检索结果-南通市图书馆

Multi-Scale Location Attention Model for Spatio-Temporal Prediction of Disease Incidence

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Intelligent Automation & Soft Computing 2024年第3期39卷 585-597页

作者： Youshen Jiang tongqing zhou Zhilin Wang Zhiping Cai Qiang Ni College of Computer National University of Defense TechnologyChangsha410073China Technical Service Center for Vocational Education National University of Defense TechnologyChangsha410073China School of Computing and Communications Lancaster UniversityLancasterLA14WAUK

Due to the increasingly severe challenges brought by various epidemic diseases,people urgently need intelligent outbreak trend *** disease onset is very important to assist *** of the exist-ing work fails to make full use of the temporal and spatial characteristics of epidemics,and also relies on multi-variate data for *** this paper,we propose a Multi-Scale Location Attention Graph Neural Networks(MSLAGNN)based on a large number of Centers for Disease Control and Prevention(CDC)patient electronic medical records research sequence source data *** order to understand the geography and timeliness of infec-tious diseases,speciﬁc neural networks are used to extract the geography and timeliness of infectious *** the model framework,the features of different periods are extracted by a multi-scale convolution *** the same time,the propagation effects between regions are simulated by graph convolution and attention *** compare the proposed method with the most advanced statistical methods and deep learning ***,we conduct comparative experiments on data sets with different time lengths to observe the predic-tion performance of the model in the face of different degrees of data *** conduct extensive experi-ments on real-world epidemic-related data *** method has strong prediction performance and can be readily used for epidemic prediction.

关键词： Spatio-temporal prediction infectious diseases graph 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

基于目标生成的IPv6网络地址扫描综述

计算机研究与发展 2024年第9期61卷 2307-2320页

作者：侯冰楠刘宁李雄略周桐庆陈颖文蔡志平卢凯国防科技大学计算机学院长沙410073

随着近年IPv6网络的迅猛发展,针对IPv6的网络测量和安全分析逐步成为热门的研究课题,这其中一项最基础、最关键的工作是通过网络扫描获取大量的IPv6活跃地址.然而IPv6庞大的地址空间和稀疏的活跃主机分布使得传统的暴力扫描工具(如ZMap... 详细信息

随着近年IPv6网络的迅猛发展,针对IPv6的网络测量和安全分析逐步成为热门的研究课题,这其中一项最基础、最关键的工作是通过网络扫描获取大量的IPv6活跃地址.然而IPv6庞大的地址空间和稀疏的活跃主机分布使得传统的暴力扫描工具(如ZMap和MASSCAN等)无法直接使用.例如在万兆带宽条件下,可5 min内扫描IPv4全网的ZMap扫描器若对IPv6进行全网扫描,仍需要花费上亿年的时间.针对大规模IPv6网络扫描所面临的效率低下问题,研究人员提出了一系列针对IPv6网络的扫描方法,提升了当前IPv6网络资产发现、识别和风控的能力.对这些基于目标生成的IPv6网络扫描方法进行了分类、梳理和总结,分析了各扫描方法的优缺点及适用场景.通过实网扫描实验,对比了多种扫描策略的命中率、边际效益和时间花销等性能情况.最后给出了对IPv6网络扫描研究的思考并对未来的研究方向进行了展望.

关键词： IPv6网络网络测量网络扫描目标生成算法别名前缀检测

Ensuring User Privacy and Model Security via Machine Unlearning: A Review

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第11期77卷 2645-2656页

作者： Yonghao Tang Zhiping Cai Qiang Liu tongqing zhou Qiang Ni College of Computer National University of Defense TechnologyChangsha410073China School of Computing and Communications Lancaster UniversityEnglandB23UK

As an emerging discipline,machine learning has been widely used in artificial intelligence,education,meteorology and other *** the training of machine learning models,trainers need to use a large amount of practical data,which inevitably involves user ***,by polluting the training data,a malicious adversary can poison the model,thus compromising model *** data provider hopes that the model trainer can prove to them the confidentiality of the *** will be required to withdraw data when the trust *** the meantime,trainers hope to forget the injected data to regain security when finding crafted poisoned data after the model ***,we focus on forgetting systems,the process of which we call machine unlearning,capable of forgetting specific data entirely and *** this paper,we present the first comprehensive survey of this *** summarize and categorize existing machine unlearning methods based on their characteristics and analyze the relation between machine unlearning and relevant fields(e.g.,inference attacks and data poisoning attacks).Finally,we briefly conclude the existing research directions.

