基于投票式属性重要度的快速属性约简算法

作为经典Pawlak粗糙集的扩展,邻域粗糙集能有效处理数值型的数据。但是,因为引入了邻域粒化的概念,所以邻域实数空间下的计算量要比经典离散空间下的计算量大得多。对于邻域粗糙集算法而言,能够有效且快速地找到数据集的属性约简是十分有意义的。为此,针对现有算法中属性重要度定义的不足,首先提出了一种改进的投票式属性重要度,然后进一步提出了一种基于投票式属性重要度的快速属性约简算法。实验证明,与现有算法相比,在保证分类精度的前提下,该算法能更快速地得到属性约简。     

基于邻域粗糙集下知识划分的信息表降维

Pawlak粗糙集的知识约简包括对决策表的知识约简和对信息表的知识约简。作为Pawlak粗糙集的扩展,邻域粗糙集在针对决策表的属性约简方面应用广泛,而针对信息表的属性约简方面应用鲜少。为了设计一种适用于信息表的属性约简算法,根据Pawlak粗糙集的信息表知识约简标准,首先提出一种邻域粗糙集的信息表知识约简标准,然后根据这种标准,结合贪心思想,进一步提出了一种适用于聚类任务的信息表属性约简算法。与主成分分析(principal component analysis,PCA)算法相比,实验结果表明用该算法对数据集降维后,得到的属性约简集合的属性个数较多,K-means算法根据属性集合进行聚类的精度较高。实验结果证明该算法能有效地应用于信息表的属性约简方面。     

F-邻域粗糙集及其约简

邻域粗糙集可以直接处理数值型数据, F- 粗糙集是第一个动态粗糙集模型. 针对动态变化的数值型数据, 结合邻域粗糙集和F- 粗糙集的优势, 提出了F- 邻域粗糙集和F- 邻域并行约简. 首先, 定义了F- 邻域粗糙集上下近似、边界区域; 其次, 在F- 邻域粗糙集中提出了F- 属性依赖度和属性重要度矩阵; 根据F- 属性依赖度和属性重要度矩阵分别提出了属性约简算法, 证明了两种约简方法的约简结果等价; 最后, 比对实验在UCI数据集、真实数据集和MATLAB生成数据集上完成, 实验结果显示, 与相关算法比较, F- 邻域粗糙集可以获得更好的分类准确率. 为粗糙集在大数据方面的应用增加了一种新方法.     

信息增益混合邻域粗糙集的肺部肿瘤高维特征选择算法

针对冗余属性和不相关属性过多对肺部肿瘤诊断的影响以及Pawlak粗糙集只适合处理离散变量而导致原始信息大量丢失的问题,提出混合信息增益和邻域粗糙集的肺部肿瘤高维特征选择算法(Information gain-neighborhood rough set-support vector machine,IG-NRS-SVM)。该算法首先提取3 000例肺部肿瘤CT图像的104维特征构造决策信息表,借助信息增益结果选出高相关的特征子集,再通过邻域粗糙集剔除高冗余的属性,通过两次属性约简得到最优的特征子集,最后采用网格寻优算法优化的支持向量机构建分类识别模型进行肺部肿瘤良恶性的鉴别。从约简和分类识别两个角度验证方法的可行性与有效性,并与不约简算法、Pawlak粗糙集、信息增益和邻域粗糙集约简算法进行对比。结果表明混合算法精确度优于其他对比算法,精确度达到96.17%,并且有效降低了时间复杂度,对肺部肿瘤计算机辅助诊断具有一定的参考价值。     

变精度下不完备邻域决策系统的属性约简算法

邻域粗糙集模型在处理完备的数值型数据中得到广泛应用,但针对不完备的数值型和符号型混合数据进行属性约简的讨论相对较少。为此,首先结合邻域粗糙集给出了可变精度模型下不完备邻域决策系统的上、下近似算子及属性约简;然后通过邻域粒化的方法构建了广义邻域下可变精度的粗糙集模型,并提出了一种属性重要度的评价方法;在此基础上,设计出了面向不完备邻域决策系统的属性约简算法,该算法可直接处理不完备的数值型和符号型混合数据;最后,通过实例分析验证了本文提出的算法能够求解出变精度下不完备邻域决策系统的属性约简结果。     

基于邻域辨识矩阵的属性约简增量式算法

邻域粗糙集模型可以直接处理连续型数据.属性约简是邻域粗糙集模型的重要研究内容之一.目前已有的增量式粗糙集约简算法主要考虑经典的粗糙集模型的情况,不适用于邻域粗糙集模型.为此,提出一种基于邻域辨识矩阵的属性约简增量式算法,主要考虑连续型数据对象动态增加的情况下的属性约简问题.为了解决该问题,提出了一种邻域决策系统的辩识矩阵,通过辨识矩阵的动态更新实现动态求核,并在此基础上,利用原有的属性约简进行属性约简的更新.     

