检索结果-内蒙古大学图书馆

4th International Conference on Big Data and Artificial Intelligence and software engineering, ICBASE 2023

作者： Zhu, Hao Hua, Baojian Suzhou Institute for Advanced Research University of Science and Technology of China School of Software Engineering Suzhou China

ISBN: (纸本)9798350329490

Julia is an emerging programming language designed for high-performance and parallel computing. However, its simple-designed foreign function interface, ccall, lacks necessary security checks, making multilingual Julia applications vulnerable to exploitation. This paper introduces SAFEJ, an infrastructure developed to enhance Julia FFI security. SAFEJ includes two key components: 1) privilege separation to protect Julia by isolating the memory of Julia and native code and 2) pointer sanitization to filter and check memory accesses from unsafe native code to provide more flexible protection. We conducted extensive experiments to evaluate the effectiveness and performance of SAFEJ. The results demonstrate that SAFEJ effectively protects Julia from common memory attacks, and its efficiency tests indicate that pointer sanitization is on par with prior studies, while privilege separation achieves a maximum reduction of 85% in runtime performance overhead. © 2023 IEEE.

关键词： Codes (symbols)

来源：评论

学校读者我要写书评

暂无评论

Federated Collaborative Graph Neural Networks for Few-shot Graph Classification

引用

Machine Intelligence Research 2024年第6期21卷 1077-1091页

作者： Yu Xie Yanfeng Liang Chao Wen A.K.Qin Maoguo Gong School of Computer and Information Technology Shanxi UniversityTaiyuan030000China Key Laboratory of Collaborative Intelligence Systems of Ministry of Education Xidian UniversityXi’an710071China Department of Computer Science and Software Engineering Swinburne University of TechnologyMelbourne3000Australia

Graph neural networks(GNNs)have achieved state-of-the-art performance on graph classification tasks,which aim to pre-dict the class labels of entire graphs and have widespread ***,existing GNN based methods for graph classification are data-hungry and ignore the fact that labeling graph examples is extremely expensive due to the intrinsic *** import-antly,real-world graph data are often scattered in different *** by these observations,this article presents federated collaborative graph neural networks for few-shot graph classification,termed *** its owned graph examples,each client first trains two branches to collaboratively characterize each graph from different views and obtains a high-quality local few-shot graph learn-ing model that can generalize to novel categories not seen while *** each branch,initial graph embeddings are extracted by any GNN and the relation information among graph examples is incorporated to produce refined graph representations via relation aggrega-tion layers for few-shot graph classification,which can reduce over-fitting while learning with scarce labeled graph ***,multiple clients owning graph data unitedly train the few-shot graph classification models with better generalization ability and effect-ively tackle the graph data island *** experimental results on few-shot graph classification benchmarks demonstrate the ef-fectiveness and superiority of our proposed framework.

关键词： Graph neural networks federated learning collaborative learning few-shot learning graph classification

来源：评论

学校读者我要写书评

暂无评论

Multi-Task Learning for Alzheimer's Disease Diagnosis and Mini-Mental State Examination Score Prediction

引用

Big Data Mining and Analytics 2024年第3期7卷 828-842页

作者： Jin Liu Xu Tian Hanhe Lin Hong-Dong Li Yi Pan Hunan Provincial Key Lab on Bioinformatics School of Computer Science and EngineeringCentral South UniversityChangsha 410083China Xinjiang Engineering Research Center of Big Data and Intelligent Software School of SoftwareXinjiang UniversityUrumqi 830091China School of Science and Engineering University of DundeeDundeeDD14HNUK Faculty of Computer Science and Control Engineering Shenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhen 518055China

