Heuristic Approaches to Attribute Reduction for Generalized Decision Preservation

Abstract

Attribute reduction is a challenging problem in rough set theory, which has been applied in many research fields, including knowledge representation, machine learning, and artificial intelligence. The main objective of attribute reduction is to obtain a minimal attribute subset that can retain the same classification or discernibility properties as the original information system. Recently, many attribute reduction algorithms, such as positive region preservation, generalized decision preservation, and distribution preservation, have been proposed. The existing attribute reduction algorithms for generalized decision preservation are mainly based on the discernibility matrix and are, thus, computationally very expensive and hard to use in large-scale and high-dimensional data sets. To overcome this problem, we introduce the similarity degree for generalized decision preservation. On this basis, the inner and outer significance measures are proposed. By using heuristic strategies, we develop two quick reduction algorithms for generalized decision preservation. Finally, theoretical and experimental results show that the proposed heuristic reduction algorithms are effective and efficient.

Using Neighborhood Rough Set Theory to Address the Smart Elderly Care in Multi-Level Attributes

“…The algorithm has been extensively evaluated using the LDOS-CoMoDa data set and accuracy of context sparsity methods by utilizing relevant context symmetric attributes whether the idea of combining soft rough sets and decision technology is extended to other domain areas. Zhang et al introduced the similarity of universal decision preservation and on this basis, put forward countermeasures of internal meaning and external meaning [44]. Two fast reduction algorithms for general decision retention are developed by using heuristic strategies.…”

Attribute Reduction Method Based on Generalized Grey Relational Analysis and Decision-Making Trial and Evaluation Laboratory

“…In classical RST research, the concept of DIS is usually the starting point and a DIS is a 4-tuple = ( , , , ) [6], [10], [13]:…”

“…Therefore, attribution reduction is one of the most important and urgent research topics in intelligent manufacturing. Currently, attribute reduction is widely applied in areas such as data classification, pattern recognition, machine learning, data mining, artificial intelligence [6], [8], [9], [10], [11].…”

“…In recent years, some new attribute reduction algorithms are proposed. These methods are mainly based on information granularity [18], [19], the similarity degree [10], incremental mechanism [20], positive approximation [9], the dominance relation [12], [21], the graph theory [22], the Map Reduce [23], the information entropy theory [24], [25], [26], [27],the discernibility matrix [28], the uncertainty measure [29], the various intelligent optimization algorithm (such as genetic algorithm [30], particle swarm [31], ant colony [32], the binary bat algorithm [33], the artificial bee colony [34], [35]), and so on. Most of the algorithms are heuristic [8], [10], [18], [36], [37], [38], which is regarded as the best method to get the minimum reduction set [39].…”

“…Most of the attribute reduction algorithms follow RST because of its effectiveness in attribute reduction. RST, as a mathematical approach solving uncertain and vague issues, has been applied extensively to attribute reduction [7], [10], [18], [20], [21]. Although RST-based methods are usually used to deal with static data sets, the probability of getting the minimum attribute reduction in the calculation is low [35], [40].…”