检索结果-南通市图书馆

International Journal of Mental Health Promotion 2024年第4期26卷 261-269页

作者： Yanjing Cao Chenchen Xu Qi Li Shan Lu Jing Xiao Beijing Key Laboratory of learning and Cognition and Department of Psychology Capital Normal UniversityBeijing100048China center for Child development Capital Normal UniversityBeijing100048China

Background:Valid and reliable measures of depressive symptoms are crucial for understanding risk factors,outcomes,and interventions across rural and urban *** this need,the longitudinal invariance of these measures over time remains *** research explores the structural components of the center for Epidemiological Studies Depression Scale(CES-D)and examines its consistency across various living environments and temporal stability in a cohort of Chinese ***:In the initial phase,1,042 adolescents furnished demographic details and undertook the CES-D *** a three-month interval,967 of these participants repeated the CES-D *** study employed Confirmatory factor analysis(CFA)to scrutinize the scale’s structural *** investigated factorial invariance by conducting a twopronged CFA:one comparing urban *** backgrounds,and another contrasting the results from the initial assessment with those from the ***:The CES-D demonstrated adequate reliability in both rural and urban high school student *** preliminary four-factor model applied to the CES-D demonstrated a good fit with the collected *** tests,including multigroup analyses comparing rural and urban samples and longitudinal assessments,confirmed the scale’s ***:The results suggest that the CES-D serves as a reliable instrument for evaluating depressive symptoms among Chinese *** applicability is consistent across different living environments and remains stable over time.

关键词： Depression factor structure measurement invariance Chinese adolescent longitudinal invariance

Understanding adversarial attacks on observations in deep reinforcement learning

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5期67卷 69-83页

作者： You QIAOBEN Chengyang YING Xinning ZHOU Hang SU Jun ZHU Bo ZHANG Department of Computer Science and Technology Beijing National Research Center for Information Science and Technology Tsinghua-Bosch Joint Center for Machine Learning Institute for Artificial Intelligence Tsinghua University Peng Cheng Laboratory

Deep reinforcement learning models are vulnerable to adversarial attacks that can decrease the cumulative expected reward of a victim by manipulating its observations. Despite the efficiency of previous optimization-based methods for generating adversarial noise in supervised learning, such methods might not achieve the lowest cumulative reward since they do not generally explore the environmental ***, a framework is provided to better understand the existing methods by reformulating the problem of adversarial attacks on reinforcement learning in the function space. The reformulation approach adopted herein generates an optimal adversary in the function space of targeted attacks, repelling them via a generic two-stage framework. In the first stage, a deceptive policy is trained by hacking the environment and discovering a set of trajectories routing to the lowest reward or the worst-case performance. Next, the adversary misleads the victim to imitate the deceptive policy by perturbing the observations. Compared to existing approaches, it is theoretically shown that our adversary is strong under an appropriate noise level. Extensive experiments demonstrate the superiority of the proposed method in terms of efficiency and effectiveness, achieving state-of-the-art performance in both Atari and MuJoCo environments.

关键词： deep learning reinforcement learning adversarial robustness adversarial attack

Preoperative serum cortisone levels are associated with cognition in preschool‑aged children with tetralogy of Fallot after corrective surgery:new evidence from human populations and mice

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

World Journal of Pediatrics 2024年第2期20卷 173-184页

作者： Si-Yu Ma Yu-Ting Liu Yue-Shuang Cun Qiang Wang Ming-Cui Fu Ke-De Wu Xin-Yu Cai Shu-Ting Cheng Nishant Patel Min Da Liang Hu Zhuoga Deqin Xue-Jun Kang Ming Yang Xu-Ming Mo Department of Cardiothoracic Surgery Children’s Hospital of Nanjing Medical University72 Guangzhou RoadNanjing 210008China Department of Radiology Children’s Hospital of Nanjing Medical University72 Guangzhou RoadNanjing 210008China Key Laboratory of Child development and learning Science Research Center For Learning ScienceSchool of Biological Sciences&Medical EngineeringMinistry of EducationSoutheast UniversityNanjing 210096China Medical School of Nanjing University Nanjing 210093China