Accurately diagnosing Alzheimer's disease is essential for improving elderly ***,accurate prediction of the mini-mental state examination score also can measure cognition impairment and track the progression of Alzheimer's ***,most of the existing methods perform Alzheimer's disease diagnosis and mini-mental state examination score prediction separately and ignore the relation between these two *** address this challenging problem,we propose a novel multi-task learning method,which uses feature interaction to explore the relationship between Alzheimer's disease diagnosis and minimental state examination score *** our proposed method,features from each task branch are firstly decoupled into candidate and non-candidate parts for ***,we propose feature sharing module to obtain shared features from candidate features and return shared features to task branches,which can promote the learning of each *** validate the effectiveness of our proposed method on multiple *** Alzheimer's disease neuroimaging initiative 1 dataset,the accuracy in diagnosis task and the root mean squared error in prediction task of our proposed method is 87.86%and 2.5,*** results show that our proposed method outperforms most state-of-the-art *** proposed method enables accurate Alzheimer's disease diagnosis and mini-mental state examination score ***,it can be used as a reference for the clinical diagnosis of Alzheimer's disease,and can also help doctors and patients track disease progression in a timely manner.

关键词： multi-task learning Alzheimer's disease diagnosis mini-mental state examination score prediction

来源：评论

学校读者我要写书评

暂无评论

A deep Q-learning model for sequential task offloading in edge AI systems

引用

Intelligent and Converged Networks 2024年第3期5卷 207-221页

作者： Dong Liu Shiheng Gu Xinyu Fan Xu Zheng Department of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengdu 610000China Shenzhen Institute for Advanced Study University of Electronic Science and Technology of ChinaShenzhen 515100China Department of Information and Software Engineering University of Electronic Science and Technology of ChinaChengdu 610000China

Currently,edge Artificial Intelligence(AI)systems have significantly facilitated the functionalities of intelligent devices such as smartphones and smart cars,and supported diverse applications and *** fundamental supports come from continuous data analysis and computation over these *** the resource constraints of terminal devices,multi-layer edge artificial intelligence systems improve the overall computing power of the system by scheduling computing tasks to edge and cloud servers for *** efforts tend to ignore the nature of strong pipelined characteristics of processing tasks in edge AI systems,such as the encryption,decryption and consensus algorithm supporting the implementation of Blockchain ***,this paper proposes a new pipelined task scheduling algorithm(referred to as PTS-RDQN),which utilizes the system representation ability of deep reinforcement learning and integrates multiple dimensional information to achieve global task ***,a co-optimization strategy based on Rainbow Deep Q-Learning(RainbowDQN)is proposed to allocate computation tasks for mobile devices,edge and cloud servers,which is able to comprehensively consider the balance of task turnaround time,link quality,and other factors,thus effectively improving system performance and user *** addition,a task scheduling strategy based on PTS-RDQN is proposed,which is capable of realizing dynamic task allocation according to device *** results based on many simulation experiments show that the proposed method can effectively improve the resource utilization,and provide an effective task scheduling strategy for the edge computing system with cloud-edge-end architecture.

关键词： edge computing task scheduling reinforcement learning Rainbow Deep Q-Learning(RainbowDQN)

来源：评论

学校读者我要写书评

暂无评论

Chaotic Map-Based Authentication and Key Agreement Protocol with Low-Latency for Metasystem

引用

Computers, Materials & Continua 2024年第3期78卷 4471-4488页

作者： Guojun Wang Qi Liu School of Electronics&Information Engineering Nanjing University of Information Science&TechnologyNanjing210044China Yancheng Polytechnic College Yancheng224000China Jiangsu Province Engineering Research Center of Advanced Computing and Intelligent Services School of SoftwareNanjing University of Information Science and TechnologyNanjingChina

With the rapid advancement in exploring perceptual interactions and digital twins,metaverse technology has emerged to transcend the constraints of space-time and reality,facilitating remote AI-based *** this dynamic metasystem environment,frequent information exchanges necessitate robust security measures,with Authentication and Key Agreement(AKA)serving as the primary line of defense to ensure communication ***,traditional AKA protocols fall short in meeting the low-latency requirements essential for synchronous interactions within the *** address this challenge and enable nearly latency-free interactions,a novel low-latency AKA protocol based on chaotic maps is *** protocol not only ensures mutual authentication of entities within the metasystem but also generates secure session *** security of these session keys is rigorously validated through formal proofs,formal verification,and informal *** confronted with the Dolev-Yao(DY)threat model,the session keys are formally demonstrated to be secure under the Real-or-Random(ROR)*** proposed protocol is further validated through simulations conducted using VMware workstation compiled in HLPSL language and C *** simulation results affirm the protocol’s effectiveness in resisting well-known attacks while achieving the desired low latency for optimal metaverse interactions.

