Dynamic Reducts and Statistical Inference
نویسنده
چکیده
We apply rough set methods and boolean reasoning for knowledge discovery from decision tables. It is often impossible to extract general laws from experimental data by computing rst all reducts (Pawlak 1991) of a data table (decision table) and next decision rules from these reducts. We have developed an idea of dynamic reducts as a tool allowing to nd relevant reducts for the decision rule generation (Bazan 1994a), (Bazan 1994b), (Bazan 1994c), (Nguyen 1993). Tests on several data tables are showing that the application of dynamic reducts leads to the increasing of the classiication quality and/or decreasing of the size of decision rule sets. In this paper we present some statistical arguments showing that the introduced stability coeecients of dynamic reducts are proper measures of their quality.
منابع مشابه
Dynamic Reducts as a Tool for Extracting Laws from Decisions Tables
We apply rough set methods and boolean reasoning for knowledge discovery from decision tables. It is not always possible to extract general laws from experimental data by computing rst all reducts 12] of a decision table and next decision rules on the basis of these reducts. We investigate a problem how information about the reduct set changes in a random sampling process of a given decision ta...
متن کاملDiscovery of Decision Rules fromExperimental
The problem of decision rules extracting (or more general knowledge discovery) from experimental data is intensively studied (see e. 27]). We apply rough set methods and boolean reasoning for decision rules discovery from decisions tables. It is not possible in general to extract general laws from experimental data by computing rst all reducts of a decision table representing data and next deci...
متن کاملDynamic Reducts in Object Oriented Information System Using Rough Set Theory
Abstract We introduce dynamic reducts in object oriented information system using rough set theory. To develop dynamic reducts in object oriented information system using rough set theory ,we propose object-oriented information system into rough set models. To accomplish this, we construct the class, object, and name structures using rough set theory. Next, combining class, name and object stru...
متن کاملReduct Generation in Information Systems
In any information system, the reducts are useful in classifying data. Janusz Starzyk developed an algorithm for computing reducts using strong equivalence and the law of expansion on the data. However, implementation of this algorithm is cumbersome for huge volume of data. This paper deals with a technique for obtaining the reduct of the entire system by partitioning it into two with respect t...
متن کاملRelated families-based attribute reduction of dynamic covering information systems with variations of object sets
In practice, there are many dynamic covering decision information systems, and knowledge reduction of dynamic covering decision information systems is a significant challenge of covering-based rough sets. In this paper, we first study mechanisms of constructing attribute reducts for consistent covering decision information systems when adding objects using related families. We also employ examp...
متن کامل