关键词： Machine learning machine unlearning privacy protection trusted data deletion

Leveraging Active Decremental TTL Measuring for Flexible and Efficient NAT Identification

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 2022年第3期70卷 5179-5198页

作者： Tao Yang Chengyu Wang tongqing zhou Zhiping Cai Kui Wu Bingnan Hou National University of Defense Technology Changsha410073China Department of Computer Science University of VictoriaCanada

Malicious attacks can be launched by misusing the network address translation technique as a *** mitigate such threats,network address translation identification is investigated to identify network address translation devices and detect abnormal ***,existingmethods in this field are mainly developed for relatively small-scale networks and work in an offline manner,which cannot adapt to the real-time inference requirements in high-speed network *** this paper,we propose a flexible and efficient network address translation identification scheme based on actively measuring the distance of a round trip to a target with decremental time-tolive *** basic intuition is that the incoming and outgoing traffic froma network address translation device usually experiences the different number of hops,which can be discovered by probing with dedicated time-to-live *** explore a joint effort of parallel transmission,stateless probes,and flexible measuring reuse to accommodate the efficiency of the measuring *** further accelerate statistical countingwith a new sublinear space data structure *** implement a prototype and conduct real-world deployments with 1000 volunteers in 31 Chinese provinces,which is believed to bring insight for ground truth collection in this *** onmulti-sources datasets show that our proposal can achieve as high precision and recall as 95%with a traffic handling throughput of over 106 pps.

关键词： Network address translation NAT security NAT identification active measurement

Time-Domain Analysis of Body Freedom Flutter Based on 6DOF Equation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

工程与科学中的计算机建模(英文) 2024年第1期138卷 489-508页

作者： Zhehan Ji tongqing Guo Di zhou Zhiliang Lu Binbin Lyu Key Laboratory of Unsteady Aerodynamics and Flow Control Ministry of Industry and Information TechnologyNanjing University of Aeronautics and AstronauticsNanjing210016China High Speed Aerodynamics Institute China Aerodynamics Research and Development CenterMianyang621000China

The reduced weight and improved efficiency of modern aeronautical structures result in a decreasing separation of frequency ranges of rigid and elastic ***,a high-aspect-ratio flexible flying wing is prone to body freedomflutter(BFF),which is a result of coupling of the rigid body short-periodmodewith 1st wing *** prediction of the BFF characteristics is helpful to reflect the attitude changes of the vehicle intuitively and design the active flutter suppression control *** of using the rigid body mode,this work simulates the rigid bodymotion of the model by using the six-degree-of-freedom(6DOF)equation.A dynamicmesh generation strategy particularly suitable for BFF simulation of free flying aircraft is *** accurate Computational Fluid Dynamics/Computational Structural Dynamics/six-degree-of-freedom equation(CFD/CSD/6DOF)-based BFF prediction method is ***,the time-domain CFD/CSD method is used to calculate the static equilibrium state of the *** on this state,the CFD/CSD/6DOF equation is solved in time domain to evaluate the structural response of *** combinedwith the variable stiffnessmethod,the critical flutter point of the model is *** method is applied to the BFF calculation of a flyingwing *** calculation results of the BFF characteristics of the model agree well with those fromthe modalmethod andNastran ***,the method is used to analyze the influence factors of *** analysis results show that the flutter speed can be improved by either releasing plunge constraint or moving the center ofmass forward or increasing the pitch inertia.

关键词： Body freedom flutter time-domain CFD/CSD/6DOF method dynamic mesh generation strategy aeroelasticity

A Survey on Security Threats and Solutions of Bitcoin

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 Cyber Security 2021年第1期3卷 29-44页

作者： Le Lai tongqing zhou Zhiping Cai Zhiyao Liang Hao Bai National University of Defense Technology Changsha410073China Macao University of Science and Technology 999078Macao

Bitcoin is known as the first decentralized digital currency around the *** uses blockchain technology to store transaction data in a distributed public ledger,is a distributed ledger that removes third-party trust *** its invention,bitcoin has achieved great success,has a market value of about$200 ***,while bitcoin has brought a wide and far-reaching impact in the financial field,it has also exposed some security problems,such as selfish mining attacks,Sybil attack,eclipse attacks,routing attacks,EREBUS attacks,and so *** paper gives a comprehensive overview of various attack scenarios that the bitcoin network may be subjected to,and the methods used to implement the attacks,and reviews the solutions and countermeasures proposed against these ***,we summarized other security challenges and proposed further optimizations for the security of the bitcoin network.

