检索结果-南通市图书馆

UAV maneuvering decision-making algorithm based on deep reinforcement learning under the guidance of expert experience

在线全文

学校读者我要写书评

暂无评论

Journal of Systems Engineering and Electronics 2024年第3期35卷 644-665页

作者： ZHAN Guang zhang kun LI Ke PIAO Haiyin School of Electronics and Information Northwestern Polytechnical UniversityXi’an 710072China Science and Technology on Electro-Optic Control Laboratory Luoyang 471009China

Autonomous umanned aerial vehicle(UAV) manipulation is necessary for the defense department to execute tactical missions given by commanders in the future unmanned battlefield. A large amount of research has been devoted to improving the autonomous decision-making ability of UAV in an interactive environment, where finding the optimal maneuvering decisionmaking policy became one of the key issues for enabling the intelligence of UAV. In this paper, we propose a maneuvering decision-making algorithm for autonomous air-delivery based on deep reinforcement learning under the guidance of expert experience. Specifically, we refine the guidance towards area and guidance towards specific point tasks for the air-delivery process based on the traditional air-to-surface fire control ***, we construct the UAV maneuvering decision-making model based on Markov decision processes(MDPs). Specifically, we present a reward shaping method for the guidance towards area and guidance towards specific point tasks using potential-based function and expert-guided advice. The proposed algorithm could accelerate the convergence of the maneuvering decision-making policy and increase the stability of the policy in terms of the output during the later stage of training process. The effectiveness of the proposed maneuvering decision-making policy is illustrated by the curves of training parameters and extensive experimental results for testing the trained policy.

关键词： unmanned aerial vehicle(UAV) maneuvering decision-making autonomous air-delivery deep reinforcement learning reward shaping expert experience

Coupling analysis method of grouting construction with deformation response of adjacent existing tunnel

在线全文

学校读者我要写书评

暂无评论

Underground Space 2024年第2期15卷 312-330页

作者： Ping-wei Jiang Zhi-hong zhang Hong Zheng Jin-kun Huang Key Laboratory of Urban Security and Disaster Engineering of China Ministry of Education Beijing University of TechnologyBeijing 100124China China MCC17 Group Co.LTD MaanshanAnhui 243000China School of Naval Architecture Ocean and Civil EngineeringShanghai Jiao Tong UniversityShanghai 200240China

In the new tunnel under close distance through the existing tunnel risk source,the grouting scheme developed to compensate for stratum losses is still based on empirical methods,relying on the overburden thickness of existing *** can potentially lead to an excessively high or low probability of uplift of existing *** a coupled deformation analysis method between the grouting construction and adjacent existing tunnels is of great theoretical significance for developing grouting *** order to reasonably limit the design parameters of grouting construction,based on the theory of fluid–solid coupling elastic pore-column expansion and the theory of random media,the calculation method of stratum displacement which simultaneously considers the coexistence of grout compaction expansion and permeability diffusion mode is derived,and the accuracy of the calculation method is verified by engineering *** accuracy of this calculation method was verified through engineering *** with the deformation coordination condition,the existing tunnel is regarded as an elastic Euler-Bernoulli continuous beam,and the finite element coupling balance equation of the interaction between the existing tunnel and the surrounding soil is *** on this,a coupling calculation model of the grouting construction and the deformation response of the adjacent existing tunnel is *** with three times of grouting construction examples in the shield tunneling project of Beijing Metro Line 12 under the existing airport line,the reliability of the coupling calculation model to determine the grouting construction parameters is *** calculation parameters in the coupling calculation model have clear physical meanings,which can provide a theoretical basis for the grouting design of similar risk source projects.

