Improving mixture of experts for view-independent face recognition using teacher-directed learning

In this paper we develop a new learning method, called teacher-directed learning (TDL), for mixture of experts (ME) to perform view-independent face recognition. In the basic form of ME the problem space is automatically divided into several subspaces for the experts, and the outputs of experts are combined by a gating network. In our proposed method, the ME is directed to adapt to a particular partitioning corresponding to predetermined views. To do this, we apply a new learning method to ME, called TDL, in a way that according to the pose of the input training sample, only the weights of the corresponding experts are updated. We apply TDL to MEs, composed of MLP experts and a radial basis function gating network, with different representation schemes: global, single-view and overlapping eigenspace. We test them with previously intermediate unseen views of faces. The experimental results support our claim that directing the experts to a predetermined partitioning of the face space improves the performance of the conventional ME for view-independent face recognition. Comparison with some of the most related methods indicates that the proposed model yields excellent recognition rate in view-independent face recognition.     

利用网络编码优化Ad Hoc网安全路由协议SAODV

网络编码可大大提高网络吞吐量、减少延迟。然而,由于编码意义上网络信息流的复杂性,实际应用中仍存在困难。另一方面,Ad Hoc网作为自组织形式的特殊网络,其安全路由协议是研究重点。针对Ad Hoc网安全路由协议中较优秀的SAODV,提出一种基于网络编码的优化方案,较传统编码易于实现、具有较强实用性。     

Improving network security using genetic algorithm approach

With the expansion of Internet and its importance, the types and number of the attacks have also grown making intrusion detection an increasingly important technique. In this work we have realized a misuse detection system based on genetic algorithm (GA) approach. For evolving and testing new rules for intrusion detection the KDD99Cup training and testing dataset were used. To be able to process network data in real time, we have deployed principal component analysis (PCA) to extract the most important features of the data. In that way we were able to keep the high level of detection rates of attacks while speeding up the processing of the data.     

A measurement model for experts knowledge-based systems algorithm using fuzzy analytic network process

This study proposes an experts knowledge-based systems measurement model, the model using fuzzy analytic network process (FANP) to resolve the uncertainty and imprecision of evaluations during pre-negotiation stages, where the comparison judgments of a decision maker are represented as fuzzy triangular numbers. A novel fuzzy prioritization method, which derives crisp priorities (criteria weights and scores of alternatives) from consistent and inconsistent fuzzy comparison matrices, is also proposed. The applicability of the proposed model is demonstrated in a government purchase digital video recorder (DVR) system project study. The stability tests indicate the advantages of the proposal model in determining the value of model. Importantly, the proposed model can provide decision makers a reference material, making it highly applicable for academic and commercial purposes.     

Improving cloud network security using the Tree-Rule firewall

This study proposes a new model of firewall called the ‘Tree-Rule Firewall’, which offers various benefits and is applicable for large networks such as ‘cloud’ networks. The recently available firewalls (i.e., Listed-Rule firewalls) have their limitations in performing the tasks and are inapplicable for working on some networks with huge firewall rule sizes. The Listed-Rule firewall is mathematically tested in this paper to prove that the firewall potentially causes conflict rules and redundant rules and hence leads to problematic network security systems and slow functional speed. To overcome these problems, we show the design and development of Tree-Rule firewall that does not create conflict rules and redundant rules. In a Tree-Rule firewall, the rule positioning is based on a tree structure instead of traditional rule listing. To manage firewall rules, we implement a Tree-Rule firewall on the Linux platform and test it on a regular network and under a cloud environment respectively to show its performance. It is demonstrated that the Tree-Rule firewall offers better network security and functional speed than the Listed-Rule firewall. Compared to the Listed-Rule firewall, rules of the Tree-Rule firewall are easier to be created, especially on a large network such as a cloud network.     

Improving the accuracy of pruned network using knowledge distillation

Pattern Analysis and Applications - The introduction of convolutional neural networks (CNN) in image processing field has attracted researchers to explore the applications of CNN itself. Some...     

