Attribute Reduction for Partially Labeled Data Based on Hypergraph Models

Attribute reduction (feature selection) has become an important challenge in areas of pattern recognition, machine learning, data mining and knowledge discovery. Based on attribute reduction, one can extract fuzzy decision rules from a fuzzy decision table. As consistency is one of several criteria for evaluating the decision performance of a decision-rule set, in this paper, we devote to present a consistency-preserving attribute reduction in fuzzy rough set framework. Through constructing the membership function of an object, we first introduce a consistency measure to assess the consistencies of a fuzzy target set and a fuzzy decision table, which underlies a foundation for attribute reduction algorithm. Then, we derive two attribute significance measures based on the proposed consistency measure and design a forward greedy algorithm (ARBC) for attribute reduction from both numerical and nominal data sets. Numerical experiments show the validity of the proposed algorithm from search strategy and heuristic function in the meaning of consistency. Number of the selected features is the least for a given threshold of consistency measure.

Attribute reduction plays an important role in knowledge discovery and data mining. Confronted with data characterized by the interval and missing values in many data analysis tasks, it is interesting to research the attribute reduction for interval-valued data with missing values. Uncertainty measures can supply efficient viewpoints, which help us to disclose the substantive characteristics of such data. Therefore, this paper addresses the attribute reduction problem based on uncertainty measure for interval-valued data with missing values. At first, an uncertainty measure is provided for measuring candidate attributes, and then an efficient attribute reduction algorithm is developed for the interval-valued data with missing values. To improve the efficiency of attribute reduction, the objects that fall within the positive region are deleted from the whole object set in the process of selecting attributes. Finally, experimental results demonstrate that the proposed algorithm can find a subset of attributes in much shorter time than existing attribute reduction algorithms without losing the classification performance.

An incremental approach to attribute reduction from dynamic incomplete decision systems in rough set theory

A systematic study on attribute reduction with rough sets based on general binary relations

Granular maximum decision entropy-based monotonic uncertainty measure for attribute reduction

An improved attribute reduction scheme with covering based rough sets

Background: Assessment of liver fibrosis is a vital need for enabling therapeutic decisions and prognostic evaluations of chronic hepatitis. Liver biopsy is considered the definitive investigation for assessing the stage of liver fibrosis but it carries several limitations. FIB-4 and APRI also have a limited accuracy. The National Committee for Control of Viral Hepatitis (NCCVH) in Egypt has supplied a valuable pool of electronic patients’ data that data mining techniques can analyze to disclose hidden patterns, trends leading to the evolution of predictive algorithms. Aim: to collaborate with physicians to develop a novel reliable, easy to comprehend noninvasive model to predict the stage of liver fibrosis utilizing routine workup, without imposing extra costs for additional examinations especially in areas with limited resources like Egypt. Methods: This multi-centered retrospective study included baseline demographic, laboratory, and histopathological data of 69106 patients with chronic hepatitis C. We started by data collection preprocessing, cleansing and formatting for knowledge discovery of useful information from Electronic Health Records EHRs. Data mining has been used to build a decision tree (Reduced Error Pruning tree (REP tree)) with 10-fold internal cross-validation. Histopathology results were used to assess accuracy for fibrosis stages. Machine learning feature selection and reduction (CfsSubseteval / best first) reduced the initial number of input features (N=15) to the most relevant ones (N=6) for developing the prediction model. Results: In this study, 32419 patients had F(0-1), 25073 had F(2) and 11615 had F(3-4). FIB-4 and APRI revalidation in our study showed low accuracy and high discordance with biopsy results, with overall AUC 0.68 and 0.58 respectively. Out of 15 attributes machine learning selected Age, AFP, AST, glucose, albumin, and platelet as the most relevant attributes. Results for REP tree indicated an overall classification accuracy up to 70% and ROC Area 0.74 which was not nearly affected by attribute reduction, and pruning . However attribute reduction, and tree pruning were associated with simpler model easy to understand by physician with less time for execution. Conclusion: This study we had the chance to study a large cohort of 69106 chronic hepatitis patients with available liver biopsy results to revise and validate the accuracy of FIB-4 and APRI. This study represents the collaboration between computer scientist and hepatologists to provide clinicians with an accurate novel and reliable, noninvasive model to predict the stage of liver fibrosis.

Attribute reduction plays an important role in pattern recognition and machine learning, and the theory of rough sets has become a commonly used model for attribute reduction since its superiority in describing and quantifying vagueness and uncertainty. However, little attention has been paid to analyzing the importance of core attributes in different circumstances, and core attributes are generally all selected into the reduct without considering their differences. In this study, the role of core attributes is analyzed in terms of their impacts on classification ability, and the three-way partition of attributes is proposed to distinguish different core attributes and condition attributes. Then, a unified approximate attribute reduction framework based on the three-way decision is introduced to keep the quality and resulting classification performance of the reduct. Moreover, a general forward-adding and back-deleting heuristic algorithm is developed to effectively select important attributes and also eliminate unimportant core and condition attributes in the boundary region. Comprehensive comparative experiments and statistical significance analysis are conducted on UCI data sets. The experimental results show that our method achieves a better attribute reduction rate and classification performance and also verify that core attributes are not always indispensable.

Fuzzy object-induced network three-way concept lattice and its attribute reduction

Distance metric learning-based multi-granularity neighborhood rough sets for attribute reduction

Attribute reduction is one of the most important research issues in the rough set theory. The purpose of attribute reduction is to find a minimal attribute subset that satisfies some specific criteria, while the minimal attribute subset is called attribute reduct. In this paper, we define a similarity-based attribute reduct based on a clustering perspective. Each decision class is treated as a cluster, and the defined similarity-based attribute reduct can maintain or increase the discriminating ability of different clusters in the case of removing redundant attributes. In view of this, firstly, we define the intra-class similarity for objects in the same decision class and the inter-class similarity for objects between different decision classes. Secondly, we define a similarity-based attribute reduct by maximizing intra-class similarity and minimizing inter-class similarity in the rough set model. Thirdly, by considering the heuristic search strategy, we also design a corresponding reduction method for the proposed attribute reduct. The experimental results indicate that compared with other representative attribute reducts, our proposed attribute reduct can significantly improve the classification performance.

An efficient stripped cover-based accelerator for reduction of attributes in incomplete decision tables

A novel method for attribute reduction of covering decision systems

This paper is for refining database in the data mining process. Based on the analysis of the features and disadvantages of this decision tree algorithm and the substantive characteristics of data mining, we propose the concept of the core samples set and prove its invariance. On this basis, we build an attribute reduction method based on decision tree algorithm and then give a specific implementation steps, further, combined with a specific instance analyze the characteristics and efficiency of the method. Results show that the attribute reduction method based on the decision tree has good maneuverability and explicableness. This method can simply realize the attribute reduction of information system and its basic ideas completely adapt to the attribute reduction problems of the uncertain environment.

Attribute reduction with personalized information granularity of nearest mutual neighbors