一种简化证据理论模型的研究

文中试图从几个方面来改进简化证据理论模型ＵＲＭ１的性能,针对ＵＲＭ１,文中给出了两个基本支持函数（相当于证据理论的Ｍａｓｓ函数）间的距离函数,进一步讨论了基本支持函数间的组合条件;给出了基于向最高权威看齐策略的组合带权威性因子基本支持函数的方法。提出了一种对证据理论的证据区间进行决策的方法,一方面,它比ＵＲＭ１中的证据区间决策方法更具一般性,另一方面,它更符合人类的直觉,同时,它对多个异质型专家系     

“Algorithms for Degree-Raising of Splines”中的问题及其解决办法

研究表明，Ｃｏｈｅｎ，Ｌｙｃｈｅ和Ｓｃｈｕｍａｋｅｒ于１９８５年在ＡＣＭＴｒａｎｓａｃｔｉｏｎｓｏｎＧｒａｐｈｉｃｓ杂志上所发表的论文“ＡｌｇｏｒｉｔｈｍｓｆｏｒＤｅｇｒｅｅ－ＲａｉｓｉｎｇｏｆＳｐｌｉｎｅｓ”中存在着严重问题．文中给出了解决Ｂ样条曲线升阶的经典理论中的这些问题的三个算法，同时也给出了计算实例．     

D-S证据理论在审计证据融合中的应用研究

古典概率难以解释审计判断的不确定性,而D-S证据理论是进行不确定性推理的有效方法,因此应用D-S证据理论进行审计证据融合的研究。针对审计证据的组合问题,提出了基于三角形模糊隶属度函数的基本概率分配函数计算方法,给出了证据组合结果的判决规则,并通过实例验证了该方法的有效性。     

对一种基于证据理论的不确定性处理模型的重要扩充

本文分析了文[1]中的不确定性处理模型中存在的问题,提出了有序命题概念,并针对有序命题的情况,给出了一种新的组合不确定性值的综合函数。     

隐层神经元饱和化与稳健性研究

本文通过对多层前向网络（ＭＬＦＮＮ）中隐层神经元激活函数的中强迫饱和化,降低了网络输出对输入的敏感性,进而改善了网络瓣稳健性（Ｒｏｂｕｓｔｎｅｓｓ）。文中给出了相关概念和理论分析,同时以函数逼近问题为例进行了相应的计算机仿真,其结果证明了理论分析的正确性。     

证据理论在有序命题类问题中的基本概率分配

针对证据理论在有序命题类问题中的应用构造基本概率分配函数。有序命题类问题作为一种常见的分类问题,是证据理论应用的一个活跃领域,其基本概率分配存在显著的特点,在分析其特征的基础上,采用基于典型样本的方法,利用实测值与典型值之间的距离构造正态分布曲线的密度函数,进而构造基本概率分配函数。将该方法应用于海上溢油事故等级的评定,通过数据模拟分析其存在的不足,并通过弹性拉大实测值与典型值之间的距离、将“不知道”概率赋值等方法进行改进。实验结果表明改进的基于典型样本的方法能够有效地进行基本概率分配,满足应用的特点和需要。     

“Algorithms for Degree—Raising of Splines”中的问题及其…

研究表明，Ｃｏｈｅｎ，Ｌｙｃｈｅ和Ｓｃｈｕｍａｋｅｒ于１９８５年在ＡＣＭＴｒａｎｓｃｃｔｉｏｎｓｏｎＧｒａｐｈｉｃｓ杂志上所发表的论文“ＡｌｇｏｒｔｉｔｈｍｓｆｏｒＤｅｇｒｅｅ－ＲａｓｉｓｉｎｇｏｆＳｐｌｉｎｅｓ”中存在着严重问题，文中给出解决Ｂ样条曲线升阶的经典理论中的这些问题的三个算法，同时也给出了计算实例。     

在VB中如何自动检测CD—ROM光驱

本文给出一种在ＶｉｓｕａｌＢａｓｉｃ多媒体应用软件中实现自动检测ＣＤ－ＲＯＭ光盘驱动器的方法。其特点是通过调用ＷｉｎｄｏｗｓＡＰＩ函数来完成的，简单易行     

基于信任函数理论的修正融合目标识别算法

针对信任函数理论中经典Dempster组合规则难以有效融合高冲突证据并存在焦元基模糊问题,提出了一种基于信任函数理论的修正融合目标识别算法.修正融合算法在对相容命题进行组合时,考虑了焦元基的影响,使基本信任质量合理地向基数较小的焦元命题聚焦,以避免焦元基模糊问题;在对冲突命题进行组合时,对命题进行倾向性分析并对局部冲突采用局部分配的策略,以有效融合高冲突证据.算例与仿真比较分析验证了此修正融合目标识别算法的合理有效性和优越性.     

