检索结果-南通市图书馆

Application of the improved dung beetle optimizer,muti-head attention and hybrid deep learning algorithms to groundwater depth prediction in the Ningxia area,China

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

Atmospheric and Oceanic Science Letters 2025年第1期18卷 18-23页

作者： Jiarui Cai Bo Sun Huijun Wang Yi Zheng Siyu Zhou Huixin Li Yanyan Huang Peishu Zong Collaborative Innovation Center on forecast and Evaluation of Meteorological Disasters/Key Laboratory of Meteorological Disaster Ministry of Education/Joint International Research Laboratory of Climate and Environment ChangeNanjing University of Information Science and TechnologyNanjingChina Southern Marine Science and Engineering Guangdong Laboratory(zhuhai) ZhuhaiChina China Meteorological Administration Key Laboratory of Transportation MeteorologyNanjingChina Jiangsu Meteorological Observatory NanjingChina

Due to the lack of accurate data and complex parameterization,the prediction of groundwater depth is a chal-lenge for numerical *** learning can effectively solve this issue and has been proven useful in the prediction of groundwater depth in many *** this study,two new models are applied to the prediction of groundwater depth in the Ningxia area,*** two models combine the improved dung beetle optimizer(DBO)algorithm with two deep learning models:The Multi-head Attention-Convolution Neural network-Long Short Term Memory networks(MH-CNN-LSTM)and the Multi-head Attention-Convolution Neural network-Gated Recurrent Unit(MH-CNN-GRU).The models with DBO show better prediction performance,with larger R(correlation coefficient),RPD(residual prediction deviation),and lower RMSE(root-mean-square error).Com-pared with the models with the original DBO,the R and RPD of models with the improved DBO increase by over 1.5%,and the RMSE decreases by over 1.8%,indicating better prediction *** addition,compared with the multiple linear regression model,a traditional statistical model,deep learning models have better prediction performance.

关键词： Groundwater depth Multi-head attention Improved dung beetle optimizer CNN-LSTM CNN-GRU Ningxia

Hybrid method integrating machine learning and particle swarm optimization for smart chemical process operations

在线全文

学校读者我要写书评

暂无评论

Frontiers of Chemical Science and Engineering 2022年第2期16卷 274-287页

作者： Haoqin Fang Jianzhao Zhou Zhenyu Wang Ziqi Qiu Yihua Sun Yue Lin Ke Chen Xiantai Zhou Ming Pan School of Chemical Engineering and technology Sun Yat-Sen UniversityZhuhai 519082China School of Mathematics Sun Yat-Sen UniversityZhuhai 519082China

Modeling and optimization is crucial to smart chemical process ***,a large number of nonlinearities must be considered in a typical chemical process according to complex unit operations,chemical reactions and *** leads to a great challenge of implementing mechanistic models into industrial-scale problems due to the resulting computational ***,this paper presents an efficient hybrid framework of integrating machine learning and particle swarm optimization to overcome the aforementioned *** industrial propane dehydrogenation process was carried out to demonstrate the validity and efficiency of our ***,a data set was generated based on process mechanistic simulation validated by industrial data,which provides sufficient and reasonable samples for model training and ***,four well-known machine learning methods,namely,K-nearest neighbors,decision tree,support vector machine,and artificial neural network,were compared and used to obtain the prediction models of the processes *** of these methods achieved highly accurate model by adjusting model parameters on the basis of high-coverage data and properly ***,optimal process operations were obtained by using the particle swarm optimization approach.

