Quick general reduction algorithms for inconsistent decision tables

Ge, Hao; Long-shu, LI; Xu, Yi; Yang, Chuanjian

doi:10.1016/j.ijar.2016.11.016

Cited by 23 publications

(4 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For U/(C-{c i }) and U/(C-{c i+1 }), |C|-2 times sorts are repetitive (i.e., c i+2 ,…,c |C| ,c 1 ,…,c i-1 ) and have only one different sort. We all know that radix sort is stable; thus we can obtain U/(C-{c i+1 }) derived from U/(C-{c i }) [59] [36].…”

Section: A the Acceleration Strategy For Removing Redundant Attributesmentioning

confidence: 99%

Incremental Attribute Reduction Under Variations of the Attribute Set Based on Conflict Region

Yang

2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

Section: A the Acceleration Strategy For Removing Redundant Attributesmentioning

confidence: 99%

Incremental Attribute Reduction Under Variations of the Attribute Set Based on Conflict Region

Yang

2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

“…An attribute reduction algorithm based on conditional entropy of approximation set (ACIEAS) is proposed by [31]. It is based on formulation of the mutual information for relative reduction of knowledge to measure the goodness of feature subset by [9,13]. This algorithm is based on the conditional entropy.…”

Section: Introductionmentioning

confidence: 99%

Hybrid Entropy Method for Large Data Set Reduction Using MLP-ANN and SVM Classifiers

Rashmi

Ghose

2020

Communications in Computer and Information Science

View full text Add to dashboard Cite

Data reduction has an extreme role in machine learning and pattern recognition with high-dimensional data. It can be achieved with attribute reduction and/or instance selection. The selection of relevant instances and/or attributes from the large amount of data not only affects data reduction (size) but also maintains classification accuracy. Different algorithms have been proposed by many researchers based on instance based learning for attribute reduction to improve classification accuracy. In this paper, based on entropy and fuzzy entropy attribute reduction method is introduced and further tested with different kinds of classifiers. Proposed method helps in reducing storage size and improving classification accuracy. A large number of standard data sets with multiple classes are used to investigate the performance of the proposed method. The performance of this novel approach in terms of reduced data size and mean classification accuracy is measured and compared with existing instance based learning and attribute reduction methods. The experimental result reveals that the performance of the proposed method is positively better than current methods.

show abstract

“…In rough set theory, the information granulation is of extensive concern [ 45 , 46 , 47 , 48 , 49 ], and the granulation monotonicity plays an important role in attribute reduction [ 12 , 50 , 51 , 52 ]. In particular, a decision table acts as a formal background of data mining [ 12 , 53 , 54 , 55 ], and it involves condition/decision granules and classifications from granular structures. According to granular computing, Zhang and Miao [ 56 ] introduced three-layer granular structures of decision tables, and they further hierarchically constructed three-way informational measures based on weighted-entropies; moreover, Wang et al [ 57 ] utilized three-layer granular structures to research three-way weighted combination-entropies.…”

Section: Introductionmentioning

confidence: 99%

Double-Granule Conditional-Entropies Based on Three-Level Granular Structures

Zhang

2019

Entropy

View full text Add to dashboard Cite

Rough set theory is an important approach for data mining, and it refers to Shannon’s information measures for uncertainty measurements. The existing local conditional-entropies have both the second-order feature and application limitation. By improvements of hierarchical granulation, this paper establishes double-granule conditional-entropies based on three-level granular structures (i.e., micro-bottom, meso-middle, macro-top ), and then investigates the relevant properties. In terms of the decision table and its decision classification, double-granule conditional-entropies are proposed at micro-bottom by the dual condition-granule system. By virtue of successive granular summation integrations, they hierarchically evolve to meso-middle and macro-top, to respectively have part and complete condition-granulations. Then, the new measures acquire their number distribution, calculation algorithm, three bounds, and granulation non-monotonicity at three corresponding levels. Finally, the hierarchical constructions and achieved properties are effectively verified by decision table examples and data set experiments. Double-granule conditional-entropies carry the second-order characteristic and hierarchical granulation to deepen both the classical entropy system and local conditional-entropies, and thus they become novel uncertainty measures for information processing and knowledge reasoning.

show abstract

Quick general reduction algorithms for inconsistent decision tables

Cited by 23 publications

References 29 publications

Incremental Attribute Reduction Under Variations of the Attribute Set Based on Conflict Region

Incremental Attribute Reduction Under Variations of the Attribute Set Based on Conflict Region

Hybrid Entropy Method for Large Data Set Reduction Using MLP-ANN and SVM Classifiers

Double-Granule Conditional-Entropies Based on Three-Level Granular Structures

Contact Info

Product

Resources

About