检索结果-南通市图书馆

A benchmark-based method for evaluating hyperparameter optimization techniques of neural networks for surface water quality prediction

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Environmental Science & Engineering 2024年第5期18卷 13-27页

作者： Xuan Wang yan Dong Jing yang Zhipeng liu Jinsuo Lu School of Environmental and Municipal Engineering Xi’an University of Architecture and TechnologyXi’an710055China Shaanxi Key Laboratory of Environmental Engineering Xi’an University of Architecture and TechnologyXi’an710055China State Key Laboratory of Green Building in West China Xi’an University of Architecture and TechnologyXi’an710055China

Neural networks(NNs)have been used extensively in surface water prediction tasks due to computing algorithm improvements and data *** essential step in developing an NN is the hyperparameter *** practice,it is common to manually determine hyperparameters in the studies of NNs in water resources *** may result in considerable randomness and require significant computation time;therefore,hyperparameter optimization(HPO)is *** study adopted five representatives of the HPO techniques in the surface water quality prediction tasks,including the grid sampling(GS),random search(RS),genetic algorithm(GA),Bayesian optimization(BO)based on the Gaussian process(GP),and the tree Parzen estimator(TPE).For the evaluation of these techniques,this study proposed a method:first,the optimal hyperparameter value sets achieved by GS were regarded as the benchmark;then,the other HPO techniques were evaluated and compared with the benchmark in convergence,optimization orientation,and consistency of the optimized *** results indicated that the TPE-based BO algorithm was recommended because it yielded stable convergence,reasonable optimization orientation,and the highest consistency rates with the benchmark *** optimization consistency rates via TPE for the hyperparameters hidden layers,hidden dimension,learning rate,and batch size were 86.7%,73.3%,73.3%,and 80.0%,*** the evaluation of HPO techniques directly based on the prediction performance of the optimized NN in a single HPO test,the proposed benchmark-based HPO evaluation approach is feasible and robust.

关键词： Neural networks Hyperparameter optimization Surface water quality prediction Bayes optimization Genetic algorithm

Robust-augmentation nonlinear dynamic inversion control of over-actuated coaxial high-speed helicopter in transition mode

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 Journal of Aeronautics 2024年第8期37卷 404-420页

作者： Yuqing QIU yan LI Jinxi LANG Yuxian liu Zhong WANG School of Automation Northwestern Polytechnical UniversityXi’an 710129China

As the elevator and rudder can be used actively for control,in addition to the rotors,Coaxial High-speed Helicopters(CHHs)have the problems of control redundancy and changing control authority in the transition *** paper presents a robust-augmentation transitioning flight control design for a CHH under the adverse conditions of parametric uncertainties and external ***,based on control characteristic analysis,an Adaptive Filtered Nonlinear Dynamic Inversion(AFNDI)controller is proposed for the angular rate to handle the effect of unknown unstructured uncertainties and external *** analysis proves that the presented angular rate controller can guarantee steady-state and transient ***,the attitude angle and velocity controllers are also ***,an Incremental-based Nonlinear Prioritizing Control Allocation(INPCA)method is designed to take into account control surface transition and changing control authority,which efficiently distributes the required moments between coaxial rotors and aero-surfaces,and avoids the control reversal problem of the yaw *** the proposed control architecture,the low-pass filter is introduced to alleviate the adverse influence of time delay and measurement ***,the effectiveness of the proposed controller is demonstrated through nonlinear numerical simulations,and is compared with existing *** results show that the proposed control law can improve both capabilities of disturbance rejection and fast response,and works satisfactorily for the CHH transitioning control characteristic.

关键词： Coaxial high-speed helicopter Transition mode Attitude control Control allocation Robust adaptive control

A novel graph oversampling framework for node classification in class-imbalanced graphs

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6期67卷 214-229页

作者： Riting XIA Chunxu ZHANG yan ZHANG Xueyan liu Bo yanG Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University College of Artificial Intelligence Jilin University College of Computer Science and Technology Jilin University College of Communication Engineering Jilin University

Graph neural network(GNN) is a promising method to analyze graphs. Most existing GNNs adopt the class-balanced assumption, which cannot deal with class-imbalanced graphs well. The oversampling technique is effective in alleviating class-imbalanced problems. However, most graph oversampling methods generate synthetic minority nodes and their edges after applying GNNs. They ignore the problem that the representations of the original and synthetic minority nodes are dominated by majority nodes caused by aggregating neighbor information through GNN before oversampling. In this paper, we propose a novel graph oversampling framework, termed distribution alignment-based oversampling for node classification in classimbalanced graphs(named Graph-DAO). Our framework generates synthetic minority nodes before GNN to avoid the dominance of majority nodes caused by message passing in GNNs. Additionally, we introduce a distribution alignment method based on the sum-product network to learn more information about minority nodes. To our best knowledge, it is the first to use the sum-product network to solve the class-imbalanced problem in node classification. A large number of experiments on four real datasets show that our method achieves the optimal results on the node classification task for class-imbalanced graphs.