基于邻域近似条件熵的启发式属性约简

目前粗糙集的研究局限于有限集,且现有的邻域粗糙集属性约简算法中属性重要性度量方式单一。针对邻域粗糙集存在的问题,提出了基于无限集的邻域近似条件熵模型。该模型以邻域近似条件熵下的属性重要度为启发条件,构造了一种基于邻域近似条件熵的前向贪心搜索属性约简算法。利用熵的单调性,证明了算法的正确性,并分析了算法的时间复杂度。通过实例分析和多个UCI数据集上的实验表明,所提出的算法是可行的,能有效减少属性数量,与现有的算法相比,不仅能够获得较小的属性约简结果,而且具有较好的分类性能。     

基于非对称变邻域粗糙集模型的属性约简

在分析邻域粗糙集模型弊端的基础上,提出了非对称变邻域粗糙集模型,并以全局属性重要度为启发条件,构造了基于非对称变邻域粗糙集模型的属性约简的启发式算法.利用6个UCI标准数据集与现有算法进行了比较分析,结果表明,该模型不仅可以选择较少的属性个数,而且还能保持较高的分类能力.     

不完备邻域决策粗糙集的最小化代价属性约简算法

目前的决策粗糙集研究主要集中在完备离散型信息系统,很少有对不完备连续型数据进行研究,考虑这一问题,提出一种不完备邻域决策粗糙集模型。首先在不完备连续型数据中引入了不完备邻域关系,然后利用该二元关系对传统的决策粗糙集进行重构,一种称之为不完备邻域决策粗糙集的模型被提出,同时基于决策代价原则,进一步地提出了最小化决策代价的属性约简算法。最后通过实验表明了所提出的算法具有更高的属性约简性能。     

基于矩阵保留策略的邻域粗糙集属性约简算法

在基于邻域粗糙集的属性约简算法中,正域计算是保证其有效性的重要依据,也是影响其时间开销的最主要部分。为了减少算法时间开销,通过对现有算法FHARA的正域计算进行改进,采取保留策略,利用矩阵保留度量计算值的平方,将原本◢n◣维上的计算改进为1维上的计算,从而缩减了每次度量计算的时间,并在此基础上提出了基于矩阵保留策略的邻域粗糙集属性约简算法,最后通过多个UCI数据集验证了该算法。与现有算法相比较,实验结果表明,对大部分数据集而言,该算法能有效且更快速地得到数据集的属性约简。     

Three-way decision reduction in neighborhood systems

Rough set reduction has been used as an important preprocessing tool for pattern recognition, machine learning and data mining. As the classical Pawlak rough sets can just be used to evaluate categorical features, a neighborhood rough set model is introduced to deal with numerical data sets. Three-way decision theory proposed by Yao comes from Pawlak rough sets and probability rough sets for trading off different types of classification error in order to obtain a minimum cost ternary classifier. In this paper, we discuss reduction questions based on three-way decisions and neighborhood rough sets. First, the three-way decision reducts of positive region preservation, boundary region preservation and negative region preservation are introduced into the neighborhood rough set model. Second, three condition entropy measures are constructed based on three-way decision regions by considering variants of neighborhood classes. The monotonic principles of entropy measures are proved, from which we can obtain the heuristic reduction algorithms in neighborhood systems. Finally, the experimental results show that the three-way decision reduction approaches are effective feature selection techniques for addressing numerical data sets.     

基于矩阵的混合型邻域决策粗糙集增量式更新算法

决策粗糙集模型是当前粗糙集理论最为重要的研究分支之一.然而,由于现实环境下数据类型的复杂多样以及数据的动态更新,使得传统的决策粗糙集模型面临着一定的局限和不足,针对这一问题,提出一种混合型信息系统的邻域决策粗糙集模型,并设计出一种矩阵方法的邻域决策粗糙集增量式更新算法.首先,将传统的离散型决策粗糙集模型在混合型信息系统...     

