一种新的模糊时间序列模型的预测方法

针对目前在模糊时间序列模型中论域划分及数据模糊化方法存在的问题,首先提出了基于模糊聚类算法(FCM)的具有可调参数的模糊时间序列论域的非等分划分方法;然后,在数据模糊化时通过距离客观地定义了模糊集,并利用最小标准误差(RMSE)确定最优的预测结果和聚类数;最后,通过 Alabama 大学注册人数的预测表明了所提出算法的有效性.     

基于划分模糊度的聚类有效性函数

模糊C-均值(FCM)聚类算法是目前最流行的数据集模糊划分方法之一.但是,有关聚类类别数的合理选择和确定,即聚类有效性分析,对FCM算法而言仍是一个开放性问题.为此,本文结合数据集的几何结构信息和FCM算法的模糊划分信息,重新定义了划分矩阵,进而利用划分模糊度提出了一种新的模糊聚类有效性函数.实验结果表明该方法是有效的且具有良好的鲁棒性.     

基于FCM的时间序列论域划分方法

随着社会的发展,人们对于数据预测的需求日益增加,模糊时间序列因其能够处理时间序列中含糊不清的数据而备受关注。从提高模型的预测精度角度来看,论域划分作为时间序列数据预测的第一步,作用至关重要。本文提出一种基于FCM的二次论域划分方法。该方法首先根据FCM聚类算法得到的聚类中心对论域进行一次划分,然后根据样本点空间分布的疏密程度不同对论域进行二次细化,实现不等分论域,最后通过对经典样本的预测证明方法的可行性。     

基于论域空间模糊划分的粗集神经网络

针对粗集神经网络构建过程中的论域空间划分问题,提出一种基于模糊聚类的论域划分方法。将带交叉变异算子的粒子群优化算法(PSO)与模糊C-均值聚类算法(FCM)相结合,给出一种新的模糊聚类算法CMPSO-FCM,该算法具有良好的搜索能力和聚类效果。提出一种基于信息熵的模糊粗糙集决策规则获取方法,并用获取的规则指导粗集神经网络的构建。实验结果表明,该方法构造的神经网络具有更精简的结构、较好的分类精度和泛化能力。     

一种新的直觉模糊时间序列预测方法

针对现有直觉模糊时间序列预测模型论域区间划分和序列数据直觉模糊化预处理方法存在的问题,提出了一种新的直觉模糊时间序列预测算法,通过引入滑动窗口参数准确反映不确定数据集的分布特性,利用可调参的直觉模糊C均值聚类算法优化论域区间划分标准,基于直觉模糊范数定义语言变量直觉模糊集,有效地提高了复杂环境下时序系统的预测精度。最后,通过典型实例验证了该方法的有效性和优越性。     

基于主成分分析的模糊时间序列模型的平稳化算法

在模糊时间序列模型建立的过程中,对数据的预处理和模糊规则的优化往往是影响模型预测精确度的关键因素.针对上述问题,提出基于主成分分析(PCA)的平稳化算法.首先,对数据进行平稳化检验,并将非平稳的数据进行预处理使其平稳;其次,对论域进行划分并根据模糊关系构建广义的协方差矩阵,由此计算广义协方差矩阵的特征值和特征向量;再次,根据特征值的累计贡献率优化模糊规则,利用优化后模型进行预测;最后,通过实际算例验证新算法的可行性.     

增强型区间二型FCM算法

不确定性存在于图像处理、模式识别等众多领域的实际应用中, 模糊?? 均值聚类(FCM) 算法虽广泛应用于这些领域, 但其处理不确定性的能力较差. 引入区间二型模糊理论能有效提升算法处理不确定性的能力, 但相应地造成算法复杂度增加, 制约了区间二型FCM算法的推广应用. 鉴于此, 提出增强型区间二型FCM算法, 通过优化初始聚类中心和降型运算, 极大地减少了区间二型FCM算法的运算量, 并提升算法的收敛速度. 通过对随机和实际数据的实验比较验证了改进算法的有效性.

     

FCM聚类算法中模糊加权指数m的优化

研究模糊加权指数m对FCM(Fuzzy c-means)算法的聚类性能的影响,从划分熵入手提出了变权划分熵的概念,并基于模糊决策理论提出了一种最优加权指数m*的选取方法.该方法利用小的目标函数值和小的变权划分熵对应好的数据分类结果这一特性,将m的确定转化为一个带约束的非线性规划问题,从而确定最佳取值m*.实验结果表明该方法是非常有效和灵敏的.     

