Wyniki wyszukiwania - BazTech

Ograniczanie wyników

3 Foundations of Computing and Decision Sciences

Powiadomienia systemowe

Sesja wygasła!
Sesja wygasła!

Znaleziono wyników: 3

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Optimal solution of a decision table: a rough set based software toolkit

Shrabonti G., Alam S. S.

Foundations of Computing and Decision Sciences

2004

Vol. 29, No. 3

227-245

As the amount of information in the world is steadily increasing, there is a growing demand for tools to analyze information. Rough set methodology is very useful in data analysis of an information system such as in data generalization and data reduction. In this paper, we generalize the method proposed by Pawlak for reduction of a special and important class of an information system called decision table, where the attribute values are almost identical, not exactly equal. After simplification of decision table we obtain minimal solution (not necessarily unique) from a set of input data considering that they are almost equal. As the simplification of a decision table does not yield unique result, so, in general, many minimal solutions are possible and making choice of 'best' or 'optimal' solution from amongst them is not an easy task. The 'best' or 'optimal' criteria are different for different decision makers depending on their intensions. In this paper, a software toolkit (based on rough set theory) has been proposed for finding optimal solution(s) from amongst all possible minimal solutions of a decision table. As significance of attributes plays a very important role in rough set analysis, the proposed method for getting optimal solution(s) has been developed by using the measure of significance of attributes.

Approximate decision logic and reduction of decision rules

Shrabonti G., Alam S. S.

Foundations of Computing and Decision Sciences

2003

Vol. 28, No. 1

3-16

This paper generalises Pawlak's rough approach to Reduction of Decision Rules using Decision Logic language (DL-language) by introducing Approximate Decision Logic language (ADL-language) based on almost indiscernibility relation. An information system has been considered where attribute values are not always quantitative, rather subjective having vague or imprecise meanings. Some objects may have attribute values which are almost identical. This observation has been analysed here based on fuzzy proximity relations on different domains of attributes.

(alfa, beta) reduction of decision table : a rough approach

Shrabonti G., Ranjit B., Alam S. S.

Foundations of Computing and Decision Sciences

2001

Vol. 26, No. 4

273-281

In this paper, we generalise Pawlak's rough approach for simplifying a decision table in an information system. We consider an information system where attribute values are not always quantitative, rather subjective having vague or imprecise meanings. Some objects may have attribute values which are almost identical, i.e., they can't be distinguished clearly by the attributes. Considering this observation, we present a generalised method for reduction of decision table for different choice values of alfa and beta, a being for condition attributes and beta for decision attributes where Alfa, Beta € [0, 1]. For a = 1 and Beta = 1, the method reduces to Pawlak's method.