检索结果-南通市图书馆

Recommendation Method for Contrastive Enhancement of Neighborhood Information

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第1期78卷 453-472页

作者： Hairong Wang beijing Zhou Lisi zhang He Ma School of Computer Science and Engineering North Minzu UniversityNingxia750021China

Knowledge graph can assist in improving recommendation performance and is widely applied in various person-alized recommendation ***,existing knowledge-aware recommendation methods face challenges such as weak user-item interaction supervisory signals and noise in the knowledge *** tackle these issues,this paper proposes a neighbor information contrast-enhanced recommendation method by adding subtle noise to construct contrast views and employing contrastive learning to strengthen supervisory signals and reduce knowledge ***,first,this paper adopts heterogeneous propagation and knowledge-aware attention networks to obtain multi-order neighbor embedding of users and items,mining the high-order neighbor informa-tion of users and ***,in the neighbor information,this paper introduces weak noise following a uniform distribution to construct neighbor contrast views,effectively reducing the time overhead of view *** paper then performs contrastive learning between neighbor views to promote the uniformity of view information,adjusting the neighbor structure,and achieving the goal of reducing the knowledge noise in the knowledge ***,this paper introduces multi-task learning to mitigate the problem of weak supervisory *** validate the effectiveness of our method,experiments are conducted on theMovieLens-1M,MovieLens-20M,Book-Crossing,and Last-FM *** results showthat compared to the best baselines,our method shows significant improvements in AUC and F1.

关键词： Contrastive learning knowledge graph recommendation method

H_(∞)/Passive Synchronization of Semi-Markov Jump Neural Networks Subject to Hybrid Attacks via an Activation Function Division Approach

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

Journal of Systems Science & Complexity 2024年第3期37卷 1023-1036页

作者： zhang Ziwei SHEN Hao SU lei School of Electrical and Information Engineering Anhui University of TechnologyMa'anshan 243002China Anhui Province Key Laboratory of Special Heavy Load Robot and School of Electrical and Information Engineering Anhui University of TechnologyMa'anshan243002China

In this work,an H_(∞)/passive-based secure synchronization control problem is investigated for continuous-time semi-Markov neural networks subject to hybrid attacks,in which hybrid attacks are the combinations of denial-of-service attacks and deception attacks,and they are described by two groups of independent Bernoulli *** this foundation,via the Lyapunov stability theory and linear matrix inequality technology,the H_(∞)/passive-based performance criteria for semi-Markov jump neural networks are ***,an activation function division approach for neural networks is adopted to further reduce the conservatism of the ***,a simulation example is provided to verify the validity and feasibility of the proposed method.

关键词： Activation function division approach deception attacks denial-of-service attacks H_(∞)/passive synchronization semi-Markov jump neural networks

Pre-Training Physics-Informed Neural Network with Mixed Sampling and Its Application in High-Dimensional Systems

在线全文

学校读者我要写书评

暂无评论

Journal of Systems Science & Complexity 2024年第2期37卷 494-510页

作者： LIU Haiyi zhang Yabin WANG lei School of Mathematics and Physics North China Electric Power UniversityBeijing 102206China School of Control and Computer Engineering North China Electric Power UniversityBeijing 102206China

Recently,the physics-informed neural network shows remarkable ability in the context of solving the low-dimensional nonlinear partial differential ***,for some cases of high-dimensional systems,such technique may be time-consuming and *** this paper,the authors put forward a pre-training physics-informed neural network with mixed sampling(pPINN)to address these *** based on the initial and boundary conditions,the authors design the pre-training stage to filter out the set of the misfitting points,which is regarded as part of the training points in the next *** authors further take the parameters of the neural network in Stage 1 as the initialization in Stage *** advantage of the proposed approach is that it takes less time to transfer the valuable information from the first stage to the second one to improve the calculation accuracy,especially for the high-dimensional *** verify the performance of the pPINN algorithm,the authors first focus on the growing-and-decaying mode of line rogue wave in the Davey-Stewartson I *** case is the accelerated motion of lump in the inhomogeneous Kadomtsev-Petviashvili equation,which admits a more complex evolution than the uniform *** exact solution provides a perfect sample for data experiments,and can also be used as a reference frame to identify the performance of the *** experiments confirm that the pPINN algorithm can improve the prediction accuracy and training efficiency well,and reduce the training time to a large extent for simulating nonlinear waves of high-dimensional equations.

