Rough Set Approach in Machine Learning: A Review

Abstract

The Rough Set (RS) theory can be considered as a tool to reduce the input dimensionality and to deal with vagueness and uncertainty in datasets. Over the years, there has been a rapid growth in interest in rough set theory and its applications in artificial intelligence and cognitive sciences, especially in research areas such as machine learning, intelligent systems, inductive reasoning, pattern recognition, data preprocessing, knowledge discovery, decision analysis, and expert systems. This paper discusses the basic concepts of rough set theory and point out some rough set-based research directions and applications. The discussion also includes a review of rough set theory in various machine learning techniques like clustering, feature selection and rule induction.

A Recent Study on the Rough Set Theory in Multi-Criteria Decision Analysis Problems

“…Data is different among each other based on the dimension and complexity [2]. Hence, it is difficult to manage and analyze the data without having good data administration officers, techniques, theories, or tools.…”

“…The special feature of a rough set is, it does not need any fundamental or additional information in analyzing data. Therefore, it is always preferred and selected as one of the methods which can be implemented in many areas mainly in cognitive sciences and artificial intelligence such as in decision analysis [5], [14], machine learning [13], intelligent systems, inductive reasoning, pattern recognition [15], mereology, image processing, signal analysis, knowledge discovery, and expert systems [2], [7], [16], [17].…”

“…RST was commonly employed as a feature selection tool, attribute or knowledge reduction, rule extraction, uncertainty reasoning, granular computing, derivation of decision table in data mining, pattern identification and also in machine learning area [3]- [5]. Furthermore, due to many advantages of RST, researchers recently constructed many experimental works by integrating other theories such as genetic algorithm, neural network, fuzzy set and others with RST [2], [3]. These novelty works had contributed to many areas especially in reasoning, optimization, and classification tasks when imprecision and uncertainty of a data is involved in the decision process [1], [5]- [7].…”

“…Rough set theory (RST) is a mathematical method which was introduced by Z. Pawlak in 1982 to deal with the ambiguity and uncertainty of data [1], [2]. Later, in 1997, RST had been extended to deal with many application areas especially in decision analysis.…”

Generated rules for AIDS and e-learning classifier using rough set approach

“…In real world data varies in size and complexity, which is difficult to analyze and also hard to manage from computational view point. The major objectives of RS are to reduce data size and to handle inconsistency or redundancy in data [4]. Hidden patterns or hidden information or relationship can be identified from large data sets.…”