基于相似度传播的复杂网络间节点匹配算法

提出了一种基于相似度传播的复杂网络间节点匹配方法.引入节点相似度传播过程,使得初始的相似度信息能够按网络拓扑结构传播到全局,从而能够充分利用有限数目已匹配节点对所提供的相似度信息.该传播过程的稳态分布与一个大矩阵的主特征向量等价,可采用幂方法的迭代形式来高效求解,最后利用图论中的KM(Kuhn-Munkres)算法来抽取最终的匹配节点对.以四种不同结构的网络节点匹配实验为例,对本文算法进行了测试和验证.实验统计结果表明,本文方法显著提高了节点匹配的精度.     

基于主题相似度模型的TS-PageRank算法

PageRank算法是著名搜索引擎Google的核心算法,但存在主题漂移的问题,致使搜索结果中存在过多与查询主题无关的网页.在分析PageRank算法及其有关改进算法的基础上,提出了基于虚拟文档的主题相似度模型和基于主题相似度模型的TS-PageRank算法框架.只要选择不同的相似度计算模型,就可以得到不同的TS-PageRank算法,形成一个网页排序算法簇.理论分析和数值仿真实验表明,该算法在不需要额外文本信息,也不增加算法时空复杂度的情况下,就能极大地减少主题漂移现象,从而提高查询效率和质量.     

基于多层节点相似度的社区发现方法

社区发现是复杂网络研究中的一项重要研究内容,基于节点相似度的凝聚方法是一种典型的社区发现方法。针对现有节点相似度计算方法中存在的不足,提出一种基于多层节点的节点相似度计算方法,该方法既可以有效地计算节点之间的相似度,又可以解决节点相似度相同时的节点合并选择问题。进一步基于这种改进的节点相似度计算方法和团体之间的连接紧密度度量准则构建社区发现模型,并在真实世界的网络上进行社区发现实验。与GN算法、Fast Newman算法和改进的标签传播算法的实验结果相比,该模型可以更加准确地找到各个社区的成员。     

基于节点相似度的网络社团检测算法研究

社团结构是众多复杂网络的统计特性之一,挖掘网络中存在的社团结构日益受到人们的普遍关注。网络中的社团结构检测本质上类似于传统机器学习领域的聚类分析,其关键问题在于如何定义网络中节点间的相似度。首先提出了基于节点相似度的节点分裂算法SUN,相比传统的基于边界数(betweenness)的节点分裂算法GN, SGN在速度和精度上都有明显改善;接着,在利用各种节点相似度计算方法得到节点间的相似度之后,采用几种经典的聚类分析算法对网络进行社团划分,在模拟数据和真实数据上的实验表明:基于网络拓扑结构信息的signal和regular方法优于基于网络节点局部信息的Jaccard方法,而且对于复杂网络社团划分问题,如果选择好的网络节点相似度构造方法,已有的基于相似度矩阵的聚类分析算法都能快速有效地对网络社团进行划分。     

基于包含度的Vague集相似度量

在模糊模式识别中经常要根据最大相似度原理来分辨待测样品属于哪种模式．由于现有的vague集相似度量公式都是基于距离测度的，因此只要vague集间距离测度一样，它们就无法分辨，因此非常有必要寻找其它的相似度量计算方法．首先将模糊集上的包含度概念扩展到Vague集上，指出Vague集相似度量可以由包含度诱导出，然后给出一组新的Vague集相似度量计算公式．数值算例证明它们是有效的，最后将它们与现有方法进行比较，发现它们各有所长．     

基于VIKOR模型的复杂网络节点重要度评估

复杂网络重要节点在遭受敌方蓄意攻击时往往会造成网络的大范围瘫痪,评估出重要节点对网络的可靠性和网络安全具有重要意义。现有的评估重要节点的中心性准则仅针对某一测度,具有局限性,因此,文章提出了一种结合现有中心性准则对复杂网络节点进行重要度排序的方法。该方法结合度中心性、中介中心性、接近中心性和特征向量中心性准则,从多角度多方位评估节点重要性。该方法借助熵权法求得每项准则的权重,避免了人为因素带来的偏差。采用多准则妥协解排序法(VIKOR)对节点的重要度进行排序,在3个典型的复杂网络上利用病毒传播模型(SI)对传播过程进行仿真。结果表明,与单一的度中心性指标、中介中心性指标、接近中心性指标和特征向量中心性指标相比,VIKOR方法能更全面更准确地排序节点的重要性。     

基于复杂网络的大型软件系统度量

随着软件系统规模的不断增大,如何度量面向对象大规模软件系统成为一个亟待解决的问题.近年来迅速发展的复杂网络理论为解决该问题提供了一个新的视角.介绍了大规模软件系统中的复杂网络现象,从元素级、模块级、网络级3个不同的粒度提出基于复杂网络的软件系统的各种度量;实现了大型Java程序复杂网络描述和度量工具JPAC.JPAC可用于分析大型Java系统的结构,并计算基于复杂网络的各度量值.     

