一种区间型数据的自适应模糊c均值聚类算法

针对区间型数据的聚类问题,提出一种自适应模糊c均值聚类算法。该算法一方面基于区间数的中点和半宽度,通过引入区间宽度的影响因子以控制区间大小对聚类结果的影响;另一方面通过引入一个自适应系数,以减少区间型数据的数据结构对聚类效果的影响。通过仿真数据和Fish真实数据验证了该算法的有效性,并对聚类结果进行比较和分析。     

区间型数据的模糊c均值聚类算法

提取区间型数据的特征值,给出适用于区间型数据模糊聚类的FCM算法族(IFCM)。该算法适用于不同特征样本数据的模糊聚类运算,并可对聚类结果进行优化。聚类效果的仿真比较表明,IFCM聚类的平均失真度比基于欧氏距离的FCM聚类算法低6.81%。由于距离定义的合理性,IFCM可以根据区间型数据的不同特点调整特征值的聚类权重,并推广至多维类型数据的模糊聚类。     

区间型数据的可能性聚类算法

针对区间型数据的模糊c均值聚类(IFCM)算法在实际应用中的不足,将可能性理论引入区间型数据的聚类问题,通过放松样本隶属度的约束条件和修正IFCM算法的目标函数,提出一种区间型数据的可能性聚类算法。通过仿真模拟实验和平均CR指标分析,结果表明:在包含噪声和孤立点等代表性比较差的样本数据的聚类问题中,该算法明显优于IFCM算法,能有效地降低噪声对聚类效果的影响。     

基于属性权重区间监督的模糊C均值聚类算法

在加权模糊聚类算法中,属性权重确定的合理性是一个重要问题.鉴于用区间数描述决策者推理模糊性的优越性,提出属性权重用区间数表示,由区间层次分析法获得属性对聚类的贡献度,并以该区间为约束条件,提出了可同时获得属性权重和聚类结果的模糊C均值聚类新算法.实验结果表明,该算法以决策者的经验和偏好为监督,可避免迭代计算陷入不必要的局部极小解,能够提高权重分配的合理性,进而得到了更为准确的聚类结果.     

直觉模糊C-均值聚类算法研究

鉴于直觉模糊集理论作为模糊理论的推广已得到广泛的应用,研究了将模糊C-均值聚类推广为直觉模糊C-均值聚类（IFCM）的途径和方法,分析了现有的几种IFCM算法,并提出了一种基于直觉模糊集的模糊C-均值聚类算法．该算法首先定义了直觉模糊集之间的距离;然后构造了聚类的目标函数;最后给出了聚类算法步骤．将算法用于目标识别,实验结果表明了算法的有效性．     

基于加权模糊c均值聚类的快速图像自动分割算法

图像分割是指将一幅图像分解为若干互不交迭的区域的集合，是图像处理和计算机视觉的基本问题之一。为了提高图像分割的效率，提出了一种基于2维直方图加权的塔形模糊c均值（FCM）聚类图像快速分割算法。该方法先通过构造合理的2维直方图对噪声进行抑制；然后通过塔形分解来缩减聚类样本集；最后利用加权FCM聚类算法进行分类。仿真结果表明，该方法的效率明显优于标准的FCM算法。此外，为确定分割的最优类别数c，还引入了一种基于该快速算法的聚类有效性评价函数——修正划分模糊度，实现了最佳图像分割类别数c的自动确定。基于人造图像和实际图像的测试实验结果表明该方法是有效的。     

基于网格和密度的模糊c均值聚类初始化方法

模糊c均值聚类算法是目前聚类分析中最受欢迎的算法之一,但其聚类效果往往受初始参数的影响.针对这一问题,提出一种基于网格和密度的模糊c均值聚类初始化方法.以网格和密度为工具提取聚类样本的类聚类中心,以此来初始化模糊c均值聚类算法的初始参数,从而弥补原算法的不足.实验证明方法是可行的、有效的.     