关键词： Metasystem authentication and key agreement chaotic map secure communication

来源：评论

学校读者我要写书评

暂无评论

Optimisation of sparse deep autoencoders for dynamic network embedding

引用

CAAI Transactions on Intelligence technology 2024年第6期9卷 1361-1376页

作者： Huimei Tang Yutao Zhang Lijia Ma Qiuzhen Lin Liping Huang Jianqiang Li Maoguo Gong College of Computer Science and Software Engineering Shenzhen UniversityShenzhenChina Institute for Infocomm Research Agency for Science Technology and ResearchSingaporeSingapore Key Laboratory of Collaborative Intelligence Systems Ministry of EducationXidian UniversityXi'anChina

Network embedding(NE)tries to learn the potential properties of complex networks represented in a low-dimensional feature ***,the existing deep learningbased NE methods are time-consuming as they need to train a dense architecture for deep neural networks with extensive unknown weight parameters.A sparse deep autoencoder(called SPDNE)for dynamic NE is proposed,aiming to learn the network structures while preserving the node evolution with a low computational *** tries to use an optimal sparse architecture to replace the fully connected architecture in the deep autoencoder while maintaining the performance of these models in the dynamic ***,an adaptive simulated algorithm to find the optimal sparse architecture for the deep autoencoder is *** performance of SPDNE over three dynamical NE models(*** architecture-based deep autoencoder method,DynGEM,and ElvDNE)is evaluated on three well-known benchmark networks and five real-world *** experimental results demonstrate that SPDNE can reduce about 70%of weight parameters of the architecture for the deep autoencoder during the training process while preserving the performance of these dynamical NE *** results also show that SPDNE achieves the highest accuracy on 72 out of 96 edge prediction and network reconstruction tasks compared with the state-of-the-art dynamical NE algorithms.

关键词： deep autoencoder dynamic networks low-dimensional feature space network embedding sparse structure

来源：评论

学校读者我要写书评

暂无评论

Application of the ARCADIA Method on a Bulk Carrier Vessel Equipped with a Wind-assistance Device

引用

INCOSE International Symposium 2024年第1期34卷 24-36页

作者： Dreier, Mathias Bajzek, Matthias Hick, Hannes Michels, Nico Burchardt, Carsten Aoyama, Kazuhiro Institute of Machine Elements and Methods of Development Graz University of Technology Austria Institute Institute of Machine Elements and Methods of Development Graz University of Technology Austria Head of Digital Enterprise Siemens Industry Software GmbH Science Siemens Industry Software GmbH Department of Systems Innovation School of Engineering The University of Tokyo Japan

The maritime industry is undergoing a major transformation to achieve reduction of greenhouse gas emissions. Many new options, such as alternative propulsion systems and fuels, optimized routes, or auxiliary propulsion systems, including wind-assistance devices, need to be integrated and aligned within a wide network of different stakeholders. New ways are necessary to work with and manage the increasing complexity in the maritime industry. Model-based systems engineering approaches are a promising strategy to gain a better understanding of the as-is situation and to develop advanced solutions. This paper shows the application of the ARCADIA method for the maritime industry, with the target of integrating wind-assistance devices to vessels, using the ARCADIA modeling language and the Capella tool. Copyright © 2024 by Dreier et al. Permission granted to INCOSE to publish and use.