Improving method for discrete control system with network structure

This paper is dedicated to designing approximate methods of solving discrete optimal control problems with network structure; the methods involve sufficient optimality conditions derived by V.F. Krotov.     

基于改进自适应PSO算法的WSN覆盖优化方法

在标准粒子群优化（particle swarm optimization, PSO）算法的基础上提出了一种带有动态惯性权重的自适应粒子群算法, 以实现移动WSN对被监测区域的覆盖。新算法引入了粒子群进化度因子和粒子群聚合度因子, 这两个因子的数值主要受粒子群的平均适应值、局部最优值和全局最优值影响。使用这两个因子调整惯性权重会使算法带有一定的自适应性, 这种自适应性使得算法在迭代过程中既不会因步长过小而局部收敛, 也不会因步长过大而跳过待求解问题的最优值。仿真结果表明, 相比标准PSO算法, 改进后的自适应PSO算法使移动WSN的覆盖率提升了5%~8%。     

Robust evaluation method of communication network based on the combination of complex network and big data

Neural Computing and Applications - The essence of big data may be the science of complex network, which should be one of the basic theories of big data, and the direct object of mobile...     

Improving customer retention in financial services using kinship network information

This study investigates the advantage of social network mining in a customer retention context. A company that is able to identify likely churners in an early stage can take appropriate steps to prevent these potential churners from actually churning and subsequently increase profit. Academics and practitioners are constantly trying to optimize their predictive-analytics models by searching for better predictors. The aim of this study is to investigate if, in addition to the conventional sets of variables (socio-demographics, purchase history, etc.), kinship network based variables improve the predictive power of customer retention models. Results show that the predictive power of the churn model can indeed be improved by adding the social network (SNA-) based variables. Including network structure measures (i.e. degree, betweenness centrality and density) increase predictive accuracy, but contextual network based variables turn out to have the highest impact on discriminating churners from non-churners. For the majority of the latter type of network variables, the importance in the model is even higher than the individual level counterpart variable.     

利用脉冲耦合神经网络的纹理图像检索方法

为提高基于内容的图像检索系统(CBIR)中纹理特征提取的有效性,进一步提升CBIR系统的整体性能。提出了一种基于脉冲耦合神经网络的纹理图像检索方法。脉冲耦合神经网络(PCNN)是新一代的人工神经网络,在数据处理上具有很多优势。特征提取时具有平移、旋转、尺度、扭曲等不变性,以及很好的抗噪性,而这一点非常适合于图像检索系统。利用PCNN及简化模型ICM得到对应于不同灰度值的二值图像序列,计算序列中每幅图像的熵序列,其一维的特征矢量作为纹理特征。采用Eu-clidean距离进行相似度计算,建立了一套基于示例查询图像的纹理图像检索系统。实验结果表明,与小波包等特征提取方法相比,该方法不仅对噪声具有较强的鲁棒性,同时能降低特征向量维数,具有尺度、平移和旋转不变性,而且能取得更高的检索率。     

基于分解组合法的三维景观网络共享

各地的数字城市建设积累了大量城镇区域的三维景观数据,但因为采用的标准规范、技术路线不同,之间不能互相共享和应用而成为"信息孤岛"。针对社会、公众三维景观网络在线共享的需求,分析三维景观数据内容、数据组织等标准规范和共享要求,比较二维、三维地理信息数据共享模式和集成机制,研究三维景观在线发布技术,提出基于分解组合法的跨地区三维景观在线共享的基本思路和技术路线,通过将三维信息在服务端分解为地形、影像、模型等组成单元,利用标准的地理信息服务发布,在客户端利用HTML5实现三维信息的组合和表达。通过省、市、县三级的共享实验表明,该方法对现有三维景观成果进行少量的改造就能够有效地实现共享。     

一种应用复杂网络特征的K-means初始化方法

K-means算法是一种基于划分的聚类算法,具有算法简单且收敛速度快的特点。但该算法的性能依赖于聚类中心的初始位置的选择。拓展了复杂网络的重要特征,针对带有属性的数据对象所构成的数据集,定义了多维属性对象的度、聚集度和聚集系数,选取度和聚集系数高的K个点作为K-means聚类的初始中心点。实验数据表明,改进后的K-means算法较传统的算法具有更高的效率和准确度。     

