变精度粗糙集的逻辑解释及其约简

针对Ziarko提出的变精度粗糙集缺乏相应的逻辑解释, 且约简方法不合理, 对经典粗糙集的逻辑解释进行了扩展, 提出了变精度粗糙集决策算法应满足的四个条件, 证明了变精度粗糙集决策算法与β近似的关系并得到变精度粗糙集决策算法的性质; 其次, 在变精度粗糙集的逻辑解释下, 提出基于β下近似分布和β上近似分布变精度粗糙集的约简方法, 从而保证了约简前后分类能力大小不发生改变且符合变精度粗糙集的逻辑解释; 最后, 通过实例说明基于β下近似分布和β上近似分布约简方法的合理性。     

变精度粗糙集模型及其应用研究

介绍了广义粗糙集模型和Ziarko变精度粗糙集模型,找出了它们的不足;借助引入的误差参数β(0≤β<0.5),给出了基于后继邻域的一般二元关系下变精度粗糙集模型的β上近似、β下近似、3边界和β负域的定义以及β近似质量和β粗糙性测度定义;详细讨论了β上、下近似算子的性质、该模型与其他粗糙集模型的关系以及一般二元关系下两种变精度粗糙集模型的关系;最后,举例说明了该模型在信息处理中的应用。     

变精度覆盖粗糙集模型的比较

介绍覆盖粗糙集和Ziarko变精度粗糙集模型,将Ziarko变精度粗糙近似算子应用于覆盖近似空间,借助引入的误差参数β (0 ≤β<0.5),给出2种变精度覆盖粗糙集模型的β上近似、β下近似、β边界和β负域的定义。讨论2种模型中β上、下近似算子的基本性质、2种模型之间的关系以及变精度覆盖粗糙集模型与其他粗糙集模型的关系。     

变精度覆盖粗糙集

介绍了Ziarko变精度粗糙集模型和覆盖粗糙集模型;定义了多数包含关系;借助引入的误差参数β（0≤β<0.5）,给出了基于对象邻域的变精度覆盖粗糙集模型中β上近似、β下近似、β边界和β负域的定义以及β近似质量和β粗糙性测度定义;详细讨论了β上、下近似算子的性质、集合的相对可辨别性、该模型与Ziarko变精度粗糙集模型和覆盖粗糙集模型的关系;最后探讨了变精度覆盖粗糙集模型中的约简问题并在所给模型的基础上举例说明了它们在信息处理中的应用。     

变精度复合粗糙集模型及其应用*

针对复合信息系统中的噪声数据以及复合粗糙集近似边界要求严格等问题,对复合粗糙集模型进行了扩展,提出变精度复合粗糙集模型。在该模型中,通过设置阈值参数β (0.5<β ≤1),定义了基于矩阵方法的变精度复合粗糙集的β-上近似、β-下近似、β-正区域、β-负区域、β-边界区域、β-精确度和β-粗糙度等概念;同时,对变精度复合粗糙集的相关性质进行了研究。最后,通过实例说明了该模型在信息处理中的应用,进一步说明该模型具有一定的容错性,抗干扰能力增强,应用范围扩大。     

变精度粗糙模糊集模型研究

介绍了Ziarko’s变精度粗糙集模型和粗糙模糊集模型,找出了它们的不足。基于支集相对错误分类率及误差参数β（0≤β<0.5）,提出了变精度粗糙模糊集模型,讨论了模型中β上、下近似算子的性质;分析了该模型与Ziarko’s变精度粗糙集模型和粗糙模糊集模型的关系;最后给出了该模型中近似约简的定义和方法,并通过实例分析说明了约简算法的有效性。     

基于广义变精度粗糙模糊集模型的知识发现

介绍了广义Ziarko's变精度粗糙集模型和广义粗糙模糊集模型,找出了它们的不足.基于支集相对错误分类率及误差参数β(0≤β＜0.5),提出了广义变精度粗糙模糊集模型,讨论了模型中β上、下近似算子的性质;分析了该模型与广义Pawlak's粗糙集模型、广义Ziarko's变精度粗糙集模型和广义粗糙模糊集模型的关系;最后给出了该模型中近似约简的定义和方法,并通过实例分析说明了约简算法的有效性.     

变精度模糊粗糙集的一种定义

模糊粗糙集模型同经典粗糙集模型类似,容易受到噪音数据的影响.针对该问题,受变精度粗糙集模型的启发,提出了变精度模糊粗糙集的概念.针对现有变精度模糊粗糙集模型尚不能满足一些基本性质的缺陷,重新定义了模糊近似空间中某一模糊集的β-下近似和β-上近似,该定义方式能够满足上述的基本性质.     

