检索结果-南通市图书馆

The linear self-attracting diffusion driven by the weighted-fractional Brownian motion II: The parameter estimation

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 Mathematics 2025年

作者： Litan Yan Rui Guo Wenyi Pei Department of Statistics College of Science Donghua University School of Statistics and Mathematics Zhejiang Gongshang University

Let Ba,bbe a weighted-fractional Brownian motion with Hurst indexes a and b such that a>-1and 0≤b<1∧（1+a）.In this paper,we consider the linear self-attracting diffusion ■ interacting diffusion (see Cranston and Le Jan （1995）).Under the continuous observation,we study asymptotic ■ converges in distribution to the sum of the chi-square random variable with 1 degree of freedom and the random variable Z1a,b.

关键词：

Effects of the extrusion parameters on microstructure,texture and room temperature mechanical properties of extruded Mg-2.49Nd-1.82Gd-0.2Zn-0.2Zr alloy

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

International Journal of Minerals,Metallurgy and Materials 2025年第1期32卷 136-146页

作者： Chenjin Zhang Guangyu Yang Lei Xiao Zhiyong Kan Jing Guo Qiang Li Wanqi Jie State Key Laboratory of Solidification Processing Northwestern Polytechnical UniversityXi’an 710072China college of Materials science and Engineering Fuzhou UniversityFuzhou 350108China college of Chemistry and Environmental science Qujing Normal UniversityQujing 655011China

Microstructure,texture,and mechanical properties of the extruded Mg-2.49Nd-1.82Gd-0.2Zn-0.2Zr alloy were investigated at different extrusion temperatures(260 and 320℃),extrusion ratios(10:1,15:1,and 30:1),and extrusion speeds(3 and 6 mm/s).The experimental results exhibited that the grain sizes after extrusion were much finer than that of the homogenized alloy,and the second phase showed streamline distribution along the extrusion direction(ED).With extrusion temperature increased from 260 to 320℃,the microstructure,texture,and mechanical properties of alloys changed *** dynamic recrystallization(DRX)degree and grain sizes enhanced as the extrusion ratio increased from 10:1 to 30:1,and the strength gradually decreased but elongation(EL)*** the extrusion speed increased from 3 to 6 mm/s,the grain sizes and DRX degree increased significantly,and the samples presented the typical-rare-earth(RE)*** alloy extruded at 260℃ with extrusion ratio of 10:1 and extrusion speed of 3 mm/s showed the tensile yield strength(TYS)of 213 MPa and EL of 30.6%.After quantitatively analyzing the contribution of strengthening mechanisms,it was found that the grain boundary strengthening and dislocation strengthening played major roles among strengthening *** results provide some guidelines for enlarging the industrial application of extruded Mg-RE alloy.

关键词： Mg-rare earth alloys extrusion temperature extrusion ratio extrusion speed strengthening mechanisms

维普期刊数据库

Research on Stock Price Prediction Method Based on the GAN-LSTM-Attention Model

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2025年第1期82卷 609-625页

作者： Peng Li Yanrui Wei Lili Yin college of Computer science and Technology Harbin University of Science and TechnologyHarbin150006China

Stock price prediction is a typical complex time series prediction problem characterized by dynamics,nonlinearity,and *** paper introduces a generative adversarial network model that incorporates an attention mechanism(GAN-LSTM-Attention)to improve the accuracy of stock price ***,the generator of this model combines the Long and Short-Term Memory Network(LSTM),the Attention Mechanism and,the Fully-Connected Layer,focusing on generating the predicted stock *** discriminator combines the Convolutional Neural Network(CNN)and the Fully-Connected Layer to discriminate between real stock prices and generated stock ***,to evaluate the practical application ability and generalization ability of the GAN-LSTM-Attention model,four representative stocks in the United States of America(USA)stock market,namely,Standard&Poor’s 500 Index stock,Apple Incorporatedstock,AdvancedMicroDevices Incorporatedstock,and Google Incorporated stock were selected for prediction experiments,and the prediction performance was comprehensively evaluated by using the three evaluation metrics,namely,mean absolute error(MAE),root mean square error(RMSE),and coefficient of determination(R2).Finally,the specific effects of the attention mechanism,convolutional layer,and fully-connected layer on the prediction performance of the model are systematically analyzed through ablation *** results of experiment show that the GAN-LSTM-Attention model exhibits excellent performance and robustness in stock price prediction.

