检索结果-南通市图书馆

维普期刊数据库

Enhancing cut selection through reinforcement learning

在线全文

学校读者我要写书评

暂无评论

science China Mathematics 2024年第6期67卷 1377-1394页

作者： Shengchao Wang Liang Chen Lingfeng Niu Yu-Hong Dai academy of Mathematics and Systems science Chinese Academy of SciencesBeijing100190China Research Center on Fictitious Economy and data science Chinese Academy of SciencesBeijing100190China

With the rapid development of artificial intelligence in recent years,applying various learning techniques to solve mixed-integer linear programming(MILP)problems has emerged as a burgeoning research *** from constructing end-to-end models directly,integrating learning approaches with some modules in the traditional methods for solving MILPs is also a promising *** cutting plane method is one of the fundamental algorithms used in modern MILP solvers,and the selection of appropriate cuts from the candidate cuts subset is crucial for enhancing *** to the reliance on expert knowledge and problem-specific heuristics,classical cut selection methods are not always transferable and often limit the scalability and generalizability of the cutting plane *** provide a more efficient and generalizable strategy,we propose a reinforcement learning(RL)framework to enhance cut selection in the solving process of ***,we design feature vectors to incorporate the inherent properties of MILP and computational information from the solver and represent MILP instances as bipartite ***,we choose the weighted metrics to approximate the proximity of feasible solutions to the convex hull and utilize the learning method to determine the weights assigned to each ***,a graph convolutional neural network is adopted with a self-attention mechanism to predict the value of weighting ***,we transform the cut selection process into a Markov decision process and utilize RL method to train the *** experiments are conducted based on a leading open-source MILP solver *** on both general and specific datasets validate the effectiveness and efficiency of our proposed approach.

关键词： reinforcement learning mixed-integer linear programming cutting plane method cut selection

维普期刊数据库

同方期刊数据库

Identity-Preserving Adversarial Training for Robust Network Embedding

在线全文

学校读者我要写书评

暂无评论

Journal of Computer science & Technology 2024年第1期39卷 177-191页

作者：岑科廷沈华伟曹婍徐冰冰程学旗 data Intelligence System Research Center Institute of Computing TechnologyChinese Academy of SciencesBeijing 100190China University of Chinese academy of sciences Beijing 101480China Beijing academy of Artificial Intelligence Beijing 100000China Chinese academy of sciences Key Laboratory of Network data science and Technology Institute of Computing Technology Chinese Academy of SciencesBeijing 100190China

Network embedding,as an approach to learning low-dimensional representations of nodes,has been proved extremely useful in many applications,e.g.,node classification and link ***,existing network embed-ding models are vulnerable to random or adversarial perturbations,which may degrade the performance of network em-bedding when being applied to downstream *** achieve robust network embedding,researchers introduce adversari-al training to regularize the embedding learning process by training on a mixture of adversarial examples and original ***,existing methods generate adversarial examples heuristically,failing to guarantee the imperceptibility of generated adversarial examples,and thus limit the power of adversarial *** this paper,we propose a novel method Identity-Preserving Adversarial Training(IPAT)for network embedding,which generates imperceptible adversarial exam-ples with explicit identity-preserving *** formalize such identity-preserving regularization as a multi-class classification problem where each node represents a class,and we encourage each adversarial example to be discriminated as the class of its original *** experimental results on real-world datasets demonstrate that our proposed IPAT method significantly improves the robustness of network embedding models and the generalization of the learned node representations on various downstream tasks.

关键词： network embedding identity-preserving adversarial training adversarial the example

A causal multiomics study discriminates the early immune features of Ad5-vectored Ebola vaccine recipients

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

The Innovation 2024年第3期5卷 77-87页

作者： Zhe Zhang Wenjing Yang Zhengshan Chen Haoang Chi Shipo Wu Wanru Zheng Ruochun Jin Busen Wang Yudong Wang Nan Huo Jinlong Zhang Xiaohong Song Liyang Xu Jun Zhang Lihua Hou Wei Chen Institute of Biotechnology Academy of Military Medical SciencesBeijing 100071China Department of Intelligent data science College of Computer Science and TechnologyNational University of Defense TechnologyChangsha 410073China Intelligent Game and Decision Lab Academy of Military ScienceBeijing 100091China

The vaccine-induced innate immune response is essential for the generation of an antibody *** date,how Ad5-vectored vaccines are influenced by preexisting anti-Ad5 antibodies during activation of the early immune response remains ***,we investigated the specific alterations in GP1,2-specific IgG-related elements of the early immune response at the genetic,molecular,and cellular levels on days 0,1,3,and 7 after Ad5-EBOV *** a causal multiomics analysis,distinct early immune responses associated with GP1,2-specific IgG were observed in Ad5-EBOV recipients with a low level of preexisting anti-Ad5 *** study revealed the correlates of the Ad5-EBOV-induced IgG response and provided mechanistic evidence for overcoming preexisting Ad5 immunity during the administration of Ad5-vectored vaccines.