基于相似度传播的二分网络链接预测

链接预测是复杂网络分析中的重要研究问题。提出了一个基于链接相似度传播的二部图链路预测算法。该算法将链接相似度得分通过随机游走在网络中进行传播和更新。在该算法中,网络里的每一条边都被分配一个基于相似度的传播概率。不同部分的节点之间的链接相似性得分根据它们的边的传播概率来传播。在不同大小的真实社交网络上的实验结果证明,该算法可以取得比其他算法更精确的预测结果。     

一种基于复杂网络的短文本语义相似度计算

将传统的文本相似度量方法直接移植到短文本时,由于短文本内容简短的特性会导致数据稀疏而造成计算结果出现偏差。该文通过使用复杂网络表征短文本,提出了一种新的短文本相似度量方法。该方法首先对短文本进行预处理,然后对短文本建立复杂网络模型,计算短文本词语的复杂网络特征值,再借助外部工具计算短文本词语之间的语义相似度,然后结合短文本语义相似度定义计算短文本之间的相似度。最后在基准数据集上进行聚类实验,验证本文提出的短文本相似度计算方法在基于F-度量值标准上,优于传统的TF-IDF方法和另一种基于词项语义相似度的计算方法。     

Adversarial network embedding using structural similarity

Network embedding which aims to embed a given network into a low-dimensional vector space has been proved effective in various network analysis and mining tasks such as node classification,link prediction and network visualization.The emerging network embedding methods have shifted of emphasis in utilizing mature deep learning models.The neural-network based network embedding has become a mainstream solution because of its high eficiency and capability of preserv-ing the nonlinear characteristics of the network.In this paper,we propose Adversarial Network Embedding using Structural Similarity(ANESS),a novel,versatile,low-complexity GAN-based network embedding model which utilizes the inherent vertex-to-vertex structural similarity attribute of the network.ANESS learns robustness and ffective vertex embeddings via a adversarial training procedure.Specifically,our method aims to exploit the strengths of generative adversarial networks in generating high-quality samples and utilize the structural similarity identity of vertexes to learn the latent representations of a network.Meanwhile,ANESS can dynamically update the strategy of generating samples during each training iteration.The extensive experiments have been conducted on the several benchmark network datasets,and empirical results demon-strate that ANESS significantly outperforms other state-of-theart network embedding methods.     

复杂电路虚拟维修的建模与仿真技术

分析了电路虚拟维修的特点,总结了电路虚拟维修系统中必不可少的3种模型:仿真模型、交互模型和三维模型,研究了3种模型的特点和建模方法.提出了一种层次化模型结构:功能层、应用层和显示层,并研究了各层之间的信息传递.引入多Agent系统理论建立电路虚拟维修系统中不同类型的智能Agent模型,研究了基于KQML的各Agent间通信的方式.最后根据模型的层次化结构建立了一个基于多Agent系统的电路虚拟维修训练系统.     

Semantic similarity measurement using historical google search patterns

Computing the semantic similarity between terms (or short text expressions) that have the same meaning but which are not lexicographically similar is an important challenge in the information integration field. The problem is that techniques for textual semantic similarity measurement often fail to deal with words not covered by synonym dictionaries. In this paper, we try to solve this problem by determining the semantic similarity for terms using the knowledge inherent in the search history logs from the Google search engine. To do this, we have designed and evaluated four algorithmic methods for measuring the semantic similarity between terms using their associated history search patterns. These algorithmic methods are: a) frequent co-occurrence of terms in search patterns, b) computation of the relationship between search patterns, c) outlier coincidence on search patterns, and d) forecasting comparisons. We have shown experimentally that some of these methods correlate well with respect to human judgment when evaluating general purpose benchmark datasets, and significantly outperform existing methods when evaluating datasets containing terms that do not usually appear in dictionaries.     

