检索结果-南通市图书馆

An attention-based teacher-student model for multivariate short-term landslide displacement prediction incorporating weather forecast data

引用

Journal of Mountain Science 2024年第8期21卷 2739-2753页

作者： CHEN Jun HU Wang ZHANG Yu qiu Hongzhi WANG Renchao Sichuan Artificial Intelligence Research Institute Yibin 644000China School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengdu 611731China School of Architecture and Civil Engineering Chengdu UniversityChengdu 610106China

Predicting the displacement of landslide is of utmost practical importance as the landslide can pose serious threats to both human life and ***,traditional methods have the limitation of random selection in sliding window selection and seldom incorporate weather forecast data for displacement prediction,while a single structural model cannot handle input sequences of different lengths at the same *** order to solve these limitations,in this study,a new approach is proposed that utilizes weather forecast data and incorporates the maximum information coefficient(MIC),long short-term memory network(LSTM),and attention mechanism to establish a teacher-student coupling model with parallel structure for short-term landslide displacement *** MIC,a suitable input sequence length is selected for the LSTM *** investigate the influence of rainfall on landslides during different seasons,a parallel teacher-student coupling model is developed that is able to learn sequential information from various time series of different *** teacher model learns sequence information from rainfall intensity time series while incorporating reliable short-term weather forecast data from platforms such as China Meteorological Administration(CMA)and Reliable Prognosis(https://***)to improve the model’s expression capability,and the student model learns sequence information from other time *** attention module is then designed to integrate different sequence information to derive a context vector,representing seasonal temporal attention ***,the predicted displacement is obtained through a linear *** proposed method demonstrates superior prediction accuracies,surpassing those of the support vector machine(SVM),LSTM,recurrent neural network(RNN),temporal convolutional network(TCN),and LSTM-Attention *** achieves a mean absolute error(MAE)of 0.072 mm,root mean square error(RMSE)of 0.096 mm,and pearson correlation coefficients(PC

关键词： Landslide prediction MIC LSTM Attention mechanism Teacher Student model Prediction stability and interpretability

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

ChatGPT: potential, prospects, and limitations

引用

Frontiers of Information Technology & Electronic Engineering 2024年第1期25卷 6-11页

作者： Jie ZHOU Pei KE Xipeng qiu Minlie HUANG Junping ZHANG School of Computer Science Fudan UniversityShanghai 200433China Department of Computer Science and Technology Tsinghua UniversityBeijing 100084China Shanghai Key Laboratory of Intelligent Information Processing Shanghai 200433China

Recently,OpenAI released Chat Generative Pre-trained Transformer(ChatGPT)(Schulman et al.,2022)(https://***),which has attracted considerable attention from the industry and academia because of its impressive *** is the first time that such a variety of open tasks can be well solved within one large language *** better understand ChatGPT,we briefly introduce its history,discuss its advantages and disadvantages,and point out several potential ***,we analyze its impact on the development of trustworthy artificial intelligence,conversational search engine,and artificial general intelligence.

关键词： artificial limitations intelligence

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Phase-field lattice-Boltzmann study on fully coupled thermal-solute-convection dendrite growth of Al-Cu alloy

引用

China Foundry 2024年第2期21卷 125-136页

作者： Yin-qi qiu Meng-wu Wu Xun-peng Qin Shou-mei Xiong Hubei Key Laboratory of Advanced Technology for Automotive Components Wuhan University of TechnologyWuhan 430070China Hubei Longzhong Laboratory Xiangyang 441000HubeiChina School of Materials Science and Engineering Tsinghua UniversityBeijing 100084China

Dendrite growth is a complex liquid-solid phase transition process involving multiple physical factors.A phase-field lattice-Boltzmann method was developed to simulate the two-and three-dimension dendrite growth of Al-Cu *** effect of fully coupled thermal-solute-convection interaction on the dendrite growth was investigated by incorporating a parallel-adaptive mesh refinement algorithm into the numerical *** accurately reproducing the latent heat release,solute diffusion and convective transport behaviors at the liquidsolid interface,the interaction mechanism among thermal-solute-convection transport as well as their coupling effects on the dendrite growth dynamics were *** simulation results show that the release of latent heat slows down the dendrite growth rate,and both natural and forced convection disrupt the symmetrical growth of *** combination makes the growth of dendrites more complex,capturing important physical aspects such as recalescence,dendrite tip splitting,dendrite tilting,dendrite remelting,and solute plume in the simulation *** on the robustness and powerful ability of the numerical model,the formation mechanisms of these physical aspects were revealed.