关键词： Bitcoin blockchain security attack P2P network

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

面向可穿戴设备的数据安全隐私保护技术综述

计算机研究与发展 2018年第1期55卷 14-29页

作者：刘强李桐于洋蔡志平周桐庆国防科技大学计算机学院长沙410073

基于可穿戴设备的移动计算被视为支撑泛在感知型应用的重要技术,它使用大范围部署的传感器持续不断地感知环境信息,利用短距通信和数据挖掘/机器学习技术传递和处理感知数据.现有的可穿戴设备相关工作主要关注新型移动应用、信息采集、... 详细信息

基于可穿戴设备的移动计算被视为支撑泛在感知型应用的重要技术,它使用大范围部署的传感器持续不断地感知环境信息,利用短距通信和数据挖掘/机器学习技术传递和处理感知数据.现有的可穿戴设备相关工作主要关注新型移动应用、信息采集、产品形态和人性化用户接口等方面的设计与实现.然而,面向可穿戴设备的数据安全隐私保护技术研究尚处于起步阶段.从数据分析者的视角来看,研究者分析可穿戴设备的数据源特点与隐私安全隐患,重点研究基于多源感知数据的个体活动识别方法和数据挖掘机制;从隐私安全保护者的视角来看,面向可穿戴设备的隐私保护技术亟需解决云辅助的隐私保护机制、隐私感知的个人信息发布和基于策略的访问控制等方面的问题.以可穿戴健康跟踪设备Fitbit为对象展开了可穿戴设备安全与隐私实例分析.最后,总结了面向可穿戴设备的隐私保护的8条技术途径,并展望了需要进一步研究的热点问题.

关键词：移动计算可穿戴设备数据安全与隐私安全威胁隐私保护

在线全文

学校读者我要写书评

暂无评论

编码计算研究综述

计算机研究与发展 2021年第10期58卷 2187-2212页

作者：郑腾飞周桐庆蔡志平吴虹佳国防科技大学计算机学院长沙410073

编码计算将编码理论融于分布式计算中,利用灵活多样的编码方式降低数据洗牌造成的高通信负载,缓解掉队节点导致的计算延迟,有效提升分布式计算系统的整体性能,并通过纠错机制和数据掩藏等技术为分布式计算系统提供安全保障.鉴于其在通... 详细信息

编码计算将编码理论融于分布式计算中,利用灵活多样的编码方式降低数据洗牌造成的高通信负载,缓解掉队节点导致的计算延迟,有效提升分布式计算系统的整体性能,并通过纠错机制和数据掩藏等技术为分布式计算系统提供安全保障.鉴于其在通信、存储和计算复杂度等方面的优势,受到学术界的广泛关注,成为分布式计算领域的热门方向.对此,首先介绍编码计算的研究背景,明确编码计算的内涵与定义;随后对现有编码计算方案进行评述,从核心挑战入手,分别对面向通信瓶颈,计算延迟和安全隐私的编码计算方案展开介绍、总结和对比分析;最后指出未来可能的研究方向和技术挑战,为相关领域的研究提供有价值的参考.

关键词：编码计算分布式计算分布式机器学习网络编码性能优化系统安全数据隐私

黄芪注射液对慢性阻塞性肺疾病加重期患者细胞因子及肺功能的影响

在线全文

学校读者我要写书评

暂无评论

长春中医药大学学报 2016年第2期32卷 337-338页

作者：周永清张家口市第五医院预防保健科河北张家口075000

目的观察黄芪注射液对慢性阻塞性肺疾病加重期(AECOPD)患者细胞因子及肺功能的影响。方法选择我院收治的60例AECOPD患者为研究对象,随机均分为观察组和对照组。2组均给予相应氧疗、抗感染、解痉、化痰、平喘、营养支持等治疗,结合临床... 详细信息

目的观察黄芪注射液对慢性阻塞性肺疾病加重期(AECOPD)患者细胞因子及肺功能的影响。方法选择我院收治的60例AECOPD患者为研究对象,随机均分为观察组和对照组。2组均给予相应氧疗、抗感染、解痉、化痰、平喘、营养支持等治疗,结合临床护理路径进行护理,观察组在上述治疗基础上加用黄芪注射液50 m L+5%葡萄糖注射液250 m L静脉滴注,1次/d,2组疗程均为14 d。观察治疗前后血清白细胞介素-2(IL-2)、白细胞介素-8(IL-8)及肿瘤坏死因子-α(TNF-α)变化及肺功能第1秒用力呼气容积(FEV1)、FEV1%预测值、第1秒用力呼气容积和用力肺活量比值(FEV1/FVC)及用力肺活量(FVC)改善情况。结果 2组IL-2升高,IL-8、TNF-α降低,但观察组优于对照组(P<0.05);2组FEV1、FEV1/FVC、FEV1%升高,FVC降低,观察组优于对照组(P<0.05)。结论在常规治疗基础上联合黄芪注射液治疗AECOPD,能显著改善患者临床症状,改善细胞因子水平,结合临床护理路径进行护理可明显改善肺功能,提高疗效。

关键词：黄芪注射液慢性阻塞性肺疾病细胞因子肺功能