Author_Institution :
Sch. of Inf. Eng., China Univ. of Geosci. (Beijing), Beijing, China
Abstract :
The information system classification is a crucial part of data mining, which aims to analysis the information system, extract important message from complex data, and forecast the future development trend of data. At present, there are many methods to classify the data, for example, Rough Set Theory, Decision Tree, Bayesian Network, Genetic Algorithm, etc. The method presented in this paper, based on ID3 Algorithm, associated with the combination of Rough Set Theory and Decision Tree Theory, uses the conditional attribute as the decision tree´s node to classify data in the information system. Moreover, a new fast algorithm for getting approximate operators is used in the information system classification to improve the efficiency.
Keywords :
belief networks; data mining; decision trees; genetic algorithms; information systems; pattern classification; rough set theory; Bayesian network; ID3 Algorithm; data mining; decision tree theory; genetic algorithm; information system classification; rough set approximate operators; Algorithm design and analysis; Approximation algorithms; Approximation methods; Classification algorithms; Classification tree analysis; Information systems; approximate operators; decision tree; information system classification; rough set;
