On a simple method for testing independencies in Bayesian networks

Testing independencies is a fundamental task in reasoning with Bayesian networks (BNs). In practice, d‐separation is often used for this task, since it has linear‐time complexity. However, many have had difficulties understanding d‐separation in BNs. An equivalent method that is easier to understand, called m‐separation, transforms the problem from directed separation in BNs into classical separation in undirected graphs. Two main steps of this transformation are pruning the BN and adding undirected edges. In this paper, we propose u‐separation as an even simpler method for testing independencies in a BN. Our approach also converts the problem into classical separation in an undirected graph. However, our method is based upon the novel concepts of inaugural variables and rationalization. Thereby, the primary advantage of u‐separation over m‐separation is that m‐separation can prune unnecessarily and add superfluous edges. Our experiment results show that u‐separation performs 73% fewer modifications on average than m‐separation.     

Credal网络推理的一种不完全枚举法

Credal网络是研究不确定环境下知识表示和因果推理的一种图模型,其条件概率值可以用不精确的区间或不等式定性地表示,使得表达方式更加灵活有效。Credal网络的推理是计算一定证据下的后验概率最大值和最小值,给出了一种Credal网络推理的新方法,该方法是在桶消元框架下通过枚举计算部分因子函数值,使计算量大大减小,并且可以得到精确的结果。最后用一个实例说明了该方法的可行性。     

基于贝叶斯网络的多传感器目标识别算法研究

基于贝叶斯网络能够组合多种证据进行不确定性表达和推理的特点,提出以贝叶斯网络为基本结构的目标融合识别模型.通过详细分析空中目标识别的推理规则,建立了空中目标识别的贝叶斯网络拓扑结构.首先对各传感器的数据分别进行融合,然后应用贝叶斯网络推理算法对多种传感器融合结果进行融合计算,最后根据假定变量各状态的概率取值来判断目标平台类型.仿真结果证明了该方法直观、形象,计算速度快,降低了实用的复杂度,提高了目标识别的可靠性.     

自适应滤波算法的神经网络实现

为了提高传统自适应滤波器求解权值的速度。本文在Hopfield神经网络的基础上，提出了自适应滤波算法的神经网络硬件实现。从理论上进行了分析，并进行了仿真。     

基于粒子群优化算法的Bayesian网络结构学习

近年来,Bayesian网络已经成为人工智能领域的研究热点.为了更广泛的应用Bayesian网络,本文采用粒子群优化搜索算法,通过对粒子群算法中各个算子的确定,从训练数据样本中学习到Bayesian网络结构,并用测试数据样本测试学习结果与训练数据的匹配程度,试验结果表明,该算法能有效地学习到Bayesian网络结构.     

自适应滤波算法的神经网络实现

为了提高传统自适应滤波器求解权值的速度，本文在Hopfield神经网络的基础上，提出了自适应滤波算法的神经网络硬件实现，从理论上进行了分析，并进行了仿真。     

On the Computational Power of Max-Min Propagation Neural Networks

We investigate the computational power of max-min propagation (MMP) neural networks, composed of neurons with maximum (Max) or minimum (Min) activation functions, applied over the weighted sums of inputs. The main results presented are that a single-layer MMP network can represent exactly any pseudo-Boolean function F:{0,1} ⁿ [0,1], and that two-layer MMP neural networks are universal approximators. In addition, it is shown that several well-known fuzzy min-max (FMM) neural networks, such as Simpson's FMM, are representable by MMP neural networks.     

一种对抗社交网络链接作弊的算法

随着社交网络的普遍应用,故意构建大量链接关系以提高自身影响力的作弊行为将给社交网络造成极大的安全隐患。针对这种作弊现象,本文首先提出社交网络用户的4类特征,并利用关系强度模型,提出一种信任和非信任同时双向传播的反作弊改进算法。实验表明采用信任及非信任双向传播的反社交网络链接作弊算法具有良好的对抗性能。     

基于无线传感器网络的道路管理系统

无线传感器网络具有布线成本低、监测精度高、容错性好、可远程监控等众多优点,在环境监测等领域有着广阔的应用前景。基于当前对无线传感器网络下的道路管理系统问题的迫切需求,研究传感器节点覆盖问题来实现完全监测覆盖并降低网络成本.结合实际应用,基于树形路由算法提出新的节点间路由算法来延长网络寿命.并用OMNET++验证得到了在物理条件下难以实验的实例模型的性能参数。     