联机局部自适应模糊C均值聚类算法

基于模糊C均值(FCM)和局部自适应聚类(LAC)提出一种针对高维数据的联机局部自适应模糊C均值聚类算法(OLAFCM).OLAFCM通过为各类属性分别赋以相应的局部权重,使各类属性分布在不同属性组合的张量子空间内,从而有效降低采用全局降维方法造成的信息损失,同时适合聚类数据流.最后,在人工模拟和真实数据集上验证OLAFCM比之现有基于全局降维的划分联机聚类算法具有更好的性能.     

空战多目标模糊聚类算法研究

针对传统多机多目标攻击不易解算攻击任务分配,且计算量大的问题,提出基于划分的多目标模糊聚类算法,该算法根据目标属性的相似性进行多目标分类,可以有效地降低多目标任务分配解算维数,减少运算量,提高解算速度。采用FCM算法以及改进FCM算法度量方式构成的其他各个不同算法,建立空战多目标模糊聚类数学模型,对两组不同数据进行仿真分析,得到不同情况下的各算法的优劣性及适用性。     

基于幂均算子的区间型多属性决策方法

针对决策矩阵元素为区间数的不确定多属性决策问题,提出一种新的决策方法．定义了区间数幂均算子和区间数的相似度,利用一致度矩阵获得每个属性与其他属性的相对一致度．通过区间数幂均算子集成得到方案的综合属性值,进而给出了方案的排序结果．该方法不需要求解属性的权重．应用实例表明了所提出方法的有效性和实用性．     

New results on H∞ filtering for fuzzy systems with interval time-varying delays

This paper investigates the problem of H_∞ filtering for continuous Takagi-Sugeno (T-S) fuzzy systems with an interval time-varying delay in the state. Based on the delay partitioning idea, a new approach is proposed for solving this problem, which can achieve much less conservative feasibility conditions. The attention is focused on the design of an H_∞ filter via the parallel distributed compensation scheme such that the filter error system is asymptotically stable and the H_∞ attenuation level from disturbance to estimation error is below a prescribed scalar. The constructed Lyapunov-Krasovskii functional, by applying the delay partitioning method, can potentially guarantee the obtained delay-dependent conditions to be less conservative than those in the literature. The obtained results are formulated in the form of linear matrix inequalities (LMIs), which can be readily solved via standard numerical software. Finally, an example is illustrated to show the reduction in conservatism of the proposed filter design method.     

Comparing discretization and selection methods for the logical-combinatorial classification of continuous parameters

Preprocessing methods for handling problems with features containing continuous attributes are discussed for learning a classification algorithm based on the JSM method. Discretization methods for continuous parameters that do not make use of class information on feature distribution are compared to entropy-based methods employing class labels in interval partitioning. An entropy-information-based method for selecting attributes is also discussed.     

Analysis of approaches to feature space partitioning for nonlinear dimensionality reduction

One of the most effective ways to reduce the computational complexity of nonlinear dimensionality reduction is hierarchical partitioning of the space with the subsequent approximation of calculations. In this paper, the efficiency of two approaches to space partitioning, the partitioning of input and output spaces, is analyzed. In addition, a method for nonlinear dimensionality reduction is proposed. It is based on construction of a partitioning tree of the input multidimensional space and an iterative procedure of the gradient descent with the approximation carried out on the nodes of the constructed space partitioning tree. In the method proposed, the relative position of the corrected objects and partitioning tree nodes in both input and output spaces is taken into account in the approximation. The method developed was analyzed based on publicly available datasets.     

Some connectivity based cluster validity indices

Identification of the correct number of clusters and the appropriate partitioning technique are some important considerations in clustering where several cluster validity indices, primarily utilizing the Euclidean distance, have been used in the literature. In this paper a new measure of connectivity is incorporated in the definitions of seven cluster validity indices namely, DB-index, Dunn-index, Generalized Dunn-index, PS-index, I-index, XB-index and SV-index, thereby yielding seven new cluster validity indices which are able to automatically detect clusters of any shape, size or convexity as long as they are well-separated. Here connectivity is measured using a novel approach following the concept of relative neighborhood graph. It is empirically established that incorporation of the property of connectivity significantly improves the capabilities of these indices in identifying the appropriate number of clusters. The well-known clustering techniques, single linkage clustering technique and K-means clustering technique are used as the underlying partitioning algorithms. Results on eight artificially generated and three real-life data sets show that connectivity based Dunn-index performs the best as compared to all the other six indices. Comparisons are made with the original versions of these seven cluster validity indices.     

