Computing Baidu Research Centre for Quantum Software and Information University of Technology Sydney QICI Quantum Information and Computation Initiative Department of Computer ScienceThe University of Hong Kong Thrust of Artificial Intelligence Information HubHong Kong University of Science and Technology(Guangzhou)

An emerging direction of quantum computing is to establish meaningful quantum applications in various fields of artificial intelligence, including natural language processing(NLP). Although some efforts based on syntactic analysis have opened the door to research in quantum NLP(QNLP), limitations such as heavy syntactic preprocessing and syntax-dependent network architecture make them impracticable on larger and real-world data sets. In this paper, we propose a new simple network architecture, called the quantum selfattention neural network(QSANN), which can compensate for these limitations. Specifically, we introduce the self-attention mechanism into quantum neural networks and then utilize a Gaussian projected quantum self-attention serving as a sensible quantum version of self-attention. As a result, QSANN is effective and scalable on larger data sets and has the desirable property of being implementable on near-term quantum devices. In particular, our QSANN outperforms the best existing QNLP model based on syntactic analysis as well as a simple classical self-attention neural network in numerical experiments of text classification tasks on public data sets. We further show that our method exhibits robustness to low-level quantum noises and showcases resilience to quantum neural network architectures.

关键词： quantum neural networks self-attention natural language processing text classification parameterized quantum circuits

Intracellular RNA Labeling Technologies for the Analysis of RNA Biology

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Chemistry 2024年第7期42卷 790-801页

作者： Ruiqi zhao xin Fang Xiaocheng Weng Department of Clinical Laboratory Center for Gene DiagnosisDepartment of NeurosurgeryZhongnan Hospital of Wuhan UniversityWuhanHubei 430071China College of Chemistryand Molecular Sciences Key Laboratory of Biomedical Polymers-Ministry of EducationWuhan UniversityWuhan Hubei 430072China

As a cornerstone of the central dogma of molecular biology,RNA plays vital roles in living *** the past few decades,many RNA labeling technologies have been developed to elucidate the biological function of *** technologies have signifi-cantly advanced our understanding of RNA secondary structure,localization,and ***,taking advantage of these innovative RNA labeling approaches,plenty of tool kits have been devised for the regulation of RNA-related biological process,such as gene expression and gene *** this review,we primarily focus on an array of intracellular RNA labeling methods,encom-passing chemical probes-based labeling,metabolic labeling,and proximity-dependent *** also provide a brief overview of their applications in the research of RNA ***,the perspectives of RNA labeling are also discussed.

关键词： RNA Chemical probes Metabolic labeling Proximity-dependent labeling RNA structures Gene sequencing RNA recognition

Probabilistic seismic inversion based on physics-guided deep mixture density network

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Petroleum Science 2024年第3期21卷 1611-1631页

作者： Qian-Hao Sun zhao-Yun Zong xin Li National Key Laboratory of Deep Oil and Gas China University of Petroleum(East China)Qingdao266580ShandongChina Laoshan Laboratory Qingdao266580ShandongChina CNOOC Research Institute Ltd. Beijing100028China

Deterministic inversion based on deep learning has been widely utilized in model parameters *** by logging data,seismic data,wavelet and modeling operator,deterministic inversion based on deep learning can establish nonlinear relationships between seismic data and model ***,seismic data lacks low-frequency and contains noise,which increases the non-uniqueness of the *** conventional inversion method based on deep learning can only establish the deterministic relationship between seismic data and parameters,and cannot quantify the uncertainty of *** order to quickly quantify the uncertainty,a physics-guided deep mixture density network(PG-DMDN)is established by combining the mixture density network(MDN)with the deep neural network(DNN).Compared with Bayesian neural network(BNN)and network dropout,PG-DMDN has lower computing cost and shorter training time.A low-frequency model is introduced in the training process of the network to help the network learn the nonlinear relationship between narrowband seismic data and low-frequency *** addition,the block constraints are added to the PG-DMDN framework to improve the horizontal continuity of the inversion *** illustrate the benefits of proposed method,the PG-DMDN is compared with existing semi-supervised inversion *** synthetic data examples of Marmousi II model are utilized to quantify the influence of forward modeling part,low-frequency model,noise and the pseudo-wells number on inversion results,and prove the feasibility and stability of the proposed *** addition,the robustness and generality of the proposed method are verified by the field seismic data.