关键词： High-dimensional systems mixed sampling nonlinear wave pre-training physics-informed neural network

Digital Twin Modeling Enabled Machine Tool Intelligence:A Review

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Mechanical Engineering 2024年第2期37卷 29-54页

作者： lei zhang Jianhua Liu Cunbo Zhuang School of Mechanical Engineering Tianjin University of CommerceTianjin 300134China Laboratory of Digital Manufacturing School of Mechanical EngineeringBeijing Institute of TechnologyBeijing 10081China

Machine tools,often referred to as the“mother machines”of the manufacturing industry,are crucial in developing smart manufacturing and are increasingly becoming more *** twin technology can promote machine tool intelligence and has attracted considerable research ***,there is a lack of clear and systematic analyses on how the digital twin technology enables machine tool ***,digital twin modeling was identified as an enabling technology for machine tool intelligence based on a comparative study of the characteristics of machine tool intelligence and digital *** review then delves into state-of-the-art digital twin modelingenabled machine tool intelligence,examining it from the aspects of data-based modeling and mechanism-data dual-driven ***,it highlights three bottleneck issues facing the *** these problems,the architecture of a digital twin machine tool(DTMT)is proposed,and three key technologies are expounded in detail:Data perception and fusion technology,mechanism-data-knowledge hybrid-driven digital twin modeling and virtual-real synchronization technology,and dynamic optimization and collaborative control technology for multilevel ***,future research directions for the DTMT are *** work can provide a foundation basis for the research and implementation of digital-twin modeling-enabled machine tool intelligence,making it significant for developing intelligent machine tools.

关键词： Machine tool Digital twin Smart manufacturing Synchronization

Chien-physics-informed neural networks for solving singularly perturbed boundary-layer problems

在线全文

学校读者我要写书评

暂无评论

Applied Mathematics and Mechanics(English Edition) 2024年第9期45卷 1467-1480页

作者： Long WANG lei zhang Guowei HE The State Key Laboratory of Nonlinear Mechanics Institute of MechanicsChinese Academy of SciencesBeijing 100190China School of Engineering Sciences University of Chinese Academy of SciencesBeijing 100049China

A physics-informed neural network(PINN)is a powerful tool for solving differential equations in solid and fluid ***,it suffers from singularly perturbed boundary-layer problems in which there exist sharp changes caused by a small perturbation parameter multiplying the highest-order *** this paper,we introduce Chien's composite expansion method into PINNs,and propose a novel architecture for the PINNs,namely,the Chien-PINN(C-PINN)*** novel PINN method is validated by singularly perturbed differential equations,and successfully solves the wellknown thin plate bending *** particular,no cumbersome matching conditions are needed for the C-PINN method,compared with the previous studies based on matched asymptotic expansions.

关键词： physics-informed neural network(PINN) singular perturbation boundarylayer problem composite asymptotic expansion

Multi-Scale-Matching neural networks for thin plate bending problem

在线全文

学校读者我要写书评

暂无评论

Theoretical & Applied Mechanics Letters 2024年第1期14卷 11-15页

作者： lei zhang Guowei He The State Key Laboratory of Nonlinear Mechanics Institute of MechanicsChinese Academy of SciencesBeijing 100190China School of Engineering Science University of Chinese Academy of SciencesBeijing 100049China

Physics-informed neural networks are a useful machine learning method for solving differential equations,but encounter challenges in effectively learning thin boundary layers within singular perturbation *** resolve this issue,multi-scale-matching neural networks are proposed to solve the singular perturbation *** by matched asymptotic expansions,the solution is decomposed into inner solutions for small scales and outer solutions for large scales,corresponding to boundary layers and outer regions,***,to conform neural networks,we introduce exponential stretched variables in the boundary layers to avoid semiinfinite region *** results for the thin plate problem validate the proposed method.