关键词： graph neural network class-imbalanced graphs sum-product network oversampling node classification

Giant low-field reversible magnetocaloric effect at liquid helium temperature of niobium and iron co-substituted EuTiO_(3) compounds

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Rare Earths 2024年第4期42卷 710-715页

作者： Zhihong Hao Quanyi liu Huicai Xie yan Zhang Zhaojun Mo School of Rare Earth and New Materials Engineering Ganzhou Innovation Center of Rare Earth Permanent Magnet Material Advanced Manufacturing and Intelligent Equipment TechnologyGannan University of Science and TechnologyGanzhou341000China Ganjiang Innovation Academy Chinese Academy of SciencesGanzhou34119China School of Materials Science and Engineering Taiyuan University of Science and TechnologyTaiyuan030024China

Giant magnetocaloric effect(MCE)materials in the liquid helium temperature region have attracted a lot of attention in the field of low-temperature magnetic refrigeration(MR).In this study,a series of niobium(Nb)and iron(Fe)co-substituted EuTiO_(3) perovskites with cubic structure(space group pm3m)was successfully fabricated,and their magnetic properties as well as cryogenic magnetocaloric effects were investigated in *** expected,the introduction of Nb and Fe can significantly modulate the magnetic phase transition and magnetocaloric effect of the EuTiO_(3) *** increasing Fe concentration,two local minima corresponding to the AFM-FM magnetic phase transition near 5.0 K and FM-PM transition near 10 K with no hysteresis in the thermomagnetic curves are observed,which is attributed to an enhancement of FM *** the same time,the gradually widened-ΔSM-T curves and the two peaks with a broad shoulder lead to considerable refrigeration capacity(RC).With the field change ofΔH=2 T,the calculated values of-ΔS_(M)^(max) for the EuTi_(0.9375-x)Nb_(0.0625)Fe_(x)O_(3)(x=0.075,0.1,0.125,0.15)compounds are 24.2,17.6,14.5 and 14.0 J/(kg·K),*** corresponding RC values were calculated to be 144.6,138.3,151.2 and 159 J/kg,***,the values of-ΔS_(M)^(max) for EuTi_(0.8625)Nb_(0.0625)Fe_(0.075)O_(3) are 8.6 and 15.1 J/(kg·K)under low field changes of 0.5 and 1 T,*** giant low-field reversible magnetocaloric effect makes them attractive candidates for magnetic refrigeration in the liquid helium temperature region.

关键词： Magnetocaloric effect Refrigeration capacity Magnetic entropy change Rareearths

Simultaneous enhanced ammonia and nitrate removal from secondary effluent in constructed wetlands using a new manganese-containing substrate

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

Frontiers of Environmental Science & Engineering 2024年第4期18卷 91-102页

作者： Zhihao xian Jun yan Jingyi Dai Hao Wu Xin Zhang Wenbo Nie Fucheng Guo Yi Chen Key Laboratory of the Three Gorges Reservoir Region’s Eco-Environment(Ministry of Education) Chongqing UniversityChongqing 400044China College of Environment and Ecology Chongqing UniversityChongqing 400044China

Constructed wetlands(CWs)are widely used to treat secondary ***,simultaneously removing ammonia(NH_(4)^(+)-N)and nitrate(NO_(3)^(–)–N)is challenging because of insufficient oxygen and carbon *** this study,a novel composite material(MPCM)comprising MnO_(2) and polycaprolactone was developed as a substrate for CWs to enhance the synchronous removal of NH_(4)^(+)–N and NO_(3)^(–)–*** CWs with a higher MPCM content(H-CW),lower MPCM content(LCW),and controlled CW(C-CW)exhibited average NH_(4)^(+)–N removal efficiencies of 75.69%,70.49%,and 52.40%,*** 15N isotope tracking technique showed that NH_(4)^(+)–N removal was attributed to anaerobic ammonia oxidation mediated by MnO2 reduction(Mnammox),which accounted for 17.16%–27.24%of the NH_(4)^(+)–N removal in the composite material layers(0–20 cm)of the H-CW and *** richness of ammonia oxidizers in the upper layers(40–50 cm)of the HCW and L-CW further facilitated NH_(4)^(+)–N ***,the average total nitrogen(TN)removal efficiencies of the H-CW and L-CW were 1.99 and 1.59 times that of C-CW,respectively,owing to enhanced denitrification by ***,N_(2)O emissions were reduced by 81.31%and 70.83%in the H-CW and L-CW,*** study provides an effective approach for improving nitrogen removal and reducing N2O emissions during the treatment of secondary effluent by CWs.

