Reduct and attribute order

Based on the principle of discernibility matrix, a kind of reduction algorithm with attribute order has been developed and its solution has been proved to be complete for reduct and unique for a given attribute order. Being called the reduct problem, this algorithm can be regarded as a mapping R = Reduct(S) from the attribute order space O to the reduct space R for an information system (U, C ∪ D）, where U is the universe and C and D are two sets of condition and decision attributes respectively. This paper focuses on the reverse problem of reduct problem S = Order(R), i.e., for a given reduct R of an information system, we determine the solution of S = Order(R) in the space θ. First, we need to prove that there is at least one attribute order S such that S = Order(R). Then, some decision rules are proposed, which can be used directly to decide whether the pair of attribute orders has the same reduct. The main method is based on the fact that an attribute order can be transformed into another one by moving the attribute for limited times. Thus, the decision of the pair of attribute orders can be altered to the decision of the sequence of neighboring pairs of attribute orders. Therefore,the basic theorem of neighboring pair of attribute orders is first proved, then, the decision theorem of attribute order is proved accordingly by the second attribute.     

粗糙模糊集的格论性质

Let U denote a finite and nonempty set called the universe, and P(U) a power set. Suppose R is an equiva-lence relation on U. Consider the equivalence relation ≈ (X≈Y←→^-RX=^-R and RX=RY, X,Y, ∈ F(U)) on F(U),the quotient set denoted by F(U)/≈. In this paper we show that F(U)/≈ is a distributive lattice.     

Reduction Algorithms Based on Discernibility Matrix：The Ordered Atributes Method

In this Paper,we present reduction algorithms based on the principle of Skowron‘s discernibility matrix-the ordered attributes method.The completeness of the algorithms for Pawlak reduct and the uniqueness for a given order of the attributes are proved.Since a discernibility matrix requires the size of the memory of |U|^2,U is a universe of bojects,it would be impossible to apply these algorithms directly to a massive object set.In order to solve the problem,a so=called quasi-discernibility matrix and two reduction algorithms are prpopsed.Although the proposed algorithms are incomplete for Pawlak reduct,their optimal paradigms ensure the completeness as long as they satisfy some conditions.Finally,we consider the problem on the reduction of distributive object sets.     

A Reduction Algorithm Meeting Users Requirements

Generally a database encompasses various kinds of knowledge and is shared by many users.Different users may prefer different kinds of knowledge.So it is important for a data mining algorithm to output specific knowledge according to users‘ current requirements (preference).We call this kind of data mining requirement-oriented knowledge discovery (ROKD).When the rough set theory is used in data mining,the ROKD problem is how to find a reduct and corresponding rules interesting for the user.Since reducts and rules are generated in the same way,this paper only concerns with how to find a particular reduct.The user‘s requirement is described by an order of attributes,called attribute order,which implies the importance of attributes for the user.In the order,more important attributes are located before less important ones.then the problem becomes how to find a reduct including those attributes anterior in the attribute order.An approach to dealing with such a problem is proposed.And its completeness for reduct is proved.After that,three kinds of attribute order are developed to describe various user requirements.     

Second Attribute Algorithm Based on Tree Expression

One view of finding a personalized solution of reduct in an information system is grounded on the viewpoint that attribute order can serve as a kind of semantic representation of user requirements. Thus the problem of finding personalized solutions can be transformed into computing the reduct on an attribute order. The second attribute theorem describes the relationship between the set of attribute orders and the set of reducts, and can be used to transform the problem of searching solutions to meet user requirements into the problem of modifying reduct based on a given attribute order. An algorithm is implied based on the second attribute theorem, with computation on the discernibility matrix. Its time complexity is O（n^2 × m） （n is the number of the objects and m the number of the attributes of an information system）. This paper presents another effective second attribute algorithm for facilitating the use of the second attribute theorem, with computation on the tree expression of an information system. The time complexity of the new algorithm is linear in n. This algorithm is proved to be equivalent to the algorithm on the discernibility matrix.     

REMARKS ON JOHN DISKS

Let D■R2 be a Jordan domain,D*=R2\D,the exterior of D.In this article,the authors obtained the following results:(1)If D is a John disk,then D is an outer linearly locally connected domain;(2)If D* is a John disk,then D is an inner linearly locally connected domain;(3)A homeomorphism f:R 2 →R 2 is a quasiconformal mapping if and only if f(D)is a John disk for any John disk D■R 2 ;and(4)If D is a bounded quasidisk,then D is a John disk,and there exists an unbounded quasidisk which is not a John disk.     