Background Tetralogy of Fallot(TOF)is the most common cyanotic congenital heart *** with TOF would be confronted with neurological impairment across their *** study aimed to identify the risk factors for cerebral morphology changes and cognition in postoperative preschool-aged children with *** We used mass spectrometry(MS)technology to assess the levels of serum metabolites,Wechsler preschool and primary scale of intelligence-Fourth edition(WPPSI-Ⅳ)index scores to evaluate neurodevelopmental levels and multimodal magnetic resonance imaging(MRI)to detect cortical morphological *** Multiple linear regression showed that preoperative levels of serum cortisone were positively correlated with the gyrification index of the left inferior parietal gyrus in children with TOF and negatively related to their lower visual spaces index and nonverbal ***,preoperative SpO_(2) was negatively correlated with levels of serum cortisone after adjusting for all ***,after intervening levels of cortisone in chronic hypoxic model mice,total brain volumes were reduced at both postnatal(P)11.5 and P30 *** Our results suggest that preoperative serum cortisone levels could be used as a biomarker of neurodevelopmental impairment in children with *** study findings emphasized that preoperative levels of cortisone could influence cerebral development and cognition abilities in children with TOF.

关键词： Cognition Cortisone MRI Neurodevelopment Tetralogy of Fallot

Meta-path reasoning of knowledge graph for commonsense question answering

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 Computer Science 2024年第1期18卷 49-59页

作者： Miao ZHANG Tingting HE Ming DONG National Engineering Research center for E-learning Central China Normal UniversityWuhan 430079China Hubei Provincial Key Laboratory of Artificial Intelligence and Smart learning Central China Normal UniversityWuhan 430079China National Language Resources Monitoring&Research center for Network Media Central China Normal UniversityWuhan 430079China School of Computer Central China Normal UniversityWuhan 430079China

Commonsense question answering(CQA)requires understanding and reasoning over QA context and related commonsense knowledge,such as a structured Knowledge Graph(KG).Existing studies combine language models and graph neural networks to model ***,traditional knowledge graph are mostly concept-based,ignoring direct path evidence necessary for accurate *** this paper,we propose MRGNN(Meta-path Reasoning Graph Neural Network),a novel model that comprehensively captures sequential semantic information from concepts and *** MRGNN,meta-paths are introduced as direct inference evidence and an original graph neural network is adopted to aggregate features from both concepts and paths *** conduct sufficient experiments on the CommonsenceQA and OpenBookQA datasets,showing the effectiveness of ***,we conduct further ablation experiments and explain the reasoning behavior through the case study.

关键词： question answering knowledge graph graph neural network meta-path reasoning

A Framework Based on the DAO and NFT in Blockchain for Electronic Document 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

Computer Modeling in Engineering & Sciences 2024年第9期140卷 2373-2395页

作者： Lin Chen Jiaming Zhu Yuting Xu Huanqin Zheng Shen Su Cyberspace Institute of Advanced Technology Guangzhou UniversityGuangzhou510006China Engineering Research center of lntegration and Application of Digital learning Technology Ministry of EducationBeijing100816China

In the information age,electronic documents(e-documents)have become a popular alternative to paper documents due to their lower costs,higher dissemination rates,and ease of knowledge ***,digital copyright infringements occur frequently due to the ease of copying,which not only infringes on the rights of creators but also weakens their creative ***,it is crucial to establish an e-document sharing system that enforces copyright ***,the existing centralized system has outstanding vulnerabilities,and the plagiarism detection algorithm used cannot fully detect the context,semantics,style,and other factors of the *** watermark technology is only used as a means of infringement *** paper proposes a decentralized framework for e-document sharing based on decentralized autonomous organization(DAO)and non-fungible token(NFT)in *** use of blockchain as a distributed credit base resolves the vulnerabilities inherent in traditional centralized *** e-document evaluation and plagiarism detection mechanisms based on the DAO model effectively address challenges in comprehensive text information checks,thereby promoting the enhancement of e-document *** mechanism for protecting and circulating e-document copyrights using NFT technology ensures effective safeguarding of users’e-document copyrights and facilitates e-document ***,recognizing the security issues within the DAO governance mechanism,we introduce an innovative optimization *** experimentation,we validate the enhanced security of the optimized governance mechanism,reducing manipulation risks by up to 51%.Additionally,by utilizing evolutionary game analysis to deduce the equilibrium strategies of the framework,we discovered that adjusting the reward and penalty parameters of the incentive mechanism motivates creators to generate superior quality and unique e-documents,while evaluators are more likely to engage in