关键词： Stock price prediction generative adversarial network attention mechanism time-series prediction

An Artificial Intelligence‑Assisted Flexible and Wearable Mechanoluminescent Strain Sensor System

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Nano-Micro Letters 2025年第3期17卷 217-231页

作者： Yan Dong Wenzheng An Zihu Wang Dongzhi Zhang college of Control science and Engineering China University of Petroleum(East China)Qingdao 266580People’s Republic of China

The complex wiring,bulky data collection devices,and difficulty in fast and on-site data interpretation significantly limit the practical application of flexible strain sensors as wearable *** tackle these challenges,this work develops an artificial intelligenceassisted,wireless,flexible,and wearable mechanoluminescent strain sensor system(AIFWMLS)by integration of deep learning neural network-based color data processing system(CDPS)with a sandwich-structured flexible mechanoluminescent sensor(SFLC)*** SFLC film shows remarkable and robust mechanoluminescent performance with a simple structure for easy *** CDPS system can rapidly and accurately extract and interpret the color of the SFLC film to strain values with auto-correction of errors caused by the varying color temperature,which significantly improves the accuracy of the predicted strain.A smart glove mechanoluminescent sensor system demonstrates the great potential of the AIFWMLS system in human gesture ***,the versatile SFLC film can also serve as a encryption *** integration of deep learning neural network-based artificial intelligence and SFLC film provides a promising strategy to break the“color to strain value”bottleneck that hinders the practical application of flexible colorimetric strain sensors,which could promote the development of wearable and flexible strain sensors from laboratory research to consumer markets.

关键词： Mechanoluminescent Strain sensor Flexible Deep learning Wireless

An Iterated Greedy Algorithm with Memory and Learning Mechanisms for the Distributed Permutation Flow Shop Scheduling Problem

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2025年第1期82卷 371-388页

作者： Binhui Wang Hongfeng Wang college of Information science and Engineering Northeastern UniversityShenyang110819China

The distributed permutation flow shop scheduling problem(DPFSP)has received increasing attention in recent *** iterated greedy algorithm(IGA)serves as a powerful optimizer for addressing such a problem because of its straightforward,single-solution evolution ***,a potential draw-back of IGA is the lack of utilization of historical information,which could lead to an imbalance between exploration and exploitation,especially in large-scale *** a consequence,this paper develops an IGA with memory and learning mechanisms(MLIGA)to efficiently solve the DPFSP targeted at the ***,we incorporate a memory mechanism to make a more informed selection of the initial solution at each stage of the search,by extending,reconstructing,and reinforcing the information from previous *** addition,we design a twolayer cooperative reinforcement learning approach to intelligently determine the key parameters of IGA and the operations of the memory ***,to ensure that the experience generated by each perturbation operator is fully learned and to reduce the prior parameters of MLIGA,a probability curve-based acceptance criterion is proposed by combining a cube root function with custom *** last,a discrete adaptive learning rate is employed to enhance the stability of the memory and *** ablation experiments are utilized to verify the effectiveness of the memory mechanism,and the results show that this mechanism is capable of improving the performance of IGA to a large ***,through comparative experiments involving MLIGA and five state-of-the-art algorithms on 720 benchmarks,we have discovered that MLI-GA demonstrates significant potential for solving large-scale *** indicates that MLIGA is well-suited for real-world distributed flow shop scheduling.

关键词： Distributed permutation flow shop scheduling makespan iterated greedy algorithm memory mechanism cooperative reinforcement learning

Attention Eraser and Quantitative Measures for Automated Bone Age Assessment

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2025年第1期82卷 627-644页

作者： Liuqiang Shu Lei Yu college of Computer and Information science Chongqing Normal UniversityChongqing401331China

Bone age assessment(BAA)aims to determine whether a child’s growth and development are normal concerning their chronological *** predict bone age more accurately based on radiographs,and for the left-hand X-ray images of different races model can have better adaptability,we propose a neural network in parallel with the quantitative features from the left-hand bone measurements for *** this study,a lightweight feature extractor(LFE)is designed to obtain the featuremaps fromradiographs,and amodule called attention erasermodule(AEM)is proposed to capture the fine-grained ***,the dimensional information of the metacarpal parts in the radiographs is measured to enhance the model’s generalization capability across images fromdifferent *** is trained and validated on the RSNA,RHPE,and digital hand atlas datasets,which include images from various racial *** model achieves a mean absolute error(MAE)of 4.42 months on the RSNA dataset and 15.98 months on the RHPE *** to ResNet50,InceptionV3,and several state-of-the-art methods,our proposed method shows statistically significant improvements(p<0.05),with a reduction in MAE by 0.2±0.02 years across different racial ***,t-tests on the features also confirm the statistical significance of our approach(p<0.05).