关键词： Constructed wetland Nitrogen removal Manganese redox Polycaprolactone Nitrous oxide

Multi-Scale Feature Fusion Model for Bridge Appearance Defect Detection

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Big Data Mining and Analytics 2024年第1期7卷 1-11页

作者： Rong Pang yan yang Aiguo Huang yan liu Peng Zhang Guangwu Tang School of Computing and Artificial Intelligence Southwest Jiaotong UniversityChengdu 611756China China Merchants Chongqing Road Engineering Inspection Center Co. Ltd.Chongqing 400067China State Key Laboratory of Bridge Engineering Structural Dynamics Chongqing 400067China

Although the Faster Region-based Convolutional Neural Network(Faster R-CNN)model has obvious advantages in defect recognition,it still cannot overcome challenging problems,such as time-consuming,small targets,irregular shapes,and strong noise interference in bridge defect *** deal with these issues,this paper proposes a novel Multi-scale Feature Fusion(MFF)model for bridge appearance disease ***,the Faster R-CNN model adopts Region Of Interest(ROl)pooling,which omits the edge information of the target area,resulting in some missed detections and inaccuracies in both detecting and localizing bridge ***,this paper proposes an MFF based on regional feature Aggregation(MFF-A),which reduces the missed detection rate of bridge defect detection and improves the positioning accuracy of the target ***,the Faster R-CNN model is insensitive to small targets,irregular shapes,and strong noises in bridge defect detection,which results in a long training time and low recognition ***,a novel Lightweight MFF(namely MFF-L)model for bridge appearance defect detection using a lightweight network EfficientNetV2 and a feature pyramid network is proposed,which fuses multi-scale features to shorten the training speed and improve recognition ***,the effectiveness of the proposed method is evaluated on the bridge disease dataset and public computational fluid dynamic dataset.

关键词： defect detection Multi-scale Feature Fusion(MFF) Region Of Interest(ROl)alignment lightweight network

Analysis of risk factors of suicidal ideation in adolescent patients with depression and construction of prediction model

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

World Journal of Psychiatry 2024年第3期14卷 388-397页

作者： Jun-Chao Zhou yan Cao Xu-Yuan Xu Zhen-Ping xian Department of Psychosomatic Medicine The Affiliated Lianyungang Hospital of Xuzhou Medical UniversityThe First People's Hospital of LianyungangLianyungang 222000Jiangsu ProvinceChina

BACKGROUND Major depressive disorder is a common mental illness among adolescents and is the largest disease burden in this age *** adolescent patients with depression have suicidal ideation(SI);however,few studies have focused on the factors related to SI,and effective predictive models are *** To construct a risk prediction model for SI in adolescent depression and provide a reference assessment tool for *** The data of 150 adolescent patients with depression at the First People's Hospital of Lianyungang from June 2020 to December 2022 were retrospectively *** on whether or not they had SI,they were divided into a SI group(n=91)and a non-SI group(n=59).The general data and laboratory indices of the two groups were *** regression was used to analyze the factors influencing SI in adolescent patients with depression,a nomogram prediction model was constructed based on the analysis results,and internal evaluation was *** operating characteristic and calibration curves were used to evaluate the model’s efficacy,and the clinical application value was evaluated using decision curve analysis(DCA).RESULTS There were differences in trauma history,triggers,serum ferritin levels(SF),highsensitivity C-reactive protein levels(hs-CRP),and high-density lipoprotein(HDLC)levels between the two groups(P<0.05).Logistic regression analysis showed that trauma history,predisposing factors,SF,hs-CRP,and HDL-C were factors influencing SI in adolescent patients with *** area under the curve of the nomogram prediction model was 0.831(95%CI:0.763–0.899),sensitivity was 0.912,and specificity was *** higher net benefit of the DCA and the average absolute error of the calibration curve were 0.043,indicating that the model had a good *** The nomogram prediction model based on trauma history,triggers,ferritin,serum hs-CRP,and HDL-C levels can effectively predict the risk of SI in adolescent patients