Lower estimation of approximation rate for neural networks

Let SFd and Πψ,n,d = { nj=1bjψ(ωj·x+θj) :bj,θj∈R,ωj∈Rd} be the set of periodic and Lebesgue’s square-integrable functions and the set of feedforward neural network (FNN) functions, respectively. Denote by dist (SF d, Πψ,n,d) the deviation of the set SF d from the set Πψ,n,d. A main purpose of this paper is to estimate the deviation. In particular, based on the Fourier transforms and the theory of approximation, a lower estimation for dist (SFd, Πψ,n,d) is proved. That is, dist(SF d, Πψ,n,d) (nlogC2n)1/2 . T...     

An Efficient Algorithm for Processing Multi-Relation Queries in Relational Databases

After a relation scheme R is decomposed into the set of schemes ρ={R1，…，Rn},we may pose queries as if Rexisted in the database,taking a join of Ri‘s,when it is necessary to implement the query,Suppos a query involves a set of attributes S R，we want to find the smallest subset of ρ whose union includes.S.We prove that the problem is NP-complete and present a polynomial-bounded approximation algorithm.A subset of ρ whose union includes S and has a decomposition into 3NF with a lossless join and preservation of dependencies in given in the paper.     

The Contiguity in R/M

An r.e. degree c is contiguous if degwtt(A)=degwtt(B)for any r.e. sets A,B∈c.In this paper,we generalize the notation of contiguity to the structure R/M, the upper semilattice of the r.e. degree set R modulo the cappable r.e. degree set M.An element[C]∈R/M is contiguous if s[degwtt(A)]=[degwtt(B)]for any r.e. sets A,B such that degT(A),degT(B)∈[c],It is proved in this paper that every nonzero element in R/M is not contiguous,i.e.,for every element [C]∈R/M,if[C]≠[O] then there exist at least two r.e. sets A,B such that degT(A),degT(B)∈[C]and [degwtt[A]≠[degwtt(B)].     

改进的基于简化二进制分辨矩阵的属性约简方法

在基于二进制分辨矩阵的属性约简方法中,删除法即从属性全集中依次删除冗余属性,直至剩余的属性集是一个最小约简.针对传统的基于二进制分辨矩阵的删除法效率较低且得不到最小约简的问题,提出一种改进的二进制分辨矩阵属性约简方法.首先对决策表进行简化,然后给出一种改进的简化二进制分辨矩阵方法;其次通过一个新的属性约简度量方法一次性删除多个属性,并从理论上分析了该方法的可行性;最后通过实验证明了得到的约简结果是最小约简.     

差别矩阵约简表示及其快速算法实现

差别矩阵可以拥有不同的信息, 根据差别矩阵描述的区分信息量不同, 给出4 种差别矩阵定义, 并提出相应H-约简、S-约简、B-约简和P-约简的概念; 研究4 种约简之间的关系, 构建通用约简算法模型. 为了提高约简算法的效率, 给出相对分辨能力约简定义(RD-约简), 揭示相对分辨能力约简与4 种差别矩阵约简之间的等价性, 进而设计相对分辨能力快速约简算法. 最后, 通过实例和UCI 数据集验证了所提出约简算法的有效性和时空性能.

     

基于标记可辨识矩阵的增量式属性约简算法

针对现有增量式属性约简算法中存在的约简传承性差以及不完备现象,提出基于标记可辨识矩阵的增量式属性约简算法.本文首先定义了标记函数,对样本之间的可辨识性进行分类,并将之引入一个新的可辨识矩阵,在新增样本时,结合标记信息可以快速识别可辨识矩阵元素集的异动,获得强传承性的约简超集,在此基础上,设计与标记可辨识矩阵匹配的必要矩阵,用以快速判断并删除冗余属性,确保约简的完备性. 理论分析以及实验测试表明,本算法具有约简传承性强,约简集完备等特点,具有较强的实用性.     

Relative reducts in consistent and inconsistent decision tables of the Pawlak rough set model

A relative reduct can be considered as a minimum set of attributes that preserves a certain classification property. This paper investigates three different classification properties, and suggests three distinct definitions accordingly. In the Pawlak rough set model, while the three definitions yield the same set of relative reducts in consistent decision tables, they may result in different sets in inconsistent tables.Relative reduct construction can be carried out based on a discernibility matrix. The study explicitly stresses a fact, that the definition of a discernibility matrix should be tied to a certain property. Regarding the three classification properties, we can define three distinct definitions accordingly.Based on the common structure of the specific definitions of relative reducts and discernibility matrices, general definitions of relative reducts and discernibility matrices are suggested.     