关键词： Bone age assessment attention eraser quantitative feature metacarpal bones

An Improved Practical Byzantine Fault-Tolerant Algorithm Based on XGBoost Grouping for Consortium Chains

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2025年第1期82卷 1295-1311页

作者： Xiaowei Wang Haiyang Zhang Jiasheng Zhang Yingkai Ge Kexin Cui Zifu Peng Zhengyi Li Lihua Wang college of Electronic and Information Engineering Shandong University of Science and TechnologyQingdao266590China

In response to the challenges presented by the unreliable identity of the master node,high communication overhead,and limited network support size within the Practical Byzantine Fault-Tolerant(PBFT)algorithm for consortium chains,we propose an improved PBFT algorithm based on XGBoost grouping called XG-PBFT in this ***-PBFT constructs a dataset by training important parameters that affect node performance,which are used as classification indexes for *** XGBoost algorithm then is employed to train the dataset,and nodes joining the system will be grouped according to the trained grouping *** them,the nodes with higher parameter indexes will be assigned to the consensus group to participate in the consensus,and the rest of the nodes will be assigned to the general group to receive the consensus *** order to reduce the resource waste of the system,XG-PBFT optimizes the consensus protocol for the problem of high complexity of PBFT ***,we evaluate the performance of *** experimental results show that XG-PBFT can significantly improve the performance of throughput,consensus delay and communication complexity compared to the original PBFT algorithm,and the performance enhancement is significant compared to other algorithms in the case of a larger number of *** results demonstrate that the XG-PBFT algorithm is more suitable for large-scale consortium chains.

关键词： Consortium chain PBFT grouping reputation XGBoost

Unlocking the stable interface in aqueous zinc-ion battery with multifunctional xylose-based electrolyte additives

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 Energy Chemistry 2025年第1期100卷 770-778页

作者： Xiaoqin Li Jian Xiang Lu Qiu Xiaohan Chen Yinkun Zhao Yujue Wang Qu Yue Taotao Gao Wenlong Liu Dan Xiao Zhaoyu Jin Panpan Li Institute for Advanced Study Chengdu University School of Mechanical Engineering Chengdu University college of Food and Biological Engineering Chengdu University Institute of Fundamental and Frontier sciences University of Electronic Science and Technology of China college of Materials science and Engineering Sichuan University

The growth of dendrites and the side reactions occurring at the Zn anode pose significant challenges to the commercialization of aqueous Zn-ion batteries（AZIBs）. These challenges arise from the inherent conflict between mass transfer and electrochemical kinetics. In this study, we propose the use of a multifunctional electrolyte additive based on the xylose（Xylo） molecule to address these issues by modulating the solvation structure and electrode/electrolyte interface, thereby stabilizing the Zn anode. The introduction of the additive alters the solvation structure, creating steric hindrance that impedes charge transfer and then reduces electrochemical kinetics. Furthermore, in-situ analyses demonstrate that the reconstructed electrode/electrolyte interface facilitates stable and rapid Zn2+ion migration and suppresses corrosion and hydrogen evolution reactions. As a result, symmetric cells incorporating the Xylo additive exhibit significantly enhanced reversibility during the Zn plating/stripping process, with an impressively long lifespan of up to 1986 h, compared to cells using pure ZnSO4electrolyte. When combined with a polyaniline cathode, the full cells demonstrate improved capacity and long-term cyclic stability. This work offers an effective direction for improving the stability of Zn anode via electrolyte design, as well as highperformance AZIBs.

关键词： Solvation

Magneto‑Dielectric Synergy and Multiscale Hierarchical Structure Design Enable Flexible Multipurpose Microwave Absorption and Infrared Stealth Compatibility

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Nano-Micro Letters 2025年第2期17卷 401-416页

作者： Chen Li Leilei Liang Baoshan Zhang Yi Yang Guangbin Ji School of Electronic science and Engineering Nanjing UniversityNanjing 210093People’s Republic of China college of Materials science and Technology Nanjing University of Aeronautics and AstronauticsNanjing 210016People’s Republic of China

Developing advanced stealth devices to cope with radar-infrared(IR)fusion detection and diverse application scenarios is increasingly demanded,which faces significant challenges due to conflicting microwave and IR cloaking mechanisms and functional integration ***,we propose a multiscale hierarchical structure design,integrating wrinkled MXene IR shielding layer and flexible Fe_(3)O_(4)@C/PDMS microwave absorption *** top wrinkled MXene layer induces the intensive diffuse reflection effect,shielding IR radiation signals while allowing microwave to pass ***,the permeable microwaves are assimilated into the bottom Fe_(3)O_(4)@C/PDMS layer via strong magneto-electric *** theoretical and experimental optimization,the assembled stealth devices realize a near-perfect stealth capability in both X-band(8–12 GHz)and long-wave infrared(8–14μm)wavelength ***,it delivers a radar cross-section reduction of−20 dB m^(2),a large apparent temperature modulation range(ΔT=70℃),and a low average IR emissivity of ***,the optimal device demonstrates exceptional curved surface conformability,self-cleaning capability(contact angle≈129°),and abrasion resistance(recovery time≈5 s).This design strategy promotes the development of multispectral stealth technology and reinforces its applicability and durability in complex and hostile environments.

关键词： Microwave absorption Radar-infrared compatible stealth Wrinkled MXene Magneto-dielectric synergy Multifunction

维普期刊数据库