关键词： vaccine immunity alterations

A blockchain-based data auditing scheme with key-exposure resistance for IIoT

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 327-328页

作者： Pan YANG Jingli REN Henan academy of Big data Zhengzhou University

The Industrial Internet of Things(IIoT) enables enterprises to collect data from end devices and outsource the data to cloud servers for flexible data sharing. Public auditing plays an important role in ensuring the integrity of the *** are blockchain-based public auditing schemes that utilize smart contracts to achieve decentralized verification(such as [1]),

关键词：

Transcranial Magneto-Acoustic Stimulation Attenuates Synaptic Plasticity Impairment through the Activation of Piezo1 in Alzheimer’s Disease Mouse Model

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Research 2024年第1期2023卷 81-95页

作者： Fangxuan Chu Ruxin Tan Xin Wang Xiaoqing Zhou Ren Ma Xiaoxu Ma Ying Li Ruixu Liu Chunlan Zhang Xu Liu Tao Yin Zhipeng Liu Institute of Biomedical Engineering Chinese Academy of Medical Sciences and Peking Union Medical CollegeTianjin300192China Tianjin Institutes of Health science Tianjin301600China Neuroscience Center Chinese Academy of Medical Science&Peking Union Medical CollegeBeijing100730China

The neuropathological features of Alzheimer’s disease include amyloid *** emerging evidence suggests that Piezo1,a mechanosensitive cation channel,plays a critical role in transforming ultrasound-related mechanical stimuli through its trimeric propeller-like structure,but the importance of Piezo1-mediated mechanotransduction in brain functions is less ***,apart from mechanical stimulation,Piezo1 channels are strongly modulated by *** assume that Piezo1 may play a role in converting mechanical and electrical signals,which could induce the phagocytosis and degradation of Aβ,and the combined effect of mechanical and electrical stimulation is superior to single mechanical ***,we design a transcranial magneto-acoustic stimulation(TMAS)system,based on transcranial ultrasound stimulation(TUS)within a magnetic field that combines a magnetoacoustic coupling effect electric field and the mechanical force of ultrasound,and applied it to test the above hypothesis in 5xFAD *** tests,in vivo electrophysiological recordings,Golgi–Cox staining,enzyme-linked immunosorbent assay,immunofluorescence,immunohistochemistry,real-time quantitative PCR,Western blotting,RNA sequencing,and cerebral blood flow monitoring were used to assess whether TMAS can alleviate the symptoms of AD mouse model by activating Piezo1.

关键词： stimulation Alzheimer Piezo1

Blockchain-Based Key Management Scheme Using Rational Secret Sharing

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 2024年第4期79卷 307-328页

作者： Xingfan Zhao Changgen Peng Weijie Tan Kun Niu State Key Laboratory of Public Big data College of Computer Science and TechnologyGuizhou UniversityGuiyang550025China Guizhou Big data academy Guizhou UniversityGuiyang550025China

Traditional blockchain key management schemes store private keys in the same location,which can easily lead to security issues such as a single point of ***,decentralized threshold key management schemes have become a research focus for blockchain private key *** security of private keys for blockchain user wallet is highly related to user identity authentication and digital asset *** threshold blockchain private key management schemes based on verifiable secret sharing have made some progress,but these schemes do not consider participants’self-interested behavior,and require trusted nodes to keep private key fragments,resulting in a narrow application scope and low deployment efficiency,which cannot meet the needs of personal wallet private key escrow and recovery in public *** design a private key management scheme based on rational secret sharing that considers the self-interest of participants in secret sharing protocols,and constrains the behavior of rational participants through reasonable mechanism design,making it more suitable in distributed scenarios such as the public *** proposed scheme achieves the escrow and recovery of personal wallet private keys without the participation of trusted nodes,and simulate its implementation on smart *** to other existing threshold wallet solutions and keymanagement schemes based on password-protected secret sharing(PPSS),the proposed scheme has a wide range of applications,verifiable private key recovery,low communication overhead,higher computational efficiency when users perform one-time multi-key escrow,no need for trusted nodes,and personal rational constraints and anti-collusion attack capabilities.