关键词： smart chemical process operations data generation hybrid method machine learning particle swarm optimization

Microstructures,corrosion behavior and mechanical properties of as-cast Mg-6Zn-2X(Fe/Cu/Ni)alloys for plugging tool applications

在线全文

学校读者我要写书评

暂无评论

International Journal of Minerals,Metallurgy and Materials 2024年第4期31卷 697-711页

作者： Baosheng Liu Jiali Wei Shaohua Zhang Yuezhong Zhang Pengpeng Wu Daqing Fang Guorui Ma School of Materials Science and Engineering Taiyuan University of Science and TechnologyTaiyuan 030024China State Key Laboratory for Mechanical Behavior of Materials Xi’an Jiaotong UniversityXi’an 710049China Intelligent Equipment Research and Development Center Zhuhai Institute of Advanced Technology Chinese Academy of SciencesZhuhai 519080China Advanced Materials Research Institute Zhuhai Dingmei Medical Technology Co.Ltd.Zhuhai 519000China

Mg-6Zn-2X(Fe/Cu/Ni)alloys were prepared through semi-continuous casting,with the aim of identifying a degradable magnesium(Mg)alloy suitable for use in fracturing balls.A comparative analysis was conducted to assess the impacts of adding Cu and Ni,which result in finer grains and the formation of galvanic corrosion *** electronic microscopy examination revealed that precipitated phases concentrated at grain boundaries,forming a semi-continuous network structure that facilitated corrosion penetration in Mg-6Zn-2Cu and Mg-6Zn-2Ni *** corrosion was observed in Mg-6Zn-2Fe,while galvanic corrosion was identified as the primary mechanism in Mg-6Zn-2Cu and Mg-6Zn-2Ni *** the tests,the Mg-6Zn-2Ni alloy exhibited the highest corrosion rate(approximately 932.9 mm/a)due to its significant potential *** testing showed that Mg-6Zn-2Ni alloy possessed suitable ultimate compressive strength,making it a potential candidate material for degradable fracturing balls,effectively addressing the challenges of balancing strength and degradation rate in fracturing applications.

关键词： magnesium alloys microstructure micro-galvanic corrosion mechanical properties

High drug loading and pH-responsive nanomedicines driven by dynamic boronate covalent chemistry for potent cancer immunotherapy

在线全文

学校读者我要写书评

暂无评论

Nano Research 2021年第11期14卷 3913-3920页

作者： Wei Jiang Han Zhou Qin Wang Ziqi Chen Wang Dong Zixuan Guo Yong Li Wei Zhao Meixiao Zhan Yucai Wang Ligong Lu zhuhai Interventional Medical Center Zhuhai Precision Medical CenterZhuhai People’s Hospital(Zhuhai Hospital Affiliated with Jinan University)Zhuhai519000China Division of Molecular Medicine Hefei National Laboratory for Physical Sciences at Microscalethe CAS Key Laboratory of Innate Immunity and Chronic DiseaseSchool of Life SciencesUniversity of Science and Technology of ChinaHefei230026China

Tumor cells undergoing immunogenic cell death (ICD) have emerged as an in situ therapeutic vaccine helping to activate a persistent anti-tumor response. Several chemotherapeutic agents have been demonstrated to induce ICD, however accompanied with severe adverse effects in the clinic, weakening its immune responses. Herein, to elicit an intensive ICD while minimizing the systemic toxicity, we introduce a tumor targeting peptide modified bortezomib (BTZ) loading nanomedicine (i-NPBTZ) for the efficient delivery and controlled release of BTZ in tumors. This system is constructed by conjugating BTZ to PEGylated polyphenols via a pH-sensitive covalent boronate-phenol bond that allows them to self-assemble into nanovesicles in neutral condition with high drug loading efficiency. Once accumulated in acidic environment, BTZ-phenolic network is disassembled and thereby accelerates the release of BTZ from nanocarriers. The released BTZ selectively kill tumor cells with a concomitant evocation of tumor-specific cytotoxic T cells by triggering ICD in vivo. This can finally lead to an extended tumor ablation and prevention of distant metastasis in a syngeneic tumor mouse model, while reducing the systemic toxicity of BTZ. In general, our system offers a novel concept with clinical potential to exploit ICD for potentiating tumor immunotherapy and also provides an excellent example of the application of polymer-drug interaction for efficient drug delivery and controllable release.