关键词： Adolescents Depression Suicidal ideation Risk factors Prediction model Ferritin

Failure evaluation and control factor analysis of slope block instability along traffic corridor in Southeastern Tibet

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Mountain Science 2024年第6期21卷 1830-1848页

作者： liu Changqing BAO Han LAN Hengxing yan Changgen LI Changbo liu Shijie School of Highway Chang'an UniversityXi'an 710064China State Key Laboratory of Resources and Environmental Information System Institute of Geographic Sciences and Natural Resources ResearchChinese Academy of SciencesBeijing 100101China College of Geological Engineering and Geomatics Chang'an UniversityXi'an 710054China

The instability of slope blocks occurred frequently along traffic corridor in Southeastern Tibet(TCST),which was primarily controlled by the rock mass structures.A rapid method evaluating the control effects of rock mass structures was proposed through field statistics of the slopes and rock mass structures along TCST,which combined the stereographic projection method,modified M-JCS model,and limit equilibrium *** instabilities of slope blocks along TCST were then evaluated rapidly,and the different control factors of instability were *** showed that the probabilities of toppling(5.31%),planar(16.15%),and wedge(35.37%)failure of slope blocks along TCST increased *** instability modes were respectively controlled by the anti-dip joint,the joint parallel to slope surface with a dip angle smaller than the slope angle(singlejoint),and two groups of joints inclined out of the slope(double-joints).Regarding the control effects on slope block instability,the stabilization ability of doublejoints(72.7%),anti-dip joint(67.4%),and single-joint(57.6%)decreased sequentially,resulting in different probabilities of slope block ***,nearby regional faults significantly influenced the joints,leading to spatial heterogeneity and segmental clustering in the stabilization ability provided by joints to the slope ***,the stability of slope blocks gradually weakened as they approached the fault *** paper can provide guidance and assistance for investigating the development characteristics of rock mass structures and the stability of slope blocks.

关键词： Slope engineering Block instability Rapid evaluation method Rock mass structure Control factor

Long noncoding RNA protein-disulfide isomerase-associated 3 regulated high glucose-induced podocyte apoptosis in diabetic nephropathy through targeting miR-139-3p

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

World Journal of Diabetes 2024年第2期15卷 260-274页

作者： Yin-Xi He Ting Wang Wen-xian Li yan-Xia Chen Department of Orthopaedic Trauma The Third Hospital of ShijiazhuangShijiazhuang 050000Hebei ProvinceChina Department of Endocrinology The Second Hospital of Hebei Medical UniversityShijiazhuang 050000Hebei ProvinceChina Department of Endocrinology The First Hospital of ZhangjiakouZhangjiakou 075000Hebei ProvinceChina

BACKGROUND Podocyte apoptosis plays a vital role in proteinuria pathogenesis in diabetic nephropathy(DN).The regulatory relationship between long noncoding RNAs(lncRNAs)and podocyte apoptosis has recently become another research hot spot in the DN *** To investigate whether lncRNA protein-disulfide isomerase-associated 3(Pdia3)could regulate podocyte apoptosis through miR-139-3p and revealed the underlying *** Using normal glucose or high glucose(HG)-cultured podocytes,the cellular functions and exact mechanisms underlying the regulatory effects of lncRNA Pdia3 on podocyte apoptosis and endoplasmic reticulum stress(ERS)were *** Pdia3 and miR-139-3p expression were measured through quantitative real-time polymerase chain *** cell viability was detected through the cell counting kit-8 colorimetric *** podocyte apoptosis rate in each group was measured through flow *** interaction between lncRNA Pdia3 and miR-139-3p was examined through the dual luciferase reporter ***,western blotting was performed to detect the effect of lncRNA Pdia3 on podocyte apoptosis and ERS via *** The expression of lncRNA Pdia3 was significantly downregulated in HG-cultured ***,lncRNA Pdia3 was involved in HG-induced podocyte ***,the dual luciferase reporter assay confirmed the direct interaction between lncRNA Pdia3 and *** Pdia3 overexpression attenuated podocyte apoptosis and ERS through miR-139-3p in HG-cultured *** Taken together,this study demonstrated that lncRNA Pdia3 overexpression could attenuate HG-induced podocyte apoptosis and ERS by acting as a competing endogenous RNA of miR-139-3p,which might provide a potential therapeutic target for DN.

关键词： Long noncoding RNAs Diabetic nephropathy Podocyte apoptosis Endoplasmic reticulum stress Competing endogenous RNA