关键词： simulation phase field dendrite growth thermal-solute-convection interaction

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

First-principles study on the electronic structure of Pb_(10−x)Cu_(x)(PO_(4))_(6)O(x=0,1)

引用

Journal of Materials Science & Technology 2024年第4期171卷 66-70页

作者： Junwen Lai Jiangxu Li Peitao Liu Yan Sun Xing-qiu Chen Shenyang National Laboratory for Materials Science Institute of Metal ResearchChinese Academy of SciencesShenyang 110016China School of Materials Science and Engineering University of Science and Technology of ChinaShenyang 110016China

Recently,Lee et *** the experimental discovery of room-temperature ambient-pressure super-conductivity in a Cu-doped lead-apatite(LK-99)(arXiv:2307.12008,arXiv:2307.12037).Remarkably,the claimed superconductivity can persist up to 400 K at ambient *** the experimental im-plication,the electronic structure of LK-99 has not yet been ***,we investigate the electronic structures of LK-99 and its parent compound using first-principles calculations,aiming to elucidate the doping effects of *** results reveal that the parent compound Pb_(10)(PO_(4))_(6)O is an insulator,while Cu doping induces an insulator-metal transition and thus volume *** band structures of LK-99 around the Fermi level are featured by a half-filled flat band and a fully-occupied flat *** two very flat bands arise from both the 2p orbitals of 1/4-occupied O atoms and the hybridization of the 3d orbitals of Cu with the 2p orbitals of its nearest-neighboring O ***,we observe four van Hove singularities on these two flat ***,we show that the flat band structures can be tuned by including electronic correlation effects or by doping different *** find that among the considered doping elements(Ni,Cu,Zn,Ag,and Au),both Ni and Zn doping result in the gap opening,whereas Au exhibits doping effects more similar to Cu than *** work establishes a foundation for fu-ture studies to investigate the role of unique electronic structures of LK-99 in its claimed superconducting properties.

关键词： First-principles calculations Density functional theory Electronic structur e Superconductivity Flat bands Strongly correlated electrons

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Accelerating BERT inference with GPU-efficient exit prediction

引用

Frontiers of Computer Science 2024年第3期18卷 31-42页

作者： Lei LI Chengyu WANG Minghui qiu Cen CHEN Ming GAO Aoying ZHOU Shanghai Engineering Research Center of Big Data Management School of Data Science and EngineeringEast China Normal UniversityShanghai 200062China Alibaba Group Hangzhou 311121China KLATASDS-MOE School of StatisticsEast China Normal UniversityShanghai 200062China

BERT is a representative pre-trained language model that has drawn extensive attention for significant improvements in downstream Natural Language Processing(NLP)*** complex architecture and massive parameters bring BERT competitive performance but also result in slow speed at model inference *** speed up BERT inference,FastBERT realizes adaptive inference with an acceptable drop in accuracy based on knowledge distillation and the early-exit ***,many factors may limit the performance of FastBERT,such as the teacher classifier that is not knowledgeable enough,the batch size shrinkage and the redundant computation of student *** overcome these limitations,we propose a new BERT inference method with GPU-Efficient Exit Prediction(GEEP).GEEP leverages the shared exit loss to simplify the training process of FastBERT from two steps into only one step and makes the teacher classifier more knowledgeable by feeding diverse Transformer outputs to the teacher *** addition,the exit layer prediction technique is proposed to utilize a GPU hash table to handle the token-level exit layer distribution and to sort test samples by predicted exit *** this way,GEEP can avoid batch size shrinkage and redundant computation of student *** results on twelve public English and Chinese NLP datasets prove the effectiveness of the proposed *** source codes of GEEP will be released to the public upon paper acceptance.

关键词： BERT FastBERT inference acceleration model distillation early exit text classification

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Porous TiFe_(2) intermetallic compound fabricated via elemental powder reactive synthesis

引用

International Journal of Minerals,Metallurgy and Materials 2024年第4期31卷 764-772页

作者： Qian Zhao Zhenli He Yuehui He Yue qiu Zhonghe Wang Yao Jiang State Key Laboratory of Powder Metallurgy Powder Metallurgy Research InstituteCentral South UniversityChangsha 410083China

Porous intermetallics show potential in the field of filtration and separation as well as in the field of ***,porous Ti Fe2intermetallics were fabricated by the reactive synthesis of elemental *** phase transformation and pore formation of porous TiFe2intermetallics were investigated,and its corrosion behavior and hydrogen evolution reaction(HER)performance in alkali solution were *** TiFe2intermetallics with porosity in the range of 34.4%-56.4%were synthesized by the diffusion reaction of Ti and Fe elements,and the pore formation of porous TiFe2intermetallic compound is the result of a combination of the bridging effect and the Kirkendall *** porous TiFe2samples exhibit better corrosion resistance compared with porous 316L stainless steel,which is related to the formation of uniform nanosheets on the surface that hinder further corrosion,and porous TiFe2electrode shows the overpotential of 220.6 and 295.6 mV at 10 and 100 mA·cm-2,suggesting a good catalytic *** synthesized porous Fe-based intermetallic has a controllable pore structure as well as excellent corrosion resistance,showing its potential in the field of filtration and separation.