基于多层次灰色关联分析的复杂网络节点排序模型

复杂网络节点重要性是研究复杂网络特性的重要方面之一,被广泛应用于数据挖掘、Web 搜索、社会网络分析等众多研究领域。在选取评估节点重要性指标时,考虑到普通聚类系数仅能衡量网络节点聚类的疏密度,不能衡量聚类的规模,提出了修正的聚类系数;同时,选取了Erdos数和介数两个指标来综合衡量网络节点重要性,建立多层次 灰色关联分析模型,确定出各个节点与理想节点的关联度,实现对复杂网络节点的排序。模型不仅考虑到度、路径距离对节点排序的影响,而且也考虑到每个节点聚类程度对节点排序的影响。通过与实际网络和其他方法的排序结果对比,模型能够准确找到复杂网络的核心节点,并且排序结果真实反映了节点依次的重要程度。     

Interfaced circuit using a non-destructive method for moisture measurement

Analysing the moisture in stored products like harvested cereal grains and their products, peas, beans, oil-seeds, copra, cocoa beans, spices etc. is very much important to avoid the fungi growth. Moisture can be present in grain in more than one state, i.e. as bound, adsorbed or absorbed water. A designed, integrated circuit was interfaced with personal computer to measure the capacitance which in turn help to calculate the moisture content of rice. The interfaced circuit was tested by measuring the capacitance of different ceramic capacitor. This technique is fast, reliable, accurate and gives hundred set of readings in few seconds. Moisture contents are measured in percentage. The error correction was done with the help of mat - lab programming.     

基于ANN伪量测建模的配电网状态估计

针对配电网状态估计实时量测数量的不足,提出了一种基于ANN伪量测建模的配电网状态估计算法。该方法采用人工神经网络网络（ANN）,将部分实时量测数据作为神经网络的输入,产生较为精确的负荷伪量测数据。此外,应用高斯混合模型对产生伪量测的误差进行分解拟合,从而获得负荷伪量测的权重。最后,将获得的伪量测及其权重输入到状态估计模块中,实现了配电网的状态估计。通过英国标准配网系统（UKGDS）中16节点模型的仿真结果表明,该算法提高了配电网状态估计的精度,具有一定的现实意义和理论价值。     

Application of artificial neural network models to linear and nonlinear RF circuit modeling

Typical RF and wireless circuits comprise a large number of linear and nonlinear components. The complexity of the RF portion of a wireless system continues to increase in order to support multiple standards, multiple frequency bands, the need for higher bandwidth, and stringent adjacent channel specifications. The time required to carry out a virtual prototyping of such complex circuits and their trade‐off analysis with the baseband circuitry can be unacceptably long, because both the circuit simulation and optimization procedures can be very time consuming. Typically, one divides the task into those of designing the nonlinear elements or subcircuits that can be accurately analyzed by using RF simulators, and uses circuit level analysis for simulating the circuits at module level. In this article, we will review some approaches to modeling both the linear RF elements as well as nonlinear subcircuits (amplifiers, mixers, VCOs), and will emphasize on the application of the artificial neural networks (ANNs). Furthermore, we will demonstrate the use of the ANN to the design of RF circuits and illustrate their application to wireless types of problems of practical interest. © 2001 John Wiley & Sons, Inc. Int J RF and Microwave CAE 11: 231–247, 2001.     

结构-属性平衡图节点相似度测量算法

摘  要：节点相似度是图聚类算法的重要基础,在基于结构-属性图聚类现有方法中,由于传统图模型的限制,需要多次矩阵相乘来调整属性边的权值,算法执行效率低。为解决这一问题,提出了结构-属性平衡图的概念,并采用随机游走模型策略统一度量结构-属性平衡图GB中顶点间的相似度。与现有方法相比,该方法不但能测量直接相连的顶点之间的相似度,还可测量不直接相连而存在不同长度的路径的顶点之间的相似度,且没有增加原相似度矩阵的规模,节省了大量存储空间,提高了算法执行效率。     

Debugging measurement systems using a domain-specific modeling language

Capturing physical data in the context of measurement systems is a demanding process that often requires many repetitions with different settings. To assist in this activity, a domain-specific modeling language (DSML) called Sequencer has been developed to enable the improved definition of measurement procedures. With Sequencer, the level of abstraction has been raised and sophisticated changes in measurement procedures are now enabled. Although there are numerous DSMLs like Sequencer in the existing literature, there are some obstacles working against the more widespread adoption of DSMLs in practice. One challenge is the lack of supporting tools for DSMLs, which would improve the capabilities of end-users of such languages. For instance, support for debugging a model expressed in a DSML is often neglected. The lack of a debugger at the proper abstraction level limits the domain experts in discovering and locating bugs in a model. In this paper, Sequencer is presented together with debugging facilities (called Ladybird) that are integrated in a modeling environment. Ladybird supports different execution modes (e.g., steps, breakpoints, animations, variable views, and stack traces) that can be helpful during the debugging of a model. Ladybird's primary contribution is in showing the value of error detection in complicated industrial environments, such as data acquisition in automotive testing. The paper contributes to a discussion of the implementation details of DSML debugging facilities and how such a debugger can be reused to support domains other than the measurement context of Sequencer.     

Dynamic background modeling using deep learning autoencoder network

Multimedia Tools and Applications - Background modeling is a major prerequisite for a variety of multimedia applications like video surveillance, traffic monitoring, etc. Numerous approaches have...