关键词： bortezomib boronate-phenolic network pH-responsiveness immunogenic cell death cancer immunotherapy

Low power consumption reduced state and transition MLSE in optical interconnects

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

Science China(Information Sciences) 2023年第10期66卷 325-326页

作者： Weihao NI Fan LI Wei WANG Zhibin LUO Xingwen YI Yi CAI Zhaohui LI School of Electronics and Information technology Guangdong Provincial Key Laboratory of Optoelectronic Information Processing Chips and Systems Sun Yat-sen University Southern Marine Science and Engineering Guangdong Laboratory(zhuhai) Jiangsu Engineering Research Center of Novel Optical Fiber technology and Communication network Suzhou Key Laboratory of Advanced Optical Communication Network Technology Soochow University

Intensity modulation/direct detection(IM/DD) optical fiber communication system is an appropriate candidate for optical interconnect applications due to its low cost and low power consumption characteristics [1]. 4-level pulse amplitude modulation(PAM-4) is widely discussed in optical interconnects due to its simpler transceiver configuration and implementation [2].

关键词： Optical interconnects

Enhance hydrates formation with stainless steel fiber for high capacity methane storage

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 Chemical Engineering 2022年第10期50卷 435-443页

作者： Zhixia Deng Shuanshi Fan Yanhong Wang Xuemei Lang Gang Li School of Chemistry and Chemical Engineering South China University of TechnologyGuangzhou 510640China Guangdong Engineering technology Research Center of Advanced Insulating Coating Zhuhai 519175China Institute of Modern Industrial Innovation South China University of TechnologyZhuhai 519175China Key Laboratory of Fuel Cell technology of Guangdong Province Guangzhou 510640China

In order to realize efficient gas storage of hydrate,stainless steel fiber(SSF)was added to 0.03%(mass)sodium dodecyl sulfate(SDS)solution for gas storage *** can not only improve the problem that hydration heat cannot be removed effectively in the hydration process,but also improve gas storage speed and gas storage by increasing hydrate nucleation *** the experimental conditions(273.2 K,5-9 MPa),the peaks of temperature rise in SDS+SSF systems were found to become much smaller than those in SDS *** maximum gas storage rate and the maximum methane uptake of SSF+SDS system reached 9.89-24.90 cm^(3)·g^(-1)·min^(-1) and 178.65-200.89 cm^(3)·(g H_(2)O)-1,*** with the surfactant SDS solution without SSF,they increased by 10.47%-33.22%and 9.16%-25.36%,*** effect of SSF length on gas storage performance was *** to the continuous thermal conduction network,longer SSF showed a higher gas storage capacity and methane uptake rate compared with shorter *** the same time,compared with other metal fillers,SSF+SDS not only had excellent gas storage performance,but also the amount of SSF(0.1 g·ml^(-1))was only 7.6%of foamed aluminum,and the volume gas storage density was increased by 145.4%.The use of stainless steel fiber made the best use of the thermal conductivity of metal,reduced the amount of metal used,and improved the volume density and mass density of gas storage.

关键词： Methane Stainless steelfiber Gas storagecapacity Hydrate Gas storagerate Heat transfer

Modeling complex networks of nuclear reaction data for probing their discovery processes

在线全文

学校读者我要写书评

暂无评论

Chinese Physics C 2021年第12期45卷 114-121页

作者： Xiaohang Wang Long Zhu Jun Su Sino-French Institute of Nuclear Engineering and technology Sun Yat-sen UniversityZhuhai 519082China