关键词： Blockchain smart contract rational secret sharing key management

On the convergence of tracking differentiator with multiple stochastic disturbances

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 157-169页

作者： Zehao WU Huacheng ZHOU Baozhu GUO Feiqi DENG School of Mathematics and Big data Foshan University School of Mathematics and Statistics Central South University academy of Mathematics and Systems science Chinese Academy of Sciences Systems Engineering Institute South China University of Technology

This paper investigates the convergence, noise-tolerance, and filtering performance of a tracking differentiator in the presence of multiple stochastic disturbances for the first time. We consider a general case wherein the input signal is corrupted by additive colored noise, and the tracking differentiator is disturbed by additive colored noise and white noise. The tracking differentiator is shown to track the input signal and its generalized derivatives in the mean square sense. Further, the almost sure convergence can be achieved when the stochastic noise affecting the input signal is vanishing. Herein, numerical simulations are performed to validate the theoretical results.

关键词： tracking differentiator convergence noise-tolerance filtering performance multiple stochastic disturbances

Novel Rifle Number Recognition Based on Improved YOLO in Military Environment

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第1期78卷 249-263页

作者： Hyun Kwon Sanghyun Lee Department of Artificial Intelligence and data science Korea Military AcademySeoulKorea Graduate School of Information Security Korea Advanced Institute of Science and TechnologyDaejeonKorea

Deep neural networks perform well in image recognition,object recognition,pattern analysis,and speech *** military applications,deep neural networks can detect equipment and recognize *** military equipment,it is necessary to detect and recognize rifle management,which is an important piece of equipment,using deep neural *** have been no previous studies on the detection of real rifle numbers using real rifle image *** this study,we propose a method for detecting and recognizing rifle numbers when rifle image data are *** proposed method was designed to improve the recognition rate of a specific dataset using data fusion and transfer *** the proposed method,real rifle images and existing digit images are fusedas trainingdata,andthe final layer is transferredto theYolov5 *** detectionand recognition performance of rifle numbers was improved and analyzed using rifle image and numerical *** used actual rifle image data(K-2 rifle)and numeric image datasets,as an experimental *** was used as the machine learning *** results show that the proposed method maintains 84.42% accuracy,73.54% precision,81.81% recall,and 77.46% F1-score in detecting and recognizing rifle *** proposed method is effective in detecting rifle numbers.

关键词： Machine learning deep neural network rifle number recognition detection

On convergence of covariance matrix of empirical Bayes hyper-parameter estimator

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Control Theory and Technology 2024年第2期22卷 149-162页

作者： Yue Ju Biqiang Mu Tianshi Chen School of data science and Shenzhen Research Institute of Big data The Chinese University of Hong KongShenzhenShenzhen518172GuangdongChina Division of Decision and Control Systems School of Electrical Engineering and Computer ScienceKTH Royal Institute of Technology10044StockholmSweden Key Laboratory of Systems and Control Institute of Systems ScienceAcademy of Mathematics and System ScienceChinese Academy of SciencesBeijing100190China

Regularized system identification has become the research frontier of system identification in the past *** related core subject is to study the convergence properties of various hyper-parameter estimators as the sample size goes to *** this paper,we consider one commonly used hyper-parameter estimator,the empirical Bayes(EB).Its convergence in distribution has been studied,and the explicit expression of the covariance matrix of its limiting distribution has been ***,what we are truly interested in are factors contained in the covariance matrix of the EB hyper-parameter estimator,and then,the convergence of its covariance matrix to that of its limiting distribution is *** general,the convergence in distribution of a sequence of random variables does not necessarily guarantee the convergence of its covariance ***,the derivation of such convergence is a necessary complement to our theoretical analysis about factors that influence the convergence properties of the EB hyper-parameter *** this paper,we consider the regularized finite impulse response(FIR)model estimation with deterministic inputs,and show that the covariance matrix of the EB hyper-parameter estimator converges to that of its limiting ***,we run numerical simulations to demonstrate the efficacy of ourtheoretical results.

关键词： Regularized system identification Hyper-parameter estimator Empirical Bayes Convergence of covariance matrix