关键词： Singular perturbation Physics-informed neural networks Boundary layer Machine learning

Self-Sustaining of Critical Park Microgrids Integrating Mobile Emergency Generators Subjective to Major Outage

在线全文

学校读者我要写书评

暂无评论

CSEE Journal of Power and Energy Systems 2024年第4期10卷 1441-1453页

作者： Quan Sui lei zhang School of Electrical and Information Engineering Zhengzhou UniversityZhengzhou 450001China School of Electrical and New Energy Three Gorges UniversityYichang 443002China

In the event of a major power outage,critical park microgrids(PMGs)could be self-sustaining if mobile emergency generators(MEGs)are stationed to share ***,the need for privacy protection and the value of flexible power support on minute-time scales have not been given enough *** address the problem,this paper proposes a new self-sustaining strategy for critical PMGs integrating ***,to promote the cooperation between PMG and MEG,a bi-level benefit distribution mechanism is designed,where the participants'multiple roles and contributions are identified,and good behaviors are also ***,to increase the alliance benefits,three loss coordination modes are presented to guide the power exchange at the minute level between the MEG and PMG,considering the volatility of renewable generation and *** this basis,a multi-time scale power-energy scheduling strategy is formulated via the alternating direction method of multipliers(ADMM)to coordinate the PMG and ***,a dimensionality reduction technology is designed to equivalently simplify the optimization problem to facilitate the adaptive-step-based ADMM *** studies indicate that the proposed strategy achieves the self-sustaining of PMGs integrating MEGs while increasing the economy by no less than 3.1%.

关键词： Distributed optimization loss coordination mode mobile emergency generator park microgrid power-energy self-sustaining privacy protection

Vitrification cryopreservation of ligaments based on zwitterionic betaine

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 Journal of Chemical Engineering 2024年第8期72卷 1-9页

作者： Liming zhang Xinmeng Liu Haoyue Li lei zhang Department of Biochemical Engineering Frontier Science Center for Synthetic Biology and Key Laboratory of Systems Bioengineering(MOE)School of Chemical Engineering and TechnologyTianjin UniversityTianjin 300350China Haihe Laboratory of Sustainable Chemical Transformations Tianjin 300192China

Ligament cryopreservation enables a prolonged shelf life of allogeneic ligament grafts,which is fundamentally important to ligament ***,conventional cryopreservation techniques fail to eliminate the damage caused by ice crystal growth and the toxicity of cryopreservation agents(CPAs).Here,we report a novel CPA vitrification formulation primarily composed of betaine for ligament *** optimization was conducted on the methods for vitrification and rewarming,as well as the loading and unloading conditions,based on the critical cooling rate(CCR),critical warming rate(CWR),and permeation properties of the *** biomechanical and histological level tests,we demonstrate the superior performance of our method in ligament *** 30 days of vitrification cryopreservation,parameters such as the Young's modulus,tensile stress,denaturation temperature,and glycosaminoglycans content of the ligament remained essentially *** work pioneers the application of ice-free cryopreservation for ligament and holds great potential for improving the long-term storage of ligament,providing valuable insights for future cryopreservation technique development.

关键词： Ligament Betaine Vitrification Cryopreservation

Higher-order properties and extensions for indirect MRAC and APPC of linear systems

在线全文

学校读者我要写书评

暂无评论

Science china(Information Sciences) 2024年第4期67卷 218-238页

作者： Yanjun zhang Zhipeng zhang Jian SUN lei WANG Kangkang zhang National Key Lab of Autonomous Intelligent Unmanned Systems Beijing Institute of Technology beijing institute of Technology Chongqing Innovation Center College of Control Science and Engineering Zhejiang University Department of Electrical and Electronic Engineering Imperial College London KIOS Research and Innovation Center of Excellence University of Cyprus

Recently, a reference derived some new higher-order output tracking properties for direct model reference adaptive control(MRAC) of linear time-invariant(LTI) systems: limt→∞ e~((i))(t) = 0, i = 1,..., n~*-1, where n~* and e~((i))(t) denote the relative degree of the system and the i-th derivative of the output tracking error, respectively. However, a naturally arising question involves whether indirect adaptive control(including indirect MRAC and indirect adaptive pole placement control) of LTI systems still has higher-order tracking properties. Such properties have not been reported in the literature. Therefore, this paper provides an affirmative answer to this question. Such higher-order tracking properties are new discoveries since they hold without any additional design conditions and, in particular, without the persistent excitation condition. Given the higher-order properties, a new adaptive control system is developed with stronger tracking features.(1) It can track a reference signal with any order derivatives being unknown.(2) It has higher-order exponential or practical output tracking properties.(3) Finally, it is different from the usual MRAC system, whose reference signal’s derivatives up to the n~* order are assumed to be known. Finally, two simulation examples are provided to verify the theoretical results obtained in this paper.

关键词： higher-order tracking indirect adaptive control model reference adaptive control adaptive pole placement control