An incremental algorithm for attribute reduction with variable precision rough sets

Attribute reduction with variable precision rough sets (VPRS) attempts to select the most information-rich attributes from a dataset by incorporating a controlled degree of misclassification into approximations of rough sets. However, the existing attribute reduction algorithms with VPRS have no incremental mechanisms of handling dynamic datasets with increasing samples, so that they are computationally time-consuming for such datasets. Therefore, this paper presents an incremental algorithm for attribute reduction with VPRS, in order to address the time complexity of current algorithms. First, two Boolean row vectors are introduced to characterize the discernibility matrix and reduct in VPRS. Then, an incremental manner is employed to update minimal elements in the discernibility matrix at the arrival of an incremental sample. Based on this, a deep insight into the attribute reduction process is gained to reveal which attributes to be added into and/or deleted from a current reduct, and our incremental algorithm is designed by this adoption of the attribute reduction process. Finally, experimental comparisons validate the effectiveness of our proposed incremental algorithm.     

基于差别矩阵的属性约简完备算法

分析了传统属性频率函数作为属性重要度的不足,重新定义了属性重要度,提出了一种基于差别矩阵属性重要度的属性约简完备算法,即CRABSA（Complete Reduction Algorithm Based on the Significance of Attribute）。该算法采用迭代思想,在每次迭代过程中根据属性重要度SGF（a）选择必要的条件属性加入约简R中。由SGF（a）的定义可知,算法能确保在大多数情况下能得到决策表的最小约简。分析了算法在最坏情况下的时间复杂度,给出了该算法相对Pawlak约简的完备性的证明。     

Analysis of alternative objective functions for attribute reduction in complete decision tables

Attribute reduction and reducts are important notions in rough set theory that can preserve discriminatory properties to the highest possible extent similar to the entire set of attributes. In this paper, the relationships among 13 types of alternative objective functions for attribute reduction are systematically analyzed in complete decision tables. For inconsistent and consistent decision tables, it is demonstrated that there are only six and two intrinsically different objective functions for attribute reduction, respectively. Some algorithms have been put forward for minimal attribute reduction according to different objective functions. Through a counterexample, it is shown that heuristic methods cannot always guarantee to produce a minimal reduct. Based on the general definition of discernibility function, a complete algorithm for finding a minimal reduct is proposed. Since it only depends on reasoning mechanisms, it can be applied under any objective function for attribute reduction as long as the corresponding discernibility matrix has been well established.     

基于优化可辨识矩阵和改进差别信息树的属性约简算法

运用可辨识矩阵表示信息系统中所有对象的区分信息,为研究属性约简提供了新方向。然而,传统的可辨识矩阵在构造结束后才利用核属性消除冗余元素项,忽略了核属性在矩阵构建过程中的作用。针对这一问题,文中做了以下研究:1)优化可辨识矩阵的构造方式,在计算任意两个对象的区分信息之前,先判断核属性上的取值是否相等,如果不相等,则直接将对应元素项记为Φ,忽略对其他条件属性的判断;2)提出属性加权重要度的概念,综合考虑每个条件属性占可辨识矩阵中非空元素项的比率(称为宏观重要度)与每个属性对区分对象的贡献程度(称为微观重要度),并通过例子说明了该度量方法的合理性;3)针对优化后的矩阵仍然存在大量冗余元素和空集这一缺陷,结合差别信息树的概念提出基于优化可辨识矩阵和属性加权重要度的差别信息树。按照属性加权重要度对优化可辨识矩阵中所有非空元素项进行排序,使得重要度高的属性被更多的节点共享;且在构建过程中将不包含核属性的元素项映射到树中的一条路径上,而包含核属性的元素项则被直接忽略。最后,提出基于优化可辨识矩阵和改进差别信息树的约简算法HSDI-tree。在UCI的5个数据集上分别比较了HSDI-tree算法与CDI-tree,DI-tree和IDI-tree算法的约简结果和节点个数,实验结果表明HSDI-tree算法能有效找到最小属性约简且空间压缩能力更好。     

差别矩阵浓缩及其属性约简求解方法

属性约简是粗糙集理论的重要研究内容之一，已出现大量的属性约简算法，其中基于差别矩阵的属性约简算法是高效属性约简算法之一，但这些算法主要针对一致决策表，而对于不一致决策表，某些情况下不能得到属性约简。为此，本文提出改进的差别矩阵及其属性约简求解方法，统一考虑决策表一致和不一致情况两种情况下的属性约简，有效改进经典的基于差别矩阵求解属性约简的不足。同时，为适应大数据集属性约简需要，提出一种新的差别矩阵浓缩策略，以此提高属性约简的效率。