On a Self-Organizing Multipath Routing Protocol in Mobile Wireless Networks

In this paper, we present a self-organizing multipath (SOMP) routing protocol aiming at enhancing success rates of delivery of data packets end-to-end, restricting the routing overhead, and being robust to unstable network conditions. In this SOMP protocol, each mobile host sets up multiple beacons at other hosts to indicate routes to reach it. A beacon is an ordered list of mobile hosts along a path going from the host which holds the beacon, to the host which sets up the beacon. Two functionalities are used for routing data packets to their destinations. The first functionality is a beacon-seeking mechanism, which helps data packets to obtain beacons leading to the destinations of the data packets. The second functionality is a source routing mechanism, which is similar to the one used in Dynamic Source Routing (DSR) protocol and is used to forward data packets to their destinations using the beacons obtained. A balanced binary search tree is used in the SOMP protocol as the embedded forwarding structure, which is built on the identifiers of mobile hosts. This search tree serves for both distributing beacon updates and routing data packets to obtain beacons. The actual routes taken by data packets are jointly determined by the embedded forwarding structure and the underlying network connectivity.     

Optimal Content Location in Multicast Based Overlay Networks with Content Updates

The architecture of overlay networks should support high-performance and high-scalability at low costs. This becomes more crucial when communication, storage costs as well as service latencies grow with the exploding amounts of data exchanged and with the size and span of the overlay network. For that end, multicast methodologies can be used to deliver content from regional servers to end users, as well as for the timely and economical synchronization of content among the distributed servers. Another important architectural problem is the efficient allocation of objects to servers to minimize storage, delivery and update costs. In this work, we suggest a multicast based architecture and address the optimal allocation and replication of dynamic objects that are both consumed and updated. Our model network includes consumers which are served using multicast or unicast transmissions and media sources (that may be also consumers) which update the objects using multicast communication. General costs are associated with distribution (download) and update traffic as well as the storage of objects in the servers. Optimal object allocation algorithms for tree networks are presented with complexities of O(N) and O(N ²) in case of multicast and unicast distribution respectively. To our knowledge, the model of multicast distribution combined with multicast updates has not been analytically dealt before, despite its popularity in the industry.     

BP神经网络及其在数据分类中的应用

BP神经网络模型是一种典型的前向型神经网络,具有良好的自学习、自适应、联想记忆、并行处理和非线形转换的能力,是目前应用最为广泛的一种神经网络模型。本文介绍了BP神经网络的实现以及其在数据挖掘分类方面的应用。     

利用贝叶斯网络融合空间上下文的高分辨遥感图像分类

针对高分辨遥感图像,本文提出了一种基于贝叶斯网络的上下文模型,以及基于该模型的面向对象的遥感图像分类方法.首先,利用支持向量机(SVM)实现分割区域的初始分类,获得各个类别的候选区域.然后,利用提出的上下文模型融合候选区域及其周围区域的上下文信息,通过贝叶斯网络推理,将候选区域分类到各类地物类型中.基于贝叶斯网络的上下...     

Modeling and Analysis of Mesh Tree Hybrid Power/Ground Networks with Multiple Voltage Supply in Time Domain

This paper proposes a novel algorithm, which can be used to model and analyze mesh tree hybrid power/ground distribution networks with multiple voltage supply in time domain. Not only this algorithm enhances common method's ability on analysis of power/ground network with irregular topology, but also very high accuracy it keeps. The accuracy and stability of this algorithm is proved using strict math method in this paper. Also, the usage of both precondition technique based on Incomplete Choleskey Decomposition and fast variable elimination technique has improved the algorithm's efficiency a lot. Experimental results show that it can finish the analysis of power/ground network with enormons size within very short time. Also, this algorithm can be applied to analyze the clock network, bus network, and signal network without buffer under high working frequency because of the independence of the topology.     

