Feature selection using rough entropy-based uncertainty measures in incomplete decision systems

Sun, Lin; Xu, Jiucheng; Tian, Yun

doi:10.1016/j.knosys.2012.06.010

Cited by 124 publications

(60 citation statements)

References 25 publications

(85 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Entropy is always used to measure the out-of-order degree of a system, then Shannon introduced the concept of entropy in physics to information entropy for measuring uncertainty of the structure of a system [9,12,14]. However, Shannon's entropy cannot measure the fuzziness in rough set theory.…”

Section: Information Entropy and Conditional Entropy In Incomplete Inmentioning

confidence: 99%

“…The research has recently roused great interest in the theoretical and applicable fronts, such as pattern recognition, data mining, machine learning, decision support, and so on [5,6,7,8]. As one of the most important issues in rough set theory, uncertainty of a set and its measures have been widely studied [9,10,11].…”

Section: Introductionmentioning

confidence: 99%

“…It has been a useful mechanism for characterizing uncertainty in a great diversity of modes and applications [15,16,17,18]. Shannon's entropy and its variants have been used to measure the uncertainty in rough set theory, and information interpretation of rough set theory was given in [9,10,19]. Beaubouef et al [20] addressed information measures of uncertainty of rough sets and rough relation databases.…”

Section: Introductionmentioning

confidence: 99%

“…However, classical rough set theory is unsuitable for measuring the uncertainty and attribute reduction of incomplete information systems and incomplete decision systems. To address this issue, several interesting and meaningful extensions to equivalence relation have been proposed, such as tolerance relations [9,11,12,30,32,33], neighborhood operators [34,35], others [36,37]. In recent years, some new uncertainty measure theories and reduction methods have been developed, which are capable of reducing the attributes in incomplete information systems without preprocessing, and do not require changing the size of the original system.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Information Entropy and Information Granulation-based Uncertainty Measures in Incomplete Information Systems

Sun¹,

Xu²,

Xu³

2014

Appl. Math. Inf. Sci.

Self Cite

View full text Add to dashboard Cite

Abstract:In this paper, concepts of information entropy and information granulation-based uncertainty measures are introduced in incomplete information/decision systems, and based on maximal consistent block technique, some variants of information entropy and information granulation are presented to measure the discernibility ability of an incomplete information system. Then, some important properties of them are discussed. From these properties, it can be shown that these proposed measures provide important approaches to measure the uncertainty ability of different knowledge in incomplete information/decision systems. And relationships among these measures are established as well. These results will be very helpful for understanding the essence of knowledge content and uncertainty measures in incomplete information systems.

show abstract

Section: Information Entropy and Conditional Entropy In Incomplete Inmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Information Entropy and Information Granulation-based Uncertainty Measures in Incomplete Information Systems

Sun¹,

Xu²,

Xu³

2014

Appl. Math. Inf. Sci.

Self Cite

View full text Add to dashboard Cite

show abstract

“…That is, the selected gene subset plays an important role in the process of cancer identification [7,8]. Currently feature selection methods can be divided into three categories: filters, wrappers, and embedded methods [4,9,10]. Particularly, both wrappers and embedded methods consider the correlativity between genes, thus the feature genes select-ed by the two methods are more interpretable.…”

Section: Introductionmentioning

confidence: 99%

Feature gene selection method based on logistic and correlation information entropy

Sun

2015

BME

Self Cite

View full text Add to dashboard Cite

Abstract. In view of the characteristics of high dimension, small samples, nonlinearity and numeric type in the gene expression profile data, the logistic and the correlation information entropy are introduced into the feature gene selection. At first, the gene variable is screened preliminarily by logistic regression to obtain the genes that have a greater impact on the classification; then, the candidate features set is generated by deleting the unrelated features using Relief algorithm. On the basis of this, delete redundant features by using the correlation information entropy; finally, the feature gene subset is classified by using the classifier of support vector machine (SVM). Experimental results show that the proposed method can obtain smaller subset of genes and achieve higher recognition rate.

show abstract

A Group Incremental Reduction Algorithm with Varying Data Values

Jing

Huang

et al. 2016

Int. J. Intell. Syst.

View full text Add to dashboard Cite

Attribute reduction based on rough set theory has attracted much attention recently. In real‐life applications, many decision tables may vary dynamically with time, e.g., the variation of attributes, objects, and attribute values. The reduction of decision tables may change on the alteration of attribute values. The paper focuses on dynamic maintenance of attribute reduction when varying data values of multiple objects. Incremental mechanisms for knowledge granularity are proposed first, which aims to update attribute reduction effectively. Then, a group incremental reduction algorithm with varying data values is developed. When attribute values of multiple objects have been replaced by new ones in decision table, the proposed incremental algorithm can find the new reduct in a much shorter time. The time complexity analysis and experiments on different data sets from UCI have validated that the proposed incremental algorithms are efficient and effective to update the reduction with the variation of attribute values.

show abstract

Feature selection using rough entropy-based uncertainty measures in incomplete decision systems

Cited by 124 publications

References 25 publications

Information Entropy and Information Granulation-based Uncertainty Measures in Incomplete Information Systems

Information Entropy and Information Granulation-based Uncertainty Measures in Incomplete Information Systems

Feature gene selection method based on logistic and correlation information entropy

A Group Incremental Reduction Algorithm with Varying Data Values

Contact Info

Product

Resources

About