关键词： Deep learning Probabilistic inversion Physics-guided Deep mixture density network

Polyp-Canal Reconstruction Reveals Evolution Toward Complexity in Corals

在线全文

学校读者我要写书评

暂无评论

Research 2024年第1期2023卷 417-428页

作者： Yixin Li xin Liao xin Wang Yuanchao Li Hongwei zhao Yunpeng zhao Junyuan Chen Chunpeng He Zuhong Lu State Key Laboratory of Bioelectronics School of Biological Science and Medical EngineeringSoutheast UniversityNanjing 210096China State Key Laboratory of Coastal and Offshore Engineering Dalian University of TechnologyDalian 116024China Guangxi Key Lab of Mangrove Conservation and Utilization Guangxi Mangrove Research CenterGuangxi Academy of SciencesBeihai 536000China Hainan Academy of Ocean and Fishery Sciences Haikou 571126China State Key Laboratory of Marine Resources Utilization in South China Sea Hainan UniversityHaikou 570228China Nanjing Institute of Geology and Palaeontology Chinese Academy of Sciences39 East Beijing RoadNanjing 210008China

Modern scleractinian corals are classified into robust,complex,and basal clades through comparative molecular ***,only few morphological or biological criteria can systematically determine the evolutionary trajectories of these major scleractinian coral ***,we obtained the structural information of 21 scleractinian coral species representing robust and complex clades:High-resolution micro-computed tomography was used to reconstruct the polyp-canal systems in their colonies and to visualize the dynamic polyp growth *** found that the emergence of mesh-like canals may distinguish representatives of complex and robust *** differences in polyp-canal connections suggest distinct evolutionary trajectories among coral species:The formation of the canal network promoted the development of more complex coral structures,and coral polyps within this network formed calices of very similar volume,following precise axial growth *** influence of individual polyps on the coral colony becomes less significant as coral structures become more complex,and coral species with more complicated polyp-canal systems occupied niches more *** work supplements current evolutionary studies on reef-building corals,providing insight for further studies on coral growth patterns.

关键词： Coral representing directions

Transfer force perception skills to robot‐assisted laminectomy via imitation learning from human demonstrations

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

CAAI Transactions on Intelligence Technology 2024年第4期9卷 903-916页

作者： Meng Li Xiaozhi Qi xiaoguang Han Ying Hu Bing Li Yu zhao Jianwei Zhang Harbin Institute of Technology ShenzhenChina Shenzhen Institute of Advanced Technology Chinese Academy of SciencesShenzhenChina Shenzhen Key Laboratory of Minimally Invasive Surgical Robotics and System Shenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhenChina Beijing Jishuitan Hospital Capital Medical UniversityBeijingChina Department of Orthopedics Peking Union Medical College HospitalChinese Academy of Medical Sciences and Peking Union Medical CollegeBeijingChina University of Hamburg Hamburg22527Germany

A comparative study of two force perception skill learning approaches for robot‐assisted spinal surgery,the impedance model method and the imitation learning(IL)method,is *** impedance model method develops separate models for the surgeon and patient,incorporating spring‐damper and bone‐grinding *** surgeons'feature parameters are collected and mapped using support vector regression and image navi-gation *** imitation learning approach utilises long short‐term memory networks(LSTM)and addresses accurate data labelling challenges with custom *** results demonstrate skill recognition rates of 63.61%-74.62%for the impedance model approach,relying on manual feature ***,the imitation learning approach achieves a force perception recognition rate of 91.06%,outperforming the impedance model on curved bone *** findings demonstrate the potential of imitation learning to enhance skill acquisition in robot‐assisted spinal surgery by eliminating the laborious process of manual feature extraction.

关键词： learning(artificial intelligence) medical applications medical signal processing robotics