关键词： Grouting Close-range underpass Tunnel Random medium theory Euler-Bernoulli continuous beam

Reducing idleness in financial cloud services via multi-objective evolutionary reinforcement learning based load balancer

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) 2024年第2期67卷 20-40页

作者： peng YANG Laoming zhang Haifeng LIU Guiying LI Department of Statistics and Data Science Southern University of Science and Technology Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and EngineeringSouthern University of Science and Technology Academy for Advanced Interdisciplinary Studies Southern University of Science and Technology Guangdong OPPO Mobile Telecommunications Corp. Ltd Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology

In recent years, various companies have started to shift their data services from traditional data centers to the cloud. One of the major motivations is to save on operational costs with the aid of cloud elasticity. This paper discusses an emerging need from financial services to reduce the incidence of idle servers retaining very few user connections, without disconnecting them from the server side. This paper considers this need as a bi-objective online load balancing problem. A neural network based scalable policy is designed to route user requests to varied numbers of servers for the required elasticity. An evolutionary multi-objective training framework is proposed to optimize the weights of the policy. Not only is the new objective of idleness reduced by over 130% more than traditional industrial solutions, but the original load balancing objective itself is also slightly improved. Extensive simulations with both synthetic and real-world data help reveal the detailed applicability of the proposed method to the emergent problem of reducing idleness in financial services.

关键词： evolutionary reinforcement learning evolutionary multi-objective optimization load balance cloud computing

A nonlocal dispersal and time delayed HIV infection model with general incidences

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Applied Mathematics(A Journal of Chinese Universities) 2024年第3期39卷 448-457页

作者： WU peng zhang Yu-huai WANG Ling School of Sciences Hangzhou Dianzi UniversityHangzhou 310018China School of Humanities and Management Zhejiang Chinese Medical UniversityHangzhou 311402China Public Foundational Courses Department Nanjing Vocational University of Industry TechnologyNanjing 210023China

Biologically,because of the impact of reproduction period and nonlocal dispersal of HIV-infected cells,time delay and spatial heterogeneity should be *** this paper,we establish an HIV infection model with nonlocal dispersal and infection ***,applying the theory of Fourier transformation and von Foerster rule,we transform the model to an integrodifferential equation with nonlocal time delay and *** well-posedness,positivity,and boundedness of the solution for the model are studied.

关键词： HIV model nonlocal dispersal time delay general incidences

Weight Analysis of Impact Factors of Interbedded Anti-Inclined Slopes Block-Flexure Toppling Based on Support Vector Regression

在线全文

学校读者我要写书评

暂无评论

Journal of Earth Science 2024年第2期35卷 568-582页

作者： Bocheng zhang Huiming Tang Yibing Ning kun Fang Ding Xia Department of Engineering Geology and Geotechnical Engineering Faculty of EngineeringChina University of GeosciencesWuhan430074China Badong National Observation and Research Station of Geohazards China University of GeosciencesWuhan430074China College of Geological Engineering and Geomatics Chang’an UniversityXi’an710054China

Block-flexure toppling failure is frequently encountered in interbedded anti-inclined rock(IAR)slopes,and seriously threatens the construction of hydropower *** this study,we first investigated the Lean Reservoir area’s geological setting and the Linda landslide’s ***,uniform design and random design were used to design 110 training datasets and 31 testing datasets,***,the toppling response was obtained by using the discrete element ***,support vector regression was used to obtain the influence weights of 21 impact *** results show that the influence weight of the slope angle and rock formation dip angle on the toppling deformation among tertiary impact factors is 25.96%and 17.28%,respectively,which are much greater than the other 19 impact factors within the research *** the primary impact factors,the influence weight is sorted from large to small as slope geometry parameters,joints parameters,and rock mechanics *** parameters,especially the geometric parameters,cannot be ignored when evaluating the stability of IAR *** numerical simulation,it was qualitatively determined that failure surfaces of slopes were controlled by cross joints and that the rocks in the slope toe play a role in preventing slope deformation.