关于部分多值逻辑函数集中准完备集的若干性质

Sheffer函数的最简判定是多值逻辑函数集完备性判定问题中的一个重要的理论和实际问题.文中根据多值逻辑函数理论中“保关系”的系统思想,使用群论和组合数学的工具,研究了部分多值逻辑函数集中准完备类相应关系的若干性质.给出并证明了非空关系Gm是完全关系以及子群H是Gm的对称群的充要条件,定出了部分k值逻辑中完满对称函数类Fs,m中函数集的个数.以上工作为解决部分多值逻辑中Sheffer函数的判定提供了研究基础.     

A wavelet extreme learning machine

Extreme learning machine (ELM) has been widely used in various fields to overcome the problem of low training speed of the conventional neural network. Kernel extreme learning machine (KELM) introduces the kernel method to ELM model, which is applicable in Stat ML. However, if the number of samples in Stat ML is too small, perhaps the unbalanced samples cannot reflect the statistical characteristics of the input data, so that the learning ability of Stat ML will be influenced. At the same time, the mix kernel functions used in KELM are conventional functions. Therefore, the selection of kernel function can still be optimized. Based on the problems above, we introduce the weighted method to KELM to deal with the unbalanced samples. Wavelet kernel functions have been widely used in support vector machine and obtain a good classification performance. Therefore, to realize a combination of wavelet analysis and KELM, we introduce wavelet kernel functions to KELM model, which has a mix kernel function of wavelet kernel and sigmoid kernel, and introduce the weighted method to KELM model to balance the sample distribution, and then we propose the weighted wavelet–mix kernel extreme learning machine. The experimental results show that this method can effectively improve the classification ability with better generalization. At the same time, the wavelet kernel functions perform very well compared with the conventional kernel functions in KELM model.     

加权Internet访问直径短期及长期预测行为分析

Internet物理特征量短期及长期预测是一个重要课题,为此,首先定义了加权Internet网络,然后形式化定义表征加权Internet的物理参量———加权Internet访问直径,接下来根据海量数据变化特点,提出了基于Logistic模型的、以正余弦函数模拟振荡变化的数学模型,使用浮点型遗传算法分别进行拟合实验,并通过实验结果对上述模型进行了评价和选优·由于加权访问直径演化极为复杂,传统的一维数学模型在长期预测中已不适用·因此,在长期预测方面,首先计算得到加权Internet访问直径的关联维数,证实其演化过程为混沌现象,存在奇异吸引子·最后根据关联维数及奇异吸引子相近空间混沌轨道运动特性,提出了基于四维微分方程组的加权访问直径长期预测的形式模型·     

Gibbs random field model based weight selection for the 2-Dadaptive weighted median filter

A generalized filtering method based on the minimization of the energy of the Gibbs model is described. The well-known linear and median filters are all special cases of this method. It is shown that, with that selection of appropriate energy functions, the method can be successfully used to adapt the weights of the adaptive weighted median filter to preserve different textures within the image white eliminating the noise. The newly developed adaptive weighted median filter is based on a 3×3 square neighborhood structure. The weights of the pixels are adapted according to the clique energies within this neighborhood structure. The assigned energies to 2- or 3-pixel cliques are based on the local statistics within a larger estimation window. It is shown that the proposed filter performance is better compared to some well-known similar filters like the standard, separable, weighted and some adaptive weighted median filters     

Finite elements and convergence for dynamic analysis of beams

Two different methods are considered for improving the accuracy of finite elements for calculation of dynamic response of the Bernoulli-Euler beam. One method involves a generalized-coordinate procedure in which quadratic displacement functions are used to formulate a non-consistent mass matrix. In the second approach, a lumped parameter model is developed by making the dynamic stiffness, or mechanical impedance, accurate at the connection points. The two finite elements developed are compared with the consistent mass model and a center-of-gravity lumped mass model. Of particular interest is the rate of convergence of natural frequencies and dynamic stiffness.     

加权犹豫模糊集的群决策方法

对于犹豫模糊元中的不同隶属度值赋予不同的权重,由此构造出一种应用范围更广、更符合实际需要的犹豫模糊集合 ----- 加权犹豫模糊集合.针对加权犹豫模糊集中的加权犹豫模糊元,定义了加权犹豫模糊集合和加权犹豫模糊元的并、交、余、数乘和幂等运算及其运算法则,并讨论它们的运算性质;同时,给出加权犹豫模糊元的得分函数和离散函数,进而给出一种比较加权犹豫模糊元的排序法则.在此基础上,提出两类集成算子:加权犹豫模糊元的加权算术平均算子和加权犹豫模糊元的加权几何平均算子,并针对专家权重(已知和未知)的两种情形,将加权犹豫模糊集合应用于群决策,给出两种基于加权犹豫模糊集合的群决策方法.最后,通过一个应用实例表明所提出的群决策方法的有效性和实用性.     