无线传感网使用网络编码的新型数据传输方法

网络编码能提高无线传感器网络数据传输可靠性,针对现有基于网络编码的数据传输策略随机选取编码向量和使用固定路径所带来的缺陷,设计了一个新的编码矩阵构造方法,并提出了一种新型的基于网络编码的可靠数据传输方法。该编码方案能保证任意k个编码向量线性无关,且不用传输编码向量。数据转发使用"区域推进"机制,自动选取最佳转发节点,将数据包可靠地向sin"k推进",并实现了最少冗余传输和网络均衡能耗。分析与仿真表明,新的数据传输策略能消除现有方法的缺陷,提高数据传输可靠性,降低能耗。     

Optimal combination of document binarization techniques using a self-organizing map neural network

This paper proposes an integrated system for the binarization of normal and degraded printed documents for the purpose of visualization and recognition of text characters. In degraded documents, where considerable background noise or variation in contrast and illumination exists, there are many pixels that cannot be easily classified as foreground or background pixels. For this reason, it is necessary to perform document binarization by combining and taking into account the results of a set of binarization techniques, especially for document pixels that have high vagueness. The proposed binarization technique takes advantage of the benefits of a set of selected binarization algorithms by combining their results using a Kohonen self-organizing map neural network. Specifically, in the first stage the best parameter values for each independent binarization technique are estimated. In the second stage and in order to take advantage of the binarization information given by the independent techniques, the neural network is fed by the binarization results obtained by those techniques using their estimated best parameter values. This procedure is adaptive because the estimation of the best parameter values depends on the content of images. The proposed binarization technique is extensively tested with a variety of degraded document images. Several experimental and comparative results, exhibiting the performance of the proposed technique, are presented.     

Improving area positioning in ZigBee sensor networks using neural network algorithm

Microsystem Technologies - This paper proposes an area-based indoor positioning scheme by using the ZigBee sensor networks. In an indoor positioning environment, signal transmission in wireless...     

Color-based object segmentation method using artificial neural network

This paper presents a color-based technique for object segmentation in colored digital images. Principally, we make use of some color spaces to segment pixels as either objects of interest or non-objects using artificial neural networks (ANN). This study clearly shows how a novel method for fusion of the existing color spaces produces better results in practice than individual color spaces. The segmented objects include lips, faces, hands, fingers and tree leaves. Using several databases to represent these problems, the ANN was trained on the color of the pixel and its surrounding 8 neighbors to be an object or non-object; in the test mode the trained set was used to segment the 9 pixels in the test image into object or non-object. The feature vector was used for training and testing results from the fusion of different types of color information that came from different color models of the targeted pixel. Several experiments were conducted on different databases and objects to evaluate the proposed method; significant results were recorded, showing the power of expressiveness of color and some texture information to deal with the object segmentation problem.     

用综合法优化前向神经网络结构

在神经网络研究中,如何确定神经网的结构是一个重要的研究方向.提出了一种通用的确定前向神经网络结构的自适应方法,即先用动态增长法快速训练网络拓扑结构及权值至满足给定的误差为止,然后用遗传算法(GA)对训练好的网络剪枝.实验表明,算法具有较好的通用性和可扩展性,收敛速度较快,对进一步的数据挖掘具有重要的意义.     

Category classification method using a self-organizing neural network

We apply a new category classification method to remote sensing data. This is a supervised and non-parametric method and employs both a selforganizing neural network and a k -nearest neighbour method. One of the features of the category is represented by the neuron weights after training the neural network based on a competitive learning role. From experimental results, we can see that the proposed method obtains superior classification results compared to other methods.     

Neural network controller using autotuning method for nonlinearfunctions

An autotuning method for the optimum sigmoid function of neural networks is proposed. It is based on the steepest descent method. Simulated results using a learning-type direct controller confirm both the practicality and the characteristics of the autotuning method.