关键词： Electronic document sharing blockchain DAO NFT evolutionary game

A Review on the Security of the Ethereum-Based DeFi Ecosystem

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2024年第4期139卷 69-101页

作者： Yue Xue Dunqiu Fan Shen Su Jialu Fu Ning Hu Wenmao Liu Zhihong Tian Cyberspace Institute of Advanced Technology Guangzhou UniversityGuanzhou510000China Innovation center NSFOCUS Inc.Beijing100089China Engineering Research center of Integration and Application of Digital learning Technology Ministry of EducationBeijing100816China

Decentralized finance(DeFi)is a general term for a series of financial products and *** is based on blockchain technology and has attracted people’s attention because of its open,transparent,and intermediary *** them,the DeFi ecosystem based on Ethereum-based blockchains attracts the most ***,the current decentralized financial system built on the Ethereum architecture has been exposed to many smart contract vulnerabilities during the last few ***,we believe it is time to improve the understanding of the prevailing Ethereum-based DeFi ecosystem security *** that end,we investigate the Ethereum-based DeFi security issues:1)inherited from the real-world financial system,which can be solved by macro-control;2)induced by the problems of blockchain architecture,which require a better blockchain platform;3)caused by DeFi invented applications,which should be focused on during the project *** on that,we further discuss the current solutions and potential directions ofDeFi *** to our research,we could provide a comprehensive vision to the research community for the improvement of Ethereum-basedDeFi ecosystem security.

关键词： Blockchain smart contract decentralized finance DeFi security

A Bitcoin Address Multi-Classification Mechanism Based on Bipartite Graph-Based Maximization Consensus

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2024年第4期139卷 783-800页

作者： Lejun Zhang Junjie Zhang Kentaroh Toyoda Yuan Liu Jing Qiu Zhihong Tian Ran Guo College of Information Engineering Yangzhou UniversityYangzhou225127China Cyberspace Institute Advanced Technology Guangzhou UniversityGuangzhou510006China Research and development center for E-learning Ministry of EducationBeijing100039China Institute of High Performance Computing(IHPC) Agency for ScienceTechnology and Research(A∗STAR)Singapore138632Singapore School of Physics and Materials Science Guangzhou UniversityGuangzhou510006China

Bitcoin is widely used as the most classic electronic currency for various electronic services such as exchanges,gambling,marketplaces,and also scams such as high-yield investment *** the services operated by a Bitcoin address can help determine the risk level of that address and build an alert model *** engineering can also be used to flesh out labeled addresses and to analyze the current state of Bitcoin in a small *** this paper,we address the problem of identifying multiple classes of Bitcoin services,and for the poor classification of individual addresses that do not have significant features,we propose a Bitcoin address identification scheme based on joint multi-model prediction using the mapping relationship between addresses and *** innovation of the method is to(1)Extract as many valuable features as possible when an address is given to facilitate the multi-class service identification task.(2)Unlike the general supervised model approach,this paper proposes a joint prediction scheme for multiple learners based on address-entity mapping ***,after obtaining the overall features,the address classification and entity clustering tasks are performed separately,and the results are subjected to graph-basedmaximization *** final result ismade to baseline the individual address classification results while satisfying the constraint of having similarly behaving entities as far as *** testing and evaluating over 26,000 Bitcoin addresses,our feature extraction method captures more useful *** addition,the combined multi-learner model obtained results that exceeded the baseline classifier reaching an accuracy of 77.4%.

关键词： Bitcoin multi-service classification graph maximization consensus data security

A machine learning framework for remaining useful lifetime prediction of li-ion batteries using diverse neural networks

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Energy and AI 2024年第1期15卷 102-135页

作者： Junghwan Lee Huanli Sun Yongshan Liu Xue Li First Automobile Works Group Corporation Research and development center No.1 Xinhongqi StreetChangchun130013JilinChina

Accurate prediction of the remaining useful life(RUL)of lithium-ion batteries(LIBs)is pivotal for enhancing their operational efficiency and safety in diverse *** operational advantages,precise RUL predictions can also expedite advancements in cell design and fast-charging methodologies,thereby reducing cycle testing *** artificial neural networks(ANNs)showing promise in this domain,determining the best-fit architecture across varied datasets and optimization approaches remains *** study introduces a machine learning framework for systematically evaluating multiple ANN *** only 30%of a training dataset derived from 124 LIBs subjected to various charging regimes,an extensive evaluation is conducted across 7 ANN *** architecture is optimized in terms of hyperparameters using this framework,a process that spans 145 days on an NVIDIA GeForce RTX 4090 *** optimizing each model to its best configuration,a fair and standardized basis for comparing their RUL predictions is *** research also examines the impact of different cycling windows on predictive *** a stratified partitioning technique underscores the significance of consistent dataset representation across ***,using only the features derived from individual charge–discharge cycles,our top-performing model,based on data from just 40 cycles,achieves a mean absolute percentage error of 10.7%.