加权模型下的相似匹配跟踪方法

针对传统跟踪方法易受相似物遮挡而导致丢失目标问题,提出一种加权模型下的相似匹配跟踪方法。首先,将目标区域分割成局部特征块,并为其分配权重,建立带权局部特征块组成的外观模型;然后,利用目标的颜色、位置特征进行相似性匹配,为了避免复杂背景干扰,在匹配前划分前景区域,从而实现较准确跟踪;最后,提出一种遮挡决策模型更新机制,通过对目标发生严重遮挡进行判定,保证模型的匹配鲁棒性。实验结果表明,利用加权模型以及多特征相似匹配,使得该方法能够得到较高的跟踪准确率,平均误差仅为13.21,跟踪重叠率为0.71。     

基于加权多决策树的入侵检测系统模型研究

传统的决策树分类方法,对于较小的数据集是非常有效的。但是,当这些方法用于入侵检测系统中时,由于巨大的网络流量,因此,存在着检测性能低和数据挖掘效率不高等问题。为了解决这些问题,提出了加权多决策树模型。将这种方法应用于入侵检测系统中,实验结果表明,该方法提高了入侵检测性能和大容量数据的处理能力。     

Integer linear programming-based multi-objective scheduling for scientific workflows in multi-cloud environments

Scientific communities are motivated to schedule the data-intensive scientific workflows in multi-cloud environments, where considerable diverse resources are provided by multiple clouds and resource limitation imposed by individual clouds is overcome. However, this scheduling involves two conflicting objectives: minimizing cost and makespan. In general, dealing with such conflicting criteria is a difficult task. But fortunately recent efficient methods for solving multi-objective optimization problems motivated us to provide a multi-objective model considering minimization of cost and makespan as objectives. For solving this model, we use different scalarization procedures such as weighted-sum, Benson's scalarization and weighted min–max under different scenarios. Moreover, we investigate the stability of obtained solutions and propose a new approach for determining the most stable solution related to weighted-sum and weighted min–max as post-optimality analysis. Results indicate that our proposed weighted-sum approach outperforms the previously developed methods in terms of hypervolume.

     

A Behavioral Analysis of WOWA and SUOWA Operators

Weighted ordered weighted averaging (WOWA) and semiuninorm‐based ordered weighted averaging (SUOWA) operators are two families of aggregation functions that simultaneously generalize weighted means and OWA operators. Both families can be obtained by using the Choquet integral with respect to normalized capacities. Therefore, they are continuous, monotonic, idempotent, compensative, and homogeneous of degree 1 functions. Although both families fulfill good properties, there are situations where their behavior is quite different. The aim of this paper is to analyze both families of functions regarding some simple cases of weighting vectors, the capacities from which they are building, the weights affecting the components of each vector, and the values they return.     

Necessity constraint in two plant optimal production problem with imprecise parameters

The purpose of this paper is to present and solve a real-life problem of two plants producing the same item under fuzzy-stochastic environment. Here, an item alongwith random defective units is produced at two different plants situated in different locations under a single management. The rates of demand, production and defectiveness at these places are different. Demands of the item are primarily met locally from the respective plants but if a stock-out situation occurs in a plant, immediately some stock, from the other plant if available, is rushed to the stock-out plant. The demands are known but production rates are unknown, functions of time are taken as control variables. The available budget for the management house is imprecise. The holding, shortage and transportation costs are assumed to be imprecise and represented by fuzzy numbers which are transformed to corresponding interval numbers. Following interval mathematics and nearest interval approximation, the objective function is changed to respective multi-objective functions and thus the single-objective fuzzy problem is reduced to a crisp multi-objective decision making (MODM) problem. The MODM problem is then again transformed to a single crisp objective function with the help of weighted sum method. Using fuzzy relations, the imprecise budget constraint expressed in the form of necessity constraint is transformed into an equivalent crisp one. Then, total cost consisting of production, holding, shortage and transportation (from one plant to another) costs is expressed as an optimal control problem and solved using weighted sum method, the Kuhn-Tucker conditions, Pontryagin’s Optimal Control principle and generalized reduced gradient (GRG) technique. The model has been illustrated by numerical data. The optimum results are presented in both tabular and graphical forms.