新型区间数据模糊C-均值聚类算法

在传统模糊C-均值聚类算法的基础上,提出了一种新型区间值数据模糊聚类算法。运用区间分割策略改进了区间距离的计算公式,成功解决了区间距离计算方法存在的缺陷。提出了区间值数据模糊聚类的数学模型,并拓广模糊C-均值算法对区间值数据进行聚类。仿真验证了所提出算法的有效性。     

IFCM:改进的区间值数据的模糊C-均值聚类算法

对基于区间值数据的模糊聚类算法进行了研究,介绍了具有控制区间大小对聚类结果影响的加权因子的模糊C-均值聚类新算法.针对区间值数据模糊C-均值聚类新算法提出了一个适应距离的弹性系数,使算法得到改进,既能利用传统的FCM算法,又考虑了区间大小对聚类结果的影响,同时也能发现不规则的聚类子集,使聚类结果更加准确.     

具有数据容错能力的模糊C均值聚类算法

提出基于模糊c均值聚类算法的两个新算法.设置每个数据隶属度的误差阈值,规定每个数据的隶属度误差不能超过给出的误差阈值.使用该类算法可以对有误差的数据进行模糊聚类.先利用隶属度矩阵的误差范围建立新的拉格朗日函数,再使用Kuhn-Tucker条件计算该函数,并通过一组实验来证明这类算法的正确性和有效性.     

基于区间2-型模糊度量的粗糙K-means聚类算法*

现有粗糙K-means聚类算法及系列改进、衍生算法均是从不同角度描述交叉类簇边界区域中的不确定性数据对象,却忽视类簇间规模的不均衡对聚类迭代过程及结果的影响.文中引入区间2-型模糊集的概念度量类簇的边界区域数据对象,提出基于区间2-型模糊度量的粗糙K-means聚类算法.首先根据类簇的数据分布生成边界区域样本对交叉类簇的隶属度区间,体现数据样本的空间分布信息.然后进一步考虑类簇的数据样本规模,在隶属度区间的基础上自适应地调整边界区域的样本对交叉类簇的影响系数.文中算法削弱边界区域对较小规模类簇的中心均值迭代的不利影响,提高聚类精度.在人工数据集及UCI标准数据集的测试分析验证算法的有效性.     

离散II-型模糊集的不确定性度量

随着II-型模糊集理论的不断发展和应用领域的扩大,需要探讨II-型模糊集不确定性的性质与度量方法,在研究II-型模糊集不确定性特征及模糊熵的基础上,通过扩展模糊熵的定义,给出了离散II-型模糊集熵的定义,证明其满足模糊熵的4条公理性条件,该定义将对II-型模糊集在不确定环境中的应用提供新的思路和方法。     

Dealing with incomplete information in linguistic group decision making by means of Interval Type-2 Fuzzy Sets

Nowadays, in the social network–based decision-making processes, like the ones involved in e-commerce and e-democracy, multiple users with different backgrounds may take part and diverse alternatives might be involved. This diversity enriches the process, but at the same time, increases the uncertainty of opinions. This uncertainty can be considered from two different perspectives: (i) the uncertainty in the meaning of the words given as preferences, that is, motivated by the heterogeneity of the decision makers; and (ii) the uncertainty inherent to any decision-making process that may lead to an expert not being able to provide all their judgments. The main objective of this study is to address these two types of uncertainty. To do so, the following approaches are proposed: First, to capture, process, and keep the uncertainty in the meaning of the linguistic assumption, the Interval Type-2 Fuzzy Sets are introduced as a way to model the experts' linguistic judgments. Second, a measure of the coherence of the information provided by each decision maker is proposed. Finally, a consistency-based completion approach is introduced to deal with the uncertainty presented in the expert judgments. The proposed approach is tested in an e-democracy decision-making scenario.     

Interval Type-2 fuzzy voter design for fault tolerant systems

A voting scheme constitutes an essential component of many fault tolerant systems. Two types of voters are commonly used in applications of real-valued systems: the inexact majority and the amalgamating voters. The inexact majority voter effectively isolates erroneous modules and is capable of reporting benign outputs when a significant disagreement is detected. However, an application specific voter threshold must be provided. On the other hand, amalgamating voter, such as the weighted average voter, reduces the influence of faulty modules by averaging the input values together. Unlike the majority voters, amalgamating voters are not capable of producing benign outputs. In the past, a Type-1 (T1) fuzzy voting scheme was introduced, allowing for both smooth amalgamation of voter inputs and effective signalization of benign outputs. The presented paper proposes an extension to the fuzzy voting scheme via incorporating Interval Type-2 (IT2) fuzzy logic. The IT2 fuzzy logic allows for an improved handling of uncertain assumptions about the distributions of noisy and erroneous inputs which are essential for correct design of the fuzzy voting scheme. The proposed voter design features robust performance when the uncertainty assumptions dynamically change over time. The IT2 fuzzy voter architecture was compared against the average voter, inexact majority voter, and the T1 fuzzy voter using a refined experimental harness. The reported results demonstrate improved availability, safety and reliability of the presented IT2 fuzzy voting scheme.     