贝叶斯网络的无损分解

处理复杂问题的途径和方法有很多,分而治之就是其中的一种有效方法。在将复杂问题分解为一些小问题的过程中,保存原始问题中的信息是关键。本文基于贝叶斯网络的联合树概念及其性质,提出了一种分解贝叶斯网络的方法,该方法可以有效地处理复杂的贝叶斯网络,并且能很好地解决分解过程中信息保存的问题。算法分解产生的各个小网络既保存了原始网络的依赖关系,又没有向分解产生的小网络增添新的依赖关系,因此该分解过程是无损的。最后借助典型的Asia网络详细地阐述了无损分解的整个过程,该例子也验证了无损分解方法的有效性。     

基于约束最大信息熵的贝叶斯网络结构学习算法

贝叶斯网络的学习可分为结构学习和参数学习.基于约束最大信息熵的结构学习算法是一种以搜索最高记分函数为原则的方法.本文以KL距离、相互信息以及最大相互信息为基础,通过附加合适的约束函数降低变量维数和网络结构的复杂度,提出了一种附加约束的最大熵记分函数,并结合爬山法设计一种贝叶斯网络结构学习的启发式算法.通过与著名的K2和B&B-MDL算法的实验比较,结果表明该算法在时间和精度上都具有较好的效果.     

基于进化聚类的动态网络社团发现

社团的数目和时间平滑性的平衡因子一直是基于进化聚类的动态网络社团发现算法的最大的问题.提出一种基于标签的多目标优化的动态网络社团发现算法（LDMGA）.借鉴多目标遗传算法思想,将进化聚类思想转换为多目标遗传算法优化问题,保证当前时刻的聚类质量的同时,又能使当前聚类结果与前一个时刻网络结构保持一致.该算法在初始化过程加入标签传播算法,增加初始个体的聚类质量.提出基于标签的变异算法,增强了算法的聚类效果和算法的收敛速度.同时,多目标遗传算法和标签算法的结合使算法可扩展性强,运行时间随着节点或者边数目增加呈线性增长.将该算法与目前优秀算法在仿真数据集和真实数据集上进行对比实验,结果表明,该算法既有良好的聚类效果,又有良好的扩展性.     

基于多标签传播的社交网络用户影响力评估

为了识别出社交网络中的关键人物,需要对用户影响力进行评估。由于影响力是借助信息在网络中的扩散而逐步形成的,因此需首先对影响力传播过程进行建模;然后以该模型为基础,用标签表示影响力的所有者,以隶属度表示用户被影响的程度,利用多标签传播来模拟影响力传播的过程,实现了一种新的用户影响力评估算法MLPIA(Multi-label Propagation User Influence Asessment Algorithm);最后,在真实数据集上测验排名靠前的用户的影响力覆盖范围和紧密中心性,结果证明了该算法的合理性和有效性。     

Convergence Rate Analysis of Gaussian Belief Propagation for Markov Networks

Gaussian belief propagation algorithm (GaBP) is one of the most important distributed algorithms in signal processing and statistical learning involving Markov networks. It is well known that the algorithm correctly computes marginal density functions from a high dimensional joint density function over a Markov network in a finite number of iterations when the underlying Gaussian graph is acyclic. It is also known more recently that the algorithm produces correct marginal means asymptotically for cyclic Gaussian graphs under the condition of walk summability (or generalised diagonal dominance). This paper extends this convergence result further by showing that the convergence is exponential under the generalised diagonal dominance condition, and provides a simple bound for the convergence rate. Our results are derived by combining the known walk summability approach for asymptotic convergence analysis with the control systems approach for stability analysis.      

自动高效的网络安全评估方法

网络安全评估是提高网络安全性的基本步骤之一。目前的评估方法通常需要手工操作,带来较大的评估开销,很难应用到大规模复杂网络,无法快速响应用户请求。提出了一种高效的自动化评估方法来解决这些问题。为了实现评估的自动化,对多个弱点资源(如NVD、Bugtraq等)的脆弱性信息进行分析,将它们关联起来,形成一个包含40000多个已知弱点的大型综合弱点数据库。为了提高评估效率,利用"原子域"的概念,提出了一种新的攻击图生成方法,相比于传统的方法,大大减少了攻击图生成开销。构建贝叶斯评估模型,基于变量消元,提出了一种新的评估方法,简化了模型中的贝叶斯推理。由于能自动化部署贝叶斯攻击图概率信息,新方法能实现评估的自动化,并且可以应用到大规模网络,快速完成评估任务,还可为网络管理员提供量化判断依据,以快速应对大型复杂网络中不断变化的安全态势。