关键词： TiFe2 intermetallic compound porous materials reactive synthesis corrosion behavior hydrogen evolution reaction

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Unveiling the size effect of nitrogen-doped carbon-supported copper-based catalysts on nitrate-to-ammonia electroreduction

引用

Nano Research 2024年第4期17卷 2438-2443页

作者： Ran Li Taotao Gao Wenxi qiu Minghao Xie Zhaoyu Jin Panpan Li College of Materials Science and Engineering Sichuan UniversityChengdu 610065China Institute for Advanced Study Chengdu UniversityChengdu 610106China Materials Science and Engineering Program and Walker Department of Mechanical Engineering The University of Texas at AustinAustinTexas 78712USA Institute of Fundamental and Frontier Sciences University of Electronic Science and Technology of ChinaChengdu 610054China

The electrocatalytic nitrate reduction reaction(NitRR)represents a promising approach toward achieving economically and environmentally sustainable ***,it remains a challenge to regulate the size effect of electrocatalysts to optimize the catalytic activity and ammonia ***,the Cu-based catalysts were tailored at the atomic level to exhibit a size gradient ranging from single-atom catalysts(SACs,0.15–0.35 nm)to single-cluster catalysts(SCCs,1.0–2.8 nm)and nanoparticles(NPs,20–30 nm),with the aim of studying the size effect for the NO_(3)^(-)-to-NH_(3) reduction ***,the Cu SCCs exhibit enhanced metal–substrate and metal–metal interactions by taking advantageous features of Cu SACs and Cu ***,Cu SCCs achieve exceptional electrocatalytic performance for the NitRR with a maximum Faradaic efficiency of ca.96%NH_(3)and the largest yield rate of ca.1.99 mg·h^(-1)·cm^(-2) at-0.5 V *** hydrogen electrode(RHE).The theoretical calculation further reveals the size effect and coordination environment on the high catalytic activity and selectivity for the *** work provides a promising various size-controlled design strategy for aerogel-based catalysts effectively applied in various electrocatalytic reactions.

关键词： nitrate electroreduction ammonia electrosynthesis size effect single-cluster catalyst

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Buried interface management via bifunctional NH_(4)BF_(4)towards efficient CsPbI_(2)Br solar cells with a V_(oc)over 1.4 V

引用

Journal of Energy Chemistry 2024年第2期89卷 364-370,I0009页

作者： Fazheng qiu Ming-Hua Li Jinpeng Wu Jin-Song Hu School of Materials Science and Engineering NingboTech UniversityNingbo 315100ZhejiangChina Beijing National Laboratory for Molecular Sciences(BNLMS) Institute of ChemistryChinese Academy of SciencesBeijing 100190China College of Chemical Engineering Beijing Advanced Innovation Center for Soft Matter Science and EngineeringBeijing University of Chemical TechnologyBeijing 100029China School of Chemical Sciences University of Chinese Academy of SciencesBeijing 100049China

CsPbI_(2)Br perovskite solar cells(PSCs)have drawn tremendous attention due to their suitable bandgap,excellent photothermal stability,and great potential as an ideal candidate for top cells in tandem solar ***,the abundant defects at the buried interface and perovskite layer induce severe charge recombination,resulting in the open-circuit voltage(V_(oc))output and stability much lower than ***,a novel buried interface management strategy is developed to regulate interfacial carrier dynamics and CsPbI_(2)Br defects by introducing ammonium tetrafluoroborate(NH_(4)BF_(4)),thereby resulting in both high CsPbI_(2)Br crystallization and minimized interfacial energy ***,NH_(4)^(+)ions could preferentially heal hydroxyl groups on the SnO_(2)surface and balance energy level alignment between SnO_(2)and CsPbI_(2)Br,enhancing charge transport efficiency,while BF_(4)^(-)anions as a quasi-halogen regulate crystal growth of CsPbI_(2)Br,thus reducing perovskite ***,it is proved that eliminating hydroxyl groups at the buried interface enhances the iodide migration activation energy of CsPbI_(2)Br for strengthening the phase *** a result,the optimized CsPbI_(2)Br PSCs realize a remarkable efficiency of 17.09%and an ultrahigh V_(oc)output of 1.43 V,which is one of the highest values for CsPbI_(2)Br PSCs.