广义变精度粗糙集模型中近似算子研究

定义了多数包含关系;借助引入的误差参数β（0≤β〈0．5）,提出了基于后继邻域的广义变精度粗糙集模型的β上近似aprβX、β下近似aprβX、β边界bnrβX和β负域negrβX的定义;详细讨论了β上、下近似算子aprβX与aprβX的性质;从对偶性角度出发推广了β上近似、β下近似算子aprβX与aprβX,得到了两对对偶的上、下近似算子aprβX与aprβX和aprβX与aprβX;最后全面讨论了推广后的两对上、下近似算子APRβX与aprβX和aprβX与aprβX的性质,详细分析了它们同广义变精度粗糙集模型中上、下近似算子aprβX与aprβX和一般关系下的变精度粗糙集模型中上、下近似算子RβX与RβX的关系。     

变精度上近似与程度下近似粗糙集模型的正域及其算法

针对变精度近似与程度近似的结合问题及正域的核心地位,组建了变精度上近似与程度下近似粗糙集模型,并定义了其中的正域概念。研究了模型正域与精度量化指标和程度量化指标关联的内涵及意义,得到了模型正域的精确刻画与性质。为了计算模型正域,提出了自然算法与原子算法,并进行了算法分析与算法比较,得到了自然算法与原子算法具有相同的时间复杂性,而原子算法却具有更优的空间复杂性的结论。最后用一个医疗实例对模型正域及其算法进行了分析与说明。变精度上近似与程度下近似粗糙集模型的正域,从膨胀的优势方向完全扩展了经典粗糙集模型的正域,对与精度参数和程度参数相关的必然性知识发现具有意义。     

加权粗糙集的矩阵表示

在加权近似空间中提出了关系矩阵和布尔列向量加权α下乘法和加权α上乘法的概念。证明了加权α下乘法就是加权下近似,加权α上乘法就是加权上近似,从而为加权粗糙集（可变精度粗糙集、经典粗糙集）的计算和研究提供了一种新的矩阵方法。最后给出了计算加权上下近似的算法。     

Generalized fuzzy rough sets determined by a triangular norm

The theory of rough sets has become well established as an approach for uncertainty management in a wide variety of applications. Various fuzzy generalizations of rough approximations have been made over the years. This paper presents a general framework for the study of T-fuzzy rough approximation operators in which both the constructive and axiomatic approaches are used. By using a pair of dual triangular norms in the constructive approach, some definitions of the upper and lower approximation operators of fuzzy sets are proposed and analyzed by means of arbitrary fuzzy relations. The connections between special fuzzy relations and the T-upper and T-lower approximation operators of fuzzy sets are also examined. In the axiomatic approach, an operator-oriented characterization of rough sets is proposed, that is, T-fuzzy approximation operators are defined by axioms. Different axiom sets of T-upper and T-lower fuzzy set-theoretic operators guarantee the existence of different types of fuzzy relations producing the same operators. The independence of axioms characterizing the T-fuzzy rough approximation operators is examined. Then the minimal sets of axioms for the characterization of the T-fuzzy approximation operators are presented. Based on information theory, the entropy of the generalized fuzzy approximation space, which is similar to Shannon’s entropy, is formulated. To measure uncertainty in T-generalized fuzzy rough sets, a notion of fuzziness is introduced. Some basic properties of this measure are examined. For a special triangular norm T = min, it is proved that the measure of fuzziness of the generalized fuzzy rough set is equal to zero if and only if the set is crisp and definable.     

基于粗概念格模型的电子商务领域本体的构建研究

以构建电子商务系统中的本体为出发点,分析现有的本体构建技术中存在的缺陷。针对这些不足,综合考虑变精度粗糙集模型和形式概念分析的相关理论,提出基于粗概念格模型来构建本体。将变精度粗糙集的β选取算法和可辨识矩阵属性约简算法进行了改进,使β 上、下分布的约简方法适用于形式背景的约简,从而提出基于变精度粗糙集的概念格约减算法;然后计算语义概念相似度,并以联合国标准产品与服务分类代码的本体元模型为核心本体,结合领域专家知识,建立电子商务领域本体模型。实验表明了粗概念格构建本体的高效性。     

Mining fuzzy β-certain and β-possible rules from quantitative data based on the variable precision rough-set model

