A new hybrid method of generation of decision rules using the constructive induction mechanism

Authors:
Wiesław Paja;Krzysztof Pancerz;Mariusz Wrzesień
Affiliations:
Department of Artificial Intelligence and Expert Systems, Institute of Biomedical Informatics, University of Information Technology and Management in Rzeszów, Poland;Department of Artificial Intelligence and Expert Systems, Institute of Biomedical Informatics, University of Information Technology and Management in Rzeszów, Poland;Department of Artificial Intelligence and Expert Systems, Institute of Biomedical Informatics, University of Information Technology and Management in Rzeszów, Poland
Venue:
RSKT'10 Proceedings of the 5th international conference on Rough set and knowledge technology
Year:
2010

Citing 6
Cited 2

Hypothesis-Driven Constructive Induction in AQ17-HCI: A Method and Experiments

Machine Learning - Special issue on evaluating and changing representation
Bayesian Networks and Decision Graphs

Bayesian Networks and Decision Graphs
Requirements for Successful Verification in Practice

Proceedings of the Fifteenth International Florida Artificial Intelligence Research Society Conference
Iterative feature construction for improving inductive learning algorithms

Expert Systems with Applications: An International Journal
Post-processing of associative classification rules using closed sets

Expert Systems with Applications: An International Journal
Non-redundant sequential rules-Theory and algorithm

Information Systems

A constructive feature induction mechanism founded on evolutionary strategies with fitness functions generated on the basis of decision trees

RSKT'11 Proceedings of the 6th international conference on Rough sets and knowledge technology
Belief networks in classification of laryngopathies based on speech spectrum analysis

RSKT'12 Proceedings of the 7th international conference on Rough Sets and Knowledge Technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

Our research is devoted to develop a new method of generation of a set of decision rules. This method is compiled using two different mechanisms. The first one is based on applying a new constructive induction algorithm to the investigated dataset. The belief networks are used in this algorithm. The aim is to find the most important descriptive attribute that is calculated on the basis of other attributes. The second part of the presented method constitutes the improvement algorithm that is used in an optimization process of a gathered rule set. The results of our research contain the comparison of classification efficiency using several datasets.