基于遗传算法的气象观测数据区间值属性约简算法

针对气象观测数据采集目的性弱、数据冗余度较高以及观测数据区间化中单值较多、等价类划分精度低的问题,提出一种基于遗传算法的气象观测数据区间值属性约简算法（MOIvGA）。首先,通过改进区间值相似度,使其能够同时适用于单值等价关系判断和区间值相似度分析;其次,通过改进自适应遗传算法,提高其收敛性;最后,通过仿真实验证明,相对于运行自适应遗传属性约简（AGAv）算法求解最优值,所提算法迭代代数减少了22代;在区间长度为1 h降水分类中,基于依赖度的区间值决策表λ-约简（MOIvGA）平均分类准确率比RIvD算法提高了6.3%,对无雨的预测准确率提高了7.13%;同时约简后的属性子集显著提高了分类准确率。由此可见,MOIvGA在区间值气象观测数据分析中能够提高收敛速度以及分类准确率。     

A data clustering algorithm for stratified data partitioning in artificial neural network

The statistical properties of training, validation and test data play an important role in assuring optimal performance in artificial neural networks (ANNs). Researchers have proposed optimized data partitioning (ODP) and stratified data partitioning (SDP) methods to partition of input data into training, validation and test datasets. ODP methods based on genetic algorithm (GA) are computationally expensive as the random search space can be in the power of twenty or more for an average sized dataset. For SDP methods, clustering algorithms such as self organizing map (SOM) and fuzzy clustering (FC) are used to form strata. It is assumed that data points in any individual stratum are in close statistical agreement. Reported clustering algorithms are designed to form natural clusters. In the case of large multivariate datasets, some of these natural clusters can be big enough such that the furthest data vectors are statistically far away from the mean. Further, these algorithms are computationally expensive as well. We propose a custom design clustering algorithm (CDCA) to overcome these shortcomings. Comparisons are made using three benchmark case studies, one each from classification, function approximation and prediction domains. The proposed CDCA data partitioning method is evaluated in comparison with SOM, FC and GA based data partitioning methods. It is found that the CDCA data partitioning method not only perform well but also reduces the average CPU time.     

Optimal partitioning method for stability analysis of continuous/discrete delay systems

This paper is concerned with the problem of stability analysis for continuous‐time/discrete‐time systems with interval time‐varying delay. Based on the idea of partitioning the delay interval into l nonuniform subintervals, new Lyapunov functionals are established. By utilizing the reciprocally convex approach to deal with the delay information in each subinterval, sufficient stability conditions are proposed in terms of linear matrix inequalities. Based on these criteria, the optimal partitioning method is given on the basis of the genetic algorithm. Finally, the reduced conservatism of the results in this paper is illustrated by numerical examples. Copyright © 2013 John Wiley & Sons, Ltd.     

Interval‐valued Pythagorean fuzzy GRA method for multiple‐attribute decision making with incomplete weight information

In this paper, the concept of multiple‐attribute group decision‐making (MAGDM) problems with interval‐valued Pythagorean fuzzy information is developed, in which the attribute values are interval‐valued Pythagorean fuzzy numbers and the information about the attribute weight is incomplete. Since the concept of interval‐valued Pythagorean fuzzy sets is the generalization of interval‐valued intuitionistic fuzzy set. Thus, due the this motivation in this paper, the concept of interval‐valued Pythagorean fuzzy Choquet integral average (IVPFCIA) operator is introduced by generalizing the concept of interval‐valued intuitionistic fuzzy Choquet integral average operator. To illustrate the developed operator, a numerical example is also investigated. Extended the concept of traditional GRA method, a new extension of GRA method based on interval‐valued Pythagorean fuzzy information is introduced. First, utilize IVPFCIA operator to aggregate all the interval‐valued Pythagorean fuzzy decision matrices. Then, an optimization model based on the basic ideal of traditional grey relational analysis (GRA) method is established, to get the weight vector of the attributes. Based on the traditional GRA method, calculation steps for solving interval‐valued Pythagorean fuzzy MAGDM problems with incompletely known weight information are given. The degree of grey relation between every alternative and positive‐ideal solution and negative‐ideal solution is calculated. To determine the ranking order of all alternatives, a relative relational degree is defined by calculating the degree of grey relation to both the positive‐ideal solution and negative ideal solution simultaneously. Finally, to illustrate the developed approach a numerical example is to demonstrate its practicality and effectiveness.     

基于核和灰度的区间灰数多属性决策方法

针对属性值为区间灰数且部分权重信息已知的多属性决策问题, 提出一种基于区间灰数的核和灰度的决策方法. 根据专家评价值的取值范围设置区间灰数的取值论域, 给出了区间灰数的基于核和灰度的简化形式, 建立了普通区间灰数到标准区间灰数的转化方法, 分别基于标准灰数的核和灰度分别求取属性的权重, 进而得到属性的综合权重, 并提出了一种基于标准区间灰数相对核的排序方法对方案进行排序. 最后通过一个算例验证了所提出方法的有效性和可行性.