基于零知识交互式证明和Bayesian信誉网的小世界P2P模型

针对当前P2P(Peer-to-Peer)系统在网络拓扑和信誉评估机制结合方面的不足,设计一种基于角色和信誉访问控制机制的可信小世界P2P(SW-R2P)模型.模型使用零知识交互式证明(ZKIP)算法,在不传输节点身份相关信息的前提下安全地验证对等节点的组信息,并以此作为构建小世界网络拓扑的基础.通过Bayesian信誉网对节点和组的多方面信誉进行评估,从而影响节点的各种操作和组之间连接的建立.仿真实验结果表明,SW-R2P模型在资源查找成功率、网络聚合度以及节点信誉偏差等方面的性能优于Chord和R2P模型.SW-R2P模型结合了ZKIP算法、Bayesian信誉网和小世界拓扑的优势,实现了一种可信、安全和高效的P2P网络架构.     

Bayesian方法在建筑物检测中的应用研究

笔者以Bayesian网络作为工具,研究建筑图像中建筑物的识别问题.首先使用边界检测提取直线特征,生成二维假设.面对平行四边形空间中众多的假设,构建并使用Bayesian网络对已有假设进行选取,最终得到有用的建筑物信息.     

定数截尾数据缺失场合下k/N(G)系统可靠性指标的Bayes估计

在定数截尾缺失数据样本下,研究了不可修k/N(G)系统的可靠性指标评估问题。将经典估计方法和Bayes方法相结合得到了部件的平均寿命、系统可靠度及平均寿命等可靠性指标的Bayes估计。最后利用随机模拟例子说明了本研究方法的正确性和可行性。     

基于自学习规则和改进贝叶斯结合的问题分类*

根据对中文问题的分析可知,问题中的疑问词和中心词等关键词对问题所属类型起着决定性的作用。提出利用自学习方法建立疑问词—类别和疑问词+中心词—类别两种规则,并结合改进贝叶斯模型的问题分类方法。该方法充分利用了关键词对分类的贡献。实验结果表明,该分类方法有很大的改进,准确率达到了84%。     

A macro-meso constitutive law for concrete having imperfect interface and nonlinear matrix

The overall behavior of concrete depends on its meso structures such as aggregate shape, interface status, and mortar matrix property. The two key meso structure characters of concrete, bond status of interface and nonlinear property of matrix, are considered in focus. The variational structure principle is adopted to establish the macro-meso constitutive law of concrete. Specially, a linear reference composite material is selected to make its effective behavior approach the nonlinear overall behavior of concrete. And the overall property of linear reference composite can be estimated by classical estimation method such as self-consistent estimates method and Mori-Tanaka method. This variational structure method involves an optimum problem ultimately. Finally, the macro-meso constitutive law of concrete is established by optimizing the shear modulus of matrix of the linear reference composite. By analyzing the constitutive relation of concrete established, we find that the brittleness of concrete stems from the imperfect interface and the shear dilation property of concrete comes from the micro holes contained in concrete. Supported by the National Natural Science Foundation of China (Grant Nos. 50679022, 90510017, 50539090) and National Basic Research Program of China (Grant No. 2007CB714104)     

动态网络中的高效多故障诊断技术

针对已有算法复杂度较高,不适用于规模较大网络的问题,将被管系统建立成动态贝叶斯模型,并提出一种能处理多故障的近似推理算法. 通过复杂度分析,证明该近似算法时间复杂度为多项式级,远远低于精确算法的时间复杂度下限,可以用于解决大规模动态网络的故障诊断问题. 实验结果证明,新算法在准确度方面虽然略低于精确算法,但执行效率上远远高于精确算法.     

Variational PCA fusion for resolution Pan-sharpening very high imagery

The Pan-sharpening approach based on principle component analysis （PCA） is affected by severe spectral distortion. To address this problem, a new pan-sharpening model based on PCA and variational technique is proposed to construct the substitute image of the first principal component （PC1）. The energy functional consists of three terms. The first term injects PC1 with the geometric structure of the panchromatic （Pan） image. The second term preserves the spectral pattern of the multi-spectral image in the merged result. And the third term guarantees the smoothness of the functional optimization solution. The fusion result is given by the minimum of the energy functional, which is computed with the gradient descend flow. The experiments on QuickBird and IKONOS datasets validate the effectiveness of the proposed model. Compared with the state- of-the-art pan-sharpening approaches, this model exhibits a better trade-off between improving spatial quality and preserving spectral signature of the MS image.     

A joint introduction to Gaussian Processes and Relevance Vector Machines with connections to Kalman filtering and other kernel smoothers

The expressive power of Bayesian kernel-based methods has led them to become an important tool across many different facets of artificial intelligence, and useful to a plethora of modern application domains, providing both power and interpretability via uncertainty analysis. This article introduces and discusses two methods which straddle the areas of probabilistic Bayesian schemes and kernel methods for regression: Gaussian Processes and Relevance Vector Machines. Our focus is on developing a common framework with which to view these methods, via intermediate methods a probabilistic version of the well-known kernel ridge regression, and drawing connections among them, via dual formulations, and discussion of their application in the context of major tasks: regression, smoothing, interpolation, and filtering. Overall, we provide understanding of the mathematical concepts behind these models, and we summarize and discuss in depth different interpretations and highlight the relationship to other methods, such as linear kernel smoothers, Kalman filtering and Fourier approximations. Throughout, we provide numerous figures to promote understanding, and we make numerous recommendations to practitioners. Benefits and drawbacks of the different techniques are highlighted. To our knowledge, this is the most in-depth study of its kind to date focused on these two methods, and will be relevant to theoretical understanding and practitioners throughout the domains of data-science, signal processing, machine learning, and artificial intelligence in general.     

结合Bi-2DPCA与CNN的美式手语识别

针对现有美式手语（ASL）识别算法准确率低和模型训练时间长的问题,提出一种结合双向二维主成分分析（Bi-2DPCA）与卷积神经网络（CNN）并基于贝叶斯优化的识别算法。利用Bi-2DPCA算法对原始图像做数据降维处理,提取行、列方向的特征图,使用卷积神经网络对特征图进行训练分类,同时采用贝叶斯优化算法对模型超参数进行自动调参。在24分类ASL数据集上的实验结果表明,该算法的识别准确率达到99.15%,训练时间相比传统CNN算法减少90.3%。     

基于频繁项挖掘的贝叶斯网络结构学习算法BNSL-FIM

贝叶斯网络能够表示不确定知识并进行推理计算表达,但由于实际样本数据存在噪声和大小限制以及网络空间搜索的复杂性,贝叶斯网络结构学习始终会存在一定的误差。为了提高贝叶斯网络结构学习的准确度,提出了以最大频繁项集和关联规则分析结果为先验知识的贝叶斯网络结构学习算法BNSL-FIM 。首先从数据中挖掘出最大频繁项集并对该项集进行结构学习,之后使用关联规则分析结果对其进行校正,从而确定基于频繁项挖掘和关联规则分析的先验知识。然后提出一种融合先验知识的BDeu评分算法进行贝叶斯网络结构学习。最后在6个公开标准的数据集上开展了实验,并对比引入先验/不引入先验的结构与原始网络结构的汉明距离,结果表明所提算法与未引入先验的BDeu评分算法相比显著提高了贝叶斯网络结构学习的准确度。