关键词： interbedded anti-inclined slopes block-flexure toppling impact factors numerical simulation support vector regression engineering geology

Multicolor upconversion reversible modulations in YNbO_(4):Er^(3+)/Tm^(3+)/Yb^(3+) photochromic materials

在线全文

学校读者我要写书评

暂无评论

Journal of Rare Earths 2024年第2期42卷 270-277,I0002页

作者： Zhen zhang peng Li Ziyi Xu Zhihao zhang Qiwei zhang Haiqin Sun Xihong Hao Inner Mongolia Key Laboratory of Ferroelectric-related New Energy Materials and Devices Schoolof Materials and MetallurgyInner Mongolia University of Science and TechnologyBaotou014010China College of Physics and Technology Guangxi Normal UniversityGuilin541004China

Photochromic materials with multicolor upconversion reversible modulations are attractive in optical switching ***,the fabricated YNbO_(4):Er^(3+)/Tm^(3+)/Yb^(3+) materials exhibit excellent photochromism and multicolor upconversion properties from green,red to near infrared(NIR) emissions with increasing Yb *** multiband upconversion modulations are achieved by alternating light(365 and 405 nm) or thermal *** 365 nm irradiation,the luminescence color changes from yellow to red,the luminescent photoswitching contrast reaches up to 86.21%(green),82.12%(red) and 77.38%(NIR) in the Y_(0.83)Er_(0.01)Tm_(0.01)NbO_(4):0.15 Yb ***,the upconversion emission intensity before and after photochromic reaction shows remarkable change in a wide temperature range of 298-718 *** results indicate that the Er^(3+)/Tm^(3+)/Yb^(3+) tri-doped YNbO_(4) materials can be a good candidate in optical switching and data storage applications.

关键词： Photochromic materials Luminescence modulation Multicolor emission Photoswitching contrast Rare earths

How the enhanced East Asian summer monsoon regulates total gross primary production in eastern China

在线全文

学校读者我要写书评

暂无评论

Advances in Climate Change Research 2024年第2期15卷 244-252页

作者： Ming-Yu HAN Yong zhang Jing peng China State Key Laboratory of Severe Weather Chinese Academy of Meteorological SciencesBeijing 100081China China Meteorological Administration Institute for Development and Programme Design Beijing 100081China CAS Key Laboratory of Regional Climate-Environment for Temperate East Asia Institute of Atmospheric PhysicsChinese Academy of Sciences(CAS)Beijing 100029China

Recognizing the relationship between gross primary production(GPP)and precipitation in eastern China,the East Asian Summer Monsoon(EASM)plays a crucial role in shaping *** confirmation of the strong link between EASM and GPP,there remains a notable research gap in understanding the specific impact of the EASM on GPP in different regions of eastern *** we used simulations from Trends in Net Land-Atmosphere Carbon Exchanges(TRENDY)models from 1951 to 2010 and divided eastern China into five subregions for the *** also used the New East Asian Summer Monsoon Index(NEWI)as a quantitative metric to distinguish between periods of strong and weak *** on this,this study aims to investigate the response of GPP in different subregions of eastern ***,under strengthened EASM years(1954,1957,1965,1969,1977,1980,1983,1987,1993 and 1998),East China experienced the most pronounced increase in GPP at 12±21(mean±1 sigma)gC m^(-2) mon^(-1) compared to the weak EASM years(1958,1961,1972,1973,1978,1981,1985,1994,1997 and 2004).In contrast,Southwest China showed a decline in GPP at-4±10 gC m^(-2) mon^(-1).Moreover,GPP also increased in Northeast and North China when EASM strengthened,while South China showed a decline in *** indicated that GPP changed with monsoon *** to the mechanism analysis,during strong EASM,there was intense moisture convergence through alterations in the atmospheric circulation field over East China and abundant precipitation,which further contributed to the increase in *** solar radiation in Southwest China decreased with EASM enhancement,which suppressed GPP and hindered vegetation ***,the results highlight the importance of accurately predicting the impact of different EASM intensities of regional carbon fluxes.

