Constructive approximation to real function by wavelet neural networks

We present a type of single-hidden layer feed-forward wavelet neural networks. First, we give a new and quantitative proof of the fact that a single-hidden layer wavelet neural network with n + 1 hidden neurons can interpolate n + 1 distinct samples with zero error. Then, without training, we constructed a wavelet neural network X _a (x, A), which can approximately interpolate, with arbitrary precision, any set of distinct data in one or several dimensions. The given wavelet neural network can uniformly approximate any continuous function of one variable.     

Femtosecond laser-induced silicon surface morphology in water confinement

This article investigates the use of femtosecond laser induced surface morphology on silicon wafer surface in water confinement. Unlike irradiation of silicon surfaces in the air, there are no laser induced periodic structures, but irregular roughness is formed when the silicon wafer is ablated under water. The unique discovery of a smoothly processed silicon surface in water confinement under certain laser parameter combinations may help improve laser direct micromachining surface quality in industrial applications.     

Imbalanced text classification: A term weighting approach

The natural distribution of textual data used in text classification is often imbalanced. Categories with fewer examples are under-represented and their classifiers often perform far below satisfactory. We tackle this problem using a simple probability based term weighting scheme to better distinguish documents in minor categories. This new scheme directly utilizes two critical information ratios, i.e. relevance indicators. Such relevance indicators are nicely supported by probability estimates which embody the category membership. Our experimental study using both Support Vector Machines and Naïve Bayes classifiers and extensive comparison with other classic weighting schemes over two benchmarking data sets, including Reuters-21578, shows significant improvement for minor categories, while the performance for major categories are not jeopardized. Our approach has suggested a simple and effective solution to boost the performance of text classification over skewed data sets.     

工作流资源分配中约束规则的建模研究

传统工作流系统在对任务节点进行资源分配时,只进行了组织、角色、人员的分配,而较少对不同任务节点上执行人间的潜在关系进行建模.根据企业的实际应用需求,将这种潜在的约束关系提取出来进行建模,并以规则的形式进行定义.最后采用强有力的推理工具--规则引擎--来完成对定义的规则冲突检测以及规则的实现.     

面向攻击图构建的网络连通性分析

针对目前网络攻击图构建系统的需求,设计网络连通性分析算法。通过对网络拓扑及防火墙规则进行离线分析,可以判断网络中由若干台过滤设备分隔的任意2台主机间的连通性。引入关键实体集的概念,结合经典的Apriori算法提出一种快速有效的获取关键实体集的方法。分析对比表明,关键实体集可以在连通性分析过程中为网络中各节点的重要性评估提供有力依据。     

动量抖动符号误差恒模盲多用户检测算法

针对直扩码分多址通信系统中存在的多址干扰抑制问题,采用加入动量项加快算法收敛的方法,提出一种基于动量抖动符号误差的恒模盲多用户检测算法,在理论上证明该算法的收敛性。通过计算机仿真对该算法与其他算法进行比较,结果证明该算法有较好的收敛性、跟踪性和鲁棒性。     

离散萤火虫优化算法求解概率旅行商问题

对随机组合优化问题中的概率旅行商问题(PTSP)的理论和方法进行了研究分析,采用现代进化算法中有代表性发展优势的萤火虫优化算法(FA),提出一种离散萤火虫优化算法(DFA)以求解.其中引入了新的学习机制使其相比原始的萤火虫优化算法,更容易搜索到全局最优解,有更好的收敛性能.实验中用TSPLIB中的经典实例进行测试来验证其可行性.考察了萤火虫数量和进化迭代次数对求解结果性能的影响,并将DFA与GA、PSO和ACO等其他著名的进化计算算法进行性能比较.实验结果证实了DFA无论对固定访问概率,还是访问概率为区间内随机数等不同情况,都具有良好的有效性和高效性,因此对求解随机组合优化系列问题的有效解决具有一定参考和借鉴价值.     

基于边界域和知识粒度的粗糙集不确定性度量

为了克服现有作积形式不确定性度量方法的缺陷, 基于边界域提出一种用改进粗糙度和知识粒度求和形式的粗糙不确定性度量公式. 与现有方法相比, 它同时考虑了由边界域和知识粗糙性产生的不确定性, 从理论上证明了集成后的不确定性度量值确实比单个影响因素产生的不确定性度量值大, 是一种更加合理的不确定性度量方法. 将该方法推广到基于严凸函数知识粒度情形, 得到一类度量粗糙集不确定性度量方法, 并研究了随划分变细时, 粗糙 度、改进粗糙度与所提出方法之间的关系. 最后设计了一组算例对它们进行比较, 比较结果表明, 所提出的方法对划分变细更加敏感.

     

Robust periodically time‐varying horizon finite memory fault detection filter design for polytopic uncertain discrete‐time systems

In this paper, a robust periodically time‐varying horizon finite memory fault detection filter (PTVHFM‐FDF) is proposed to generate residual signal for the purpose of system monitoring. The major advantage of PTVHFM‐FDF is that finite historical data can be sufficiently utilized to enhance the robustness of fault detection against model uncertainty and external disturbance. The analysis, design, and application of PTVHFM‐FDF consist of several steps. Firstly, a periodic time‐varying residual error system is constructed on the basis of augmented method and time domain partition method. Secondly, in facilitating robust stability and performance analysis, the time‐varying residual error system is further transformed into a polyhedral time‐invariant system on the basis of time lifting technique. Thirdly, less conservative PTVHFM‐FDF analysis and design conditions are then obtained on the basis of Finsler relaxation lemma and slack variable structure definition. Fourthly, choices of memory window horizon parameters are properly suggested on the basis of a compromise between FDF robustness and its structural complexity. Finally, an integrated design and application algorithm of PTVHFM‐FDF is summarized. Effectiveness of PTVHFM‐FDF is verified through three examples. Copyright © 2017 John Wiley & Sons, Ltd.