一一映射下区间二型模糊集合的语言动力学轨迹

给出区间二型模糊扩展原理,并将常规的一一映射抽象成与之对应的区间二型模糊映射。介绍基于区间二型模糊扩展原理的词计算方法。最后分析区间二型模糊集合的语言动力学轨迹。     

基于二型模糊逻辑的多线程数据竞争检测方法研究

多线程机制以其诸多优势在程序开发中被广泛使用,然而随着多线程软件规模的增长,程序中潜存着许多并发缺陷,最常见的并发缺陷是数据竞争和死锁。目前,针对这些并发缺陷的检测手段都无法处理线程时序的不确定性,无法处理运行时环境对线程时序的影响,同时也不能计算这些并发缺陷发生的概率并根据概率生成其处理优先级。针对以上问题,提出了一种基于二型模糊逻辑的多线程数据竞争检测方法。该方法将传统的多线程时序分析和缺陷检测方法作为预处理,考虑程序运行时环境因素对线程时序的影响,利用二型模糊逻辑和隐马尔科夫模型对待检测程序建模,计算待检测程序在某一系统负载下的时序概率,并根据时序概率生成时序缺陷处理优先级列表供软件开发人员参考。     

Traffic Flow Data Forecasting Based on Interval Type-2 Fuzzy Sets Theory

This paper proposes a long-term forecasting scheme and implementation method based on the interval type-2 fuzzy sets theory for traffic flow data. The type-2 fuzzy sets have advantages in modeling uncertainties because their membership functions are fuzzy. The scheme includes traffic flow data preprocessing module, type-2 fuzzification operation module and long-term traffic flow data forecasting output module, in which the Interval Approach acts as the core algorithm. The central limit theorem is adopted to convert point data of mass traffic flow in some time range into interval data of the same time range (also called confidence interval data) which is being used as the input of interval approach. The confidence interval data retain the uncertainty and randomness of traffic flow, meanwhile reduce the influence of noise from the detection data. The proposed scheme gets not only the traffic flow forecasting result but also can show the possible range of traffic flow variation with high precision using upper and lower limit forecasting result. The effectiveness of the proposed scheme is verified using the actual sample application.      

Ⅱ-型模糊集截集的定义及特征研究

经典模糊集的截集概念是经典模糊集合与经典集合联系的桥梁,对于II-型模糊集,该文在分析II-型模糊集、区间值II-型模糊集、I-型模糊集以及经典集合之间关系的基础上,定义了II-型模糊集的截集概念,分析了II-型模糊集截集的特征,仿真证明了II-型模糊集截集的有效性,为基于II-型模糊集的决策、聚类等实际应用提供了新的方法。     

Dynamic Type-2 Fuzzy Dependent Dirichlet Regression Mixture clustering model

In this paper, a new dynamic Interval Type-2 Fuzzy Dependent Dirichlet Piecewise Regression Mixture (IT2FDDPRM) clustering model is proposed. The model overcomes shortcomings of both Dependent Dirichlet Process Mixture (DDPM) technique and Interval Type-2 Fuzzy C-regression Clustering Model (IT2FCRM). DDPM method demonstrates that the probability of assigning data to a cluster including the maximum number of data among all clusters is higher, and it ignores the similarity of data to a cluster. However, the new IT2FDDPRM clustering technique supports assignment of data to a cluster which has the most similarity to them. It also allows the model to generate infinite number of clusters. Moreover, it has the capability of segmenting functions assigned to clusters. The model is validated using statistical tests, three validity functions, and mean square error of the model. The results of numerical experiments show that the proposed method has superior performance to other clustering techniques in literature.