关键词： Gross primary production Surface air temperature Precipitation Solar radiation Eastern China Carbon cycle

Engineered extracellular vesicles for targeted reprogramming of cancer-associated fibroblasts to potentiate therapy of pancreatic cancer

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

Signal Transduction and Targeted Therapy 2024年第7期9卷 3077-3096页

作者： pengcheng Zhou Xuanlong Du Weilu Jia kun Feng Yewei zhang Department of General Surgery Affiliated Hospital of Nantong UniversityNantongChina School of Medicine Southeast UniversityNanjingChina Nanjing Medical University NanjingChina Hepatobiliary and Pancreatic Center The Second Affiliated Hospital of Nanjing Medical UniversityNanjingChina

Pancreatic cancer is one of the deadly malignancies with a significant mortality rate and there are currently few therapeutic options for *** tumor microenvironment(TME)in pancreatic cancer,distinguished by fibrosis and the existence of cancer-associated fibroblasts(CAFs),exerts a pivotal influence on both tumor advancement and resistance to *** advancements in the field of engineered extracellular vesicles(EVs)offer novel avenues for targeted therapy in pancreatic *** study aimed to develop engineered EVs for the targeted reprogramming of CAFs and modulating the TME in pancreatic *** obtained from bone marrow mesenchymal stem cells(BMSCs)were loaded with miR-138-5p and the anti-fibrotic agent pirfenidone(PFD)and subjected to surface modification with integrinα5-targeting peptides(named IEVs-PFD/138)to reprogram CAFs and suppress their pro-tumorigenic ***α5-targeting peptide modification enhanced the CAF-targeting ability of ***-138-5p directly inhibited the formation of the FERMT2-TGFBR1 complex,inhibiting TGF-βsignaling pathway *** addition,miR-138-5p inhibited proline-mediated collagen synthesis by directly targeting the FERMT2-PYCR1 *** combination of miR-138-5p and PFD in EVs synergistically promoted CAF reprogramming and suppressed the pro-cancer effects of *** experiments using the orthotopic stroma-rich and patient-derived xenograft mouse models yielded promising *** particular,IEVs-PFD/138 effectively reprogrammed CAFs and remodeled TME,which resulted in decreased tumor pressure,enhanced gemcitabine perfusion,tumor hypoxia amelioration,and greater sensitivity of cancer cells to ***,the strategy developed in this study can improve chemotherapy *** IEVs-PFD/138 as a targeted therapeutic agent to modulate CAFs and the TME represents a promising therapeutic approach for pancreatic cancer.

关键词： inhibited targeted chemotherapy

A hybrid machine learning optimization algorithm for multivariable pore pressure prediction

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

Petroleum Science 2024年第1期21卷 535-550页

作者： Song Deng Hao-Yu Pan Hai-Ge Wang Shou-kun Xu Xiao-peng Yan Chao-Wei Li Ming-Guo peng Hao-Ping peng Lin Shi Meng Cui Fei Zhao School of Petroleum and Natural Gas Engineering Changzhou UniversityChangzhou213164JiangsuChina Tubular Goods Research Institute of CNPC Beijing102249China CNPC Engineering Technology R&D Company Limited Beijing102206China

Pore pressure is essential data in drilling design,and its accurate prediction is necessary to ensure drilling safety and improve drilling *** methods for predicting pore pressure are limited when forming particular structures and *** this paper,a machine learning algorithm and effective stress theorem are used to establish the transformation model between rock physical parameters and pore *** study collects data from three *** 1 had 881 data sets for model training,and Wells 2 and 3 had 538 and 464 data sets for model *** this paper,support vector machine(SVM),random forest(RF),extreme gradient boosting(XGB),and multilayer perceptron(MLP)are selected as the machine learning algorithms for pore pressure *** addition,this paper uses the grey wolf optimization(GWO)algorithm,particle swarm optimization(PSO)algorithm,sparrow search algorithm(SSA),and bat algorithm(BA)to establish a hybrid machine learning optimization algorithm,and proposes an improved grey wolf optimization(IGWO)*** IGWO-MLP model obtained the minimum root mean square error(RMSE)by using the 5-fold cross-validation method for the training *** the pore pressure data in Well 2 and Well 3,the coefficients of determination(R^(2))of SVM,RF,XGB,and MLP are 0.9930 and 0.9446,0.9943 and 0.9472,0.9945 and 0.9488,0.9949 and *** achieves optimal performance on both training and test data,and the MLP model shows a high degree of *** indicates that the IGWO-MLP is an excellent predictor of pore pressure and can be used to predict pore pressure.

关键词： Pore pressure Grey wolf optimization Multilayer perceptron Effective stress Machine learning