The rough-set theory proposed by Pawlak, has been widely used in dealing with data classification problems. The original rough-set model is, however, quite sensitive to noisy data. Ziarko thus proposed the variable precision rough-set model to deal with noisy data and uncertain information. This model allowed for some degree of uncertainty and misclassification in the mining process. Conventionally, the mining algorithms based on the rough-set theory identify the relationships among data using crisp attribute values; however, data with quantitative values are commonly seen in real-world applications. This paper thus deals with the problem of producing a set of fuzzy certain and fuzzy possible rules from quantitative data with a predefined tolerance degree of uncertainty and misclassification. A new method, which combines the variable precision rough-set model and the fuzzy set theory, is thus proposed to solve this problem. It first transforms each quantitative value into a fuzzy set of linguistic terms using membership functions and then calculates the fuzzy β-lower and the fuzzy β-upper approximations. The certain and possible rules are then generated based on these fuzzy approximations. These rules can then be used to classify unknown objects. The paper thus extends the existing rough-set mining approaches to process quantitative data with tolerance of noise and uncertainty.     

变精度极大相容块粗糙集模型及其属性约简

主要研究不完备信息系统的属性约简问题。首先基于极大相容块构造乐观和悲观两种广义变精度粗糙集模型,分析两种模型之间的关系并研究其主要性质。在此基础上,定义乐观(悲观)β-下分布约简和β-上分布约简并且给出相应的判定定理,进而得到一种保持决策类上(下)近似分布不变的属性约简方法--布尔计算方法。这种构造极大相容块间的辨识矩阵的方法缩小了矩阵的规模,进而简化了计算属性约简的过程,从而能够有效地节省计算时间和存储空间。然后对含有"丢失""不关心"值和只有"不关心"值的两种不完备信息系统进行实例分析,最后从UCI数据集中选取5组不完备信息数据集来验证方法的有效性。     

On rough set and fuzzy sublattice

Let L be a lattice with the least element 0 and the greatest element 1 and let θ be a full congruence relation on L. In this paper, the notion of θ-upper and θ-lower approximations of a fuzzy subset of L is introduced and some important properties will be studied.     

基于概念格的粗糙集近似

粗糙集理论的一个重要研究方面是用已定义的概念来近似未定义的概念,而如何构建可定义概念以及如何确定近似运算是这一工作的基础.利用粗糙集这一工具,从概念格的角度来确定可定义概念,并在此基础上研究了概念的粗糙近似.根据粗糙集上下近似的包含关系,得到概念的一种新的上下近似的运算的定义.粗糙集近似理论利用两种不同的近似运算,产生两种不同的近似来描述概念格背景下的对象集合.     

Rough approximations on a complete completely distributive lattice with applications to generalized rough sets

The generalizations of rough sets considered with respect to similarity relation, covers and fuzzy relations, are main research topics of rough set theory. However, these generalizations have shown less connection among each other and have not been brought into a unified framework, which has limited the in-depth research and application of rough set theory. In this paper the complete completely distributive (CCD) lattice is selected as the mathematical foundation on which definitions of lower and upper approximations that form the basic concepts of rough set theory are proposed. These definitions result from the concept of cover introduced on a CCD lattice and improve the approximations of the existing crisp generalizations of rough sets with respect to similarity relation and covers. When T-similarity relation is considered, the existing fuzzy rough sets are the special cases of our proposed approximations on a CCD lattice. Thus these generalizations of rough sets are brought into a unified framework, and a wider mathematical foundation for rough set theory is established.     

一种基于粗糙集理论的最简规则挖掘方法

提出了一种基于粗糙集理论的最简规则挖掘方法，它是一个采用基于分类正确度的粗糙集模型进行多概念分类规则挖掘的新方法，能有效处理决策表的不一致性，采用启发式算法，挖掘出满足给定精确度的最简产生式规则知识。用多个UCI数据集对算法进行了测试，并且与著名的Rosetta软件进行实验对比，结果说明此方法大大提高了总的数据约简量，可以有效地简化最终得到的规则知识。     

基于粗糙度的近似概念格动态分类集成学习模型研究与应用

概念格(Galois格)是一种进行数据分类学习的有效工具,然而建格规模庞大使分类效率和准确率受到较大影响.将粗糙度理论应用到概念格分类问题研究中,提出一种新型的近似概念格动态建格和分类挖掘集成学习模型(CACLR).该模型在粗糙度区间根据样本空间分布构建多个相对独立分布且比较精确的近似概念格分类器,能及时消除建格过程中大量与分类知识无关的节点,有效缩减原格规模,融合得到的分类挖掘集成学习模型,具有较好的粗糙分类精度和知识预测学习能力.最后进行CACLR分类集成学习模型在标准UCI数据集中的对比实验,有效验证了该模型的实用价值.