Hundreds of thousands of experimental data sets of nuclear reactions have been systematically collected,and their number is still growing *** data and their correlations compose a complex system,which underpins nuclear science and *** model the nuclear reaction data as weighted evolving networks for the purpose of data verification and *** networks are employed to study the growing cross-section data of a neutron induced threshold reaction(n,2n)and photoneutron *** the networks,the nodes are the historical data,and the weights of the links are the relative deviation between the data *** is found that the networks exhibit small-world behavior,and their discovery processes are well described by the Heaps *** makes the networks novel is the mapping relation between the network properties and the salient features of the database:the Heaps exponent corresponds to the exploration efficiency of the specific data set,the distribution of the edge-weights corresponds to the global uncertainty of the data set,and the mean node weight corresponds to the uncertainty of the individual data *** new perspective to understand the database will be helpful for nuclear data analysis and compilation.

关键词： modeling complex networks neutron induced threshold reaction photoneutron reaction nuclear database

Relating brain structure images to personality characteristics using 3D convolution neural network

在线全文

学校读者我要写书评

暂无评论

CAAI Transactions on Intelligence technology 2021年第3期6卷 338-346页

作者： Lixian Cao Yanchun Liang Wei Lv Kaechang Park Yasuhiro Miura Yuki Shinomiya Shinichi Yoshida zhuhai Laboratory of Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Zhuhai College of Jilin UniversityZhuhaiChina Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education College of Computer Science and TechnologyJilin UniversityChangchunChina School of Information&Research Institute Kochi University of TechnologyKochiJapan

The Keras deep learning framework is employed to study MRI brain data in a preliminary analysis of brain structure using a convolutional neural *** results obtained are matched with the content of personality *** Big Five personality traits provide easy differentiation for dividing personalities into different *** now,the highest accuracy obtained from the results of personality prediction from the analysis of brain structure is about 70%.Although there is still no effective evidence to prove a clear relationship between brain structure and personality,the obtained results could prove helpful in understanding the basic relationship between brain structure and personality characteristics.

关键词： convolution structure dividing

Target dependence of isotopic cross sections in the spallation reactions^(238)U+p,d and^(9)Be at 1 A GeV

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

Chinese Physics C 2022年第7期46卷 159-171页

作者： Qu-Fei Song Long Zhu Jun Su Sino-French Institute of Nuclear Engineering and technology Sun Yat-sen UniversityZhuhai 519082China

The spallation of ^(238)U is an important way to produce rare *** work aims at studying the cross sections of isotopes produced in ^(238)U+p,d and^9 Be reactions at 1 A GeV and their target dependence.(1)A physical model dependent(Bayesian neural network)BNN,which includes the details of IQMD-GEMINI++model and BNN,was developed for a more accurate evaluation of production cross *** isospin-dependent quantum molecular dynamics(IQMD)model is used to study the non-equilibrium thermalization of the ^(238)U nuclei and fragmentation of the hot *** subsequent decay of the pre-fragments is simulated by the GEMINI++*** BNN algorithm is used to improve the prediction accuracy after learning the residual error between experimental data and calculations by the IQMD-GEMINI++*** is shown that the IQMD-GEMINI++model can reproduce the available experimental data(3282 points)within 1.5 orders of *** being fine tuned by the BNN algorithm,the deviation between calculations and experimental data were reduced to within 0.4 order of magnitude.(2)Based on the predictions by the IQMD-GEMINI++-BNN framework,the target dependence of isotopic cross sections was *** cross sections to produce the rare isotopes by the ^(238)U+p,d and^9 Be reactions at 1 A GeV are *** the generation of neutron-rich fission products,the cross sections for the ^(238)U+^(9)Be are the *** the generation of neutron-deficient nuclei in the region of A=200–220,the cross sections for ^(238)U+p reaction are the *** the largest cross sections and the atomic density,the beryllium target is recommended to produce the neutron-rich fission products by the ^(238)U beam at 1 A GeV,while the liquid-hydrogen target is suggested to produce the neutron-deficient nuclei in the region of A=200–220.

关键词： isotopic cross sections in the spallation isospin-dependent quantum molecular dynamics Bayesian neural network