关键词： Marine industry

来源：评论

学校读者我要写书评

暂无评论

Absorption-Reflection-Transmission Power Coefficient Guiding Gradient Distribution of Magnetic MXene in Layered Composites for Electromagnetic Wave Absorption

引用

Nano-Micro Letters 2025年第6期17卷 466-481页

作者： Yang Zhou Wen Zhang Dong Pan Zhaoyang Li Bing Zhou Ming Huang Liwei Mi Chuntai Liu Yuezhan Feng Changyu Shen State Key Laboratory of Structural Analysis Optimization and CAE Software for Industrial EquipmentNational Engineering Research Center for Advanced Polymer Processing TechnologyZhengzhou UniversityZhengzhou 450002People’s Republic of China Yaoshan Laboratory Pingdingshan UniversityPingdingshan 467000People’s Republic of China

The morphological distribution of absorbent in composites is equally important with absorbents for the overall electromagnetic properties,but it is often ***,a comprehensive consideration including electromagnetic component regulation,layered arrangement structure,and gradient concentration distribution was used to optimize impedance matching and enhance electromagnetic *** the microscale,the incorporation of magnetic Ni nanoparticles into MXene nanosheets(Ni@MXene)endows suitable intrinsic permittivity and *** the macroscale,the layered arrangement of Ni@MXene increases the effective interaction area with electromagnetic waves,inducing multiple reflection/scattering *** this basis,according to the analysis of absorption,reflection,and transmission(A-R-T)power coefficients of layered composites,the gradient concentration distribution was constructed to realize the impedance matching at low-concentration surface layer,electromagnetic loss at middle concentration interlayer and microwave reflection at high-concentration bottom ***,the layered gradient composite(LG5-10-15)achieves complete absorption coverage of X-band at thickness of 2.00-2.20 mm with RL_(min) of-68.67 dB at 9.85 GHz in 2.05 mm,which is 199.0%,12.6%,and 50.6%higher than non-layered,layered and layered descending gradient composites,***,this work confirms the importance of layered gradient structure in improving absorption performance and broadens the design of high-performance microwave absorption materials.

关键词： Magnetic MXene Layered and gradient structure Power coefficient Electromagnetic wave absorption

来源：评论

学校读者我要写书评

暂无评论

Multi-layer composite autoencoders for semi-supervised change detection in heterogeneous remote sensing images

引用

Science China(Information Sciences) 2023年第4期66卷 124-125页

作者： Jiao SHI Tiancheng WU Hanwen YU A.K.QIN Gwanggil JEON Yu LEI School of Electronics and Information Northwestern Polytechnical University School of Resources and Environment University of Electronic Science and Technology of China Department of Computer Science and Software Engineering Swinburne University of Technology Department of Embedded Systems Engineering Incheon National University

With the increasing complexity of application scenarios, the fusion of different remote sensing data types has gradually become a trend, which can greatly improve the utilization of massive remote sensing *** the problem of change detection for heterogeneous remote images can be much more complicated than the traditional change detection for homologous remote sensing images,

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Numerical Model for Sarcoplasmic Reticulum Ca2+ Blink in Rabbit Cardiomyocytes 3

The Numerical Model for Sarcoplasmic Reticulum Ca2+ Blink in...

引用

3rd International Conference on Applied Mathematics, Modelling, and Intelligent Computing, CAMMIC 2023

作者： Liang, Yongshen Xu, Menghao Beijing Engineering Research Center for IoT Software and Systems Beijing University of Technology Beijing100124 China

ISBN: (纸本)9781510667600

Ca2+ in cardiac myocyte are mainly stored in the sarcoplasmic reticulum (SR), the disturbance of Ca2+ dynamics in the SR can cause various cardiovascular diseases. However, there is a lack of research on regulatory mechanism of SR Ca2+. In this paper, we developed a spatially-detailed numerical model for Ca2+ blink to analyze Ca2+ spatiotemporal dynamic characteristics in junctional SR (jSR) cisternae of rabbit cardiomyocytes. The geometric model is constructed by 2-dimensional unstructured triangular meshes with a combined method of Delaunay Triangulations (DT) and Advancing Front Technique (AFT). The numerical method for solving the governing equations adopts Basic Function Method based on unstructured triangular meshes. Finally, our model is well reproduced the SR Ca2+ kinetics of Ca2+ blink and simulated results well match the results of a recent biological experiment. © 2023 SPIE.

关键词： Numerical models

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：