关键词： Inorganic perovskite Buried interface Defect Stability Open-circuit voltage loss

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Algorithms and statistical analysis for linear structured weighted total least squares problem

引用

Geodesy and Geodynamics 2024年第2期15卷 177-188页

作者： Jian Xie Tianwei qiu Cui Zhou Dongfang Lin Sichun Long School of Earth Science and Spatial Information Engineering Hunan University of Science and TechnologyXiangtan 411201China College of Science Central South University of Forestry and TechnologyChangsha 410018China National-Local Joint Engineering Laboratory of Geo-spatial Information Technology Hunan University of Science and TechnologyXiangtan 411201China

Weighted total least squares(WTLS)have been regarded as the standard tool for the errors-in-variables(EIV)model in which all the elements in the observation vector and the coefficient matrix are contaminated with random ***,in many geodetic applications,some elements are error-free and some random observations appear repeatedly in different positions in the augmented coefficient *** is called the linear structured EIV(LSEIV)*** kinds of methods are proposed for the LSEIV model from functional and stochastic *** the one hand,the functional part of the LSEIV model is modified into the errors-in-observations(EIO)*** the other hand,the stochastic model is modified by applying the Moore-Penrose inverse of the cofactor *** algorithms are derived through the Lagrange multipliers method and linear *** estimation principles and iterative formula of the parameters are proven to be *** first-order approximate variance-covariance matrix(VCM)of the parameters is also derived.A numerical example is given to compare the performances of our proposed three algorithms with the STLS ***,the least squares(LS),total least squares(TLS)and linear structured weighted total least squares(LSWTLS)solutions are compared and the accuracy evaluation formula is proven to be feasible and ***,the LSWTLS is applied to the field of deformation analysis,which yields a better result than the traditional LS and TLS estimations.

关键词： Linear structured weighted total least squares Errors-in-variables Errors-in-observations Functional modelmodification Stochastic model modification Accuracyevaluation

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Coaxial Wet Spinning of Boron Nitride Nanosheet‑Based Composite Fibers with Enhanced Thermal Conductivity and Mechanical Strength

引用

Nano-Micro Letters 2024年第2期16卷 126-138页

作者： Wenjiang Lu Qixuan Deng Minsu Liu Baofu Ding Zhiyuan Xiong Ling qiu Tsinghua Shenzhen International Graduate School(TSIGS) Tsinghua UniversityShenzhen 518055People’s Republic of China Monash Suzhou Research Institute(MSRI) Monash UniversitySuzhou 215000People’s Republic of China Faculty of Materials Science and Engineering/Institute of Technology for Carbon Neutrality Shenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhen 518055People’s Republic of China Shenzhen Key Laboratory of Energy Materials for Carbon Neutrality Shenzhen 518055People’s Republic of China School of Light Industry and Engineering South China University of TechnologyGuangzhou 510614People’s Republic of China

Hexagonal boron nitride nanosheets(BNNSs)exhibit remarkable thermal and dielectric ***,their self-assembly and alignment in macroscopic forms remain challenging due to the chemical inertness of boron nitride,thereby limiting their performance in applications such as thermal *** this study,we present a coaxial wet spinning approach for the fabrication of BNNSs/polymer composite fibers with high nanosheet *** composite fibers were prepared using a superacid-based solvent system and showed a layered structure comprising an aramid core and an aramid/BNNSs ***,the coaxial fibers exhibited significantly higher BNNSs alignment compared to uniaxial aramid/BNNSs fibers,primarily due to the additional compressive forces exerted at the core-sheath interface during the hot drawing *** a BNNSs loading of 60 wt%,the resulting coaxial fibers showed exceptional properties,including an ultrahigh Herman orientation parameter of 0.81,thermal conductivity of 17.2 W m^(-1)K^(-1),and tensile strength of 192.5 *** results surpassed those of uniaxial fibers and previously reported BNNSs composite fibers,making them highly suitable for applications such as wearable thermal management *** findings present a promising strategy for fabricating high-performance composite fibers based on BNNSs.

关键词： Boron nitride nanosheets Coaxial fiber Interfacial compression Nanosheet aligning Wearable thermal management

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

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：