冗余数据约简的研究与设计

Z. Pawlak于1982年提出的Rough集理论有效地分析了不确定、不精确、不一致等各种不完备信息，其优点是无需任何关于数据的初始的或附加的信息，如统计学中的概率分布。该文介绍了Rough集的基本理论在数据约简中的应用。在分析基于信息系统的粗糙集理论的基础上，描述了一种基于核与重要度的约简算法，从降低约简算法计算复杂度角度出发，修改了属性约简算法，计算了算法修改前后的复杂度。实验结果表明，修改后的算法在降低时间复杂度的同时得出了次优属性集的约简。     

A weighted rough set based method developed for class imbalance learning

In this paper, we introduce weights into Pawlak rough set model to balance the class distribution of a data set and develop a weighted rough set based method to deal with the class imbalance problem. In order to develop the weighted rough set based method, we design first a weighted attribute reduction algorithm by introducing and extending Guiasu weighted entropy to measure the significance of an attribute, then a weighted rule extraction algorithm by introducing a weighted heuristic strategy into LEM2 algorithm, and finally a weighted decision algorithm by introducing several weighted factors to evaluate extracted rules. Furthermore, in order to estimate the performance of the developed method, we compare the weighted rough set based method with several popular methods used for class imbalance learning by conducting experiments with twenty UCI data sets. Comparative studies indicate that in terms of AUC and minority class accuracy, the weighted rough set based method is better than the re-sampling and filtering based methods, and is comparable to the decision tree and SVM based methods. It is therefore concluded that the weighted rough set based method is effective for class imbalance learning.     

Multi-level rough set reduction for decision rule mining

Most previous studies on rough sets focused on attribute reduction and decision rule mining on a single concept level. Data with attribute value taxonomies (AVTs) are, however, commonly seen in real-world applications. In this paper, we extend Pawlak’s rough set model, and propose a novel multi-level rough set model (MLRS) based on AVTs and a full-subtree generalization scheme. Paralleling with Pawlak’s rough set model, some conclusions related to the MLRS are given. Meanwhile, a novel concept of cut reduction based on MLRS is presented. A cut reduction can induce the most abstract multi-level decision table with the same classification ability on the raw decision table, and no other multi-level decision table exists that is more abstract. Furthermore, the relationships between attribute reduction in Pawlak’s rough set model and cut reduction in MLRS are discussed. We also prove that the problem of cut reduction generation is NP-hard, and develop a heuristic algorithm named CRTDR for computing the cut reduction. Finally, an approach named RMTDR for mining multi-level decision rule is provided. It can mine decision rules from different concept levels. Example analysis and comparative experiments show that the proposed methods are efficient and effective in handling the problems where data is associated with AVTs.     

基于邻域粗糙互信息熵的非单调性属性约简

属性约简是粗糙集理论一项重要的应用,目前已广泛运用于机器学习和数据挖掘等领域,邻域粗糙集是粗糙集理论中处理连续型数据的一种重要方法.针对目前邻域粗糙集模型中属性约简存在的缺陷,构造一种基于邻域粗糙集的邻域粗糙熵模型,并基于此给出邻域粗糙联合熵、邻域粗糙条件熵和邻域粗糙互信息熵等概念.邻域粗糙互信息熵是评估属性集相关性的一种重要的方法,具有非单调性变化的特性,对此,提出一种基于邻域粗糙互信息熵的非单调性属性约简算法.实验分析表明,所提出算法不仅比目前已有的单调性属性约简算法具有更优越的属性约简结果,而且具有更高的约简效率.     

Research on the model of rough set over dual-universes

To tackle the problem of rough set on single-universe, we discuss the rough set model over dual-universes in aspect of building connection between single-universe model and dual-universes model. The rough set model over dual-universes denoted as RSMDU in this paper is built through inspecting the relation between the two universes. Firstly, we propose the RSMDU and study its property using character function and relation matrix. The algorithm for obtaining the lower and upper approximations is then presented. Secondly, we show that Pawlak rough set model can be induced using RSMDU. The theorem inferring the connection between Pawlak model induced by RSMDU and RSMDU is presented. Finally, the applications of RSMDU are studied. According to proposed model, we demonstrate that the existing models of rough set are special cases of RSMDU and that the set of conditional attribute and the set of decision attribute can be regarded as dual-universes in decision-making system, where the model can be utilized to handle decision processing.