关键词： Remaining useful life Artificial neural networks Li-ion batteries Deep neural networks Machine learning Hyperparameter optimization

Using Machine learning to Identify and Optimize Sensitive Parameters in Urban Flood Model Considering Subsurface Characteristics

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

International Journal of Disaster Risk Science 2024年第1期15卷 116-133页

作者： Hengxu Jin Yu Zhao Pengcheng Lu Shuliang Zhang Yiwen Chen Shanghua Zheng Zhizhou Zhu Key Laboratory of VGE of Ministry of Education Nanjing Normal UniversityNanjing 210023China Jiangsu center for Collaborative Innovation in Geographical Information Resource development and Application Nanjing 210023China

This study presents a novel method for optimizing parameters in urban flood models,aiming to address the tedious and complex issues associated with parameter ***,a coupled one-dimensional pipe network runoff model and a two-dimensional surface runoff model were integrated to construct an interpretable urban flood ***,a principle for dividing urban hydrological response units was introduced,incorporating surface attribute *** K-means algorithm was used to explore the clustering patterns of the uncertain parameters in the model,and an artificial neural network(ANN)was employed to identify the sensitive ***,a genetic algorithm(GA) was used to calibrate the parameter thresholds of the sub-catchment units in different urban land-use zones within the flood *** results demonstrate that the parameter optimization method based on K-means-ANN-GA achieved an average Nash-Sutcliffe efficiency coefficient(NSE) of *** to the ANN-GA and K-means-deep neural networks(DNN) methods,the proposed method better characterizes the runoff generation and flow *** study demonstrates the significant potential of combining machine learning techniques with physical knowledge in parameter optimization research for flood models.

关键词： Artifcial neural network Coupled urban fooding model Genetic algorithm K-means algorithm Subcatchment delineation Uncertain parameters

Hippo-YAP/TAZ signaling in breast cancer:Reciprocal regulation of microRNAs and implications in precision medicine

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

Genes & Diseases 2024年第2期11卷 760-771页

作者： Farzad Sadri Seyede fatemeh Hosseini Zohreh Rezaei Mohammad Fereidouni student Research Committee Birjand University of Medical SciencesBirjand ***Iran Tabas School of Nursing Birjand University of Medical SciencesBirjand ***Iran Department of Biology University of Sistan and BaluchestanZahedan ***Iran Cellular and Molecular Research center Birjand University of Medical SciencesBirjand ***Iran

Breast cancer is a molecularly heterogeneous disease and the most common female *** recent years,therapy approaches have evolved to accommodate molecular diversity,with a focus on more biologically based therapies to minimize negative *** regulate cell fate in human breast cells,the Hippo signaling pathway has been associated with the alpha subtype of estrogen *** pathway regulates tissue size,regeneration,and healing,as well as the survival of tissue-specific stem cells,proliferation,and apoptosis in a variety of organs,allowing for cell *** signaling is mediated by the kinases MST1,MST2,LATS1,and LATS2,as well as the adaptor proteins SAV1 and *** kinases phosphorylate the downstream effectors of the Hippo pathway,yes-associated protein(YAP),and transcriptional coactivator with PDZ-binding motif(TAZ),suppressing the expression of their downstream target *** Hippo signaling pathway kinase cascade plays a significant role in all *** the principles of this kinase cascade would prevent the occurrence of breast *** recent years,small noncoding RNAs,or microRNAs,have been implicated in the development of several malignancies,including breast *** interconnections between miRNAs and Hippo signaling pathway core proteins in the breast,on the other hand,remain poorly *** this review,we focused on highlighting the Hippo signaling system,its key parts,its importance in breast cancer,and its regulation by miRNAs and other related pathways.

关键词： Breast cancer Hippo signaling Large tumor suppressor kinase 1 microRNAs PDZ-binding motif Yes-associated protein