A real coded MOGA for mining classification rules with missing attribute values

Authors:
Dipankar Dutta;Paramartha Dutta
Affiliations:
UIT, BU, Golapbug (North), Burdwan, West Bengal, India;VB, Santiniketan, West Bengal, India
Venue:
Proceedings of the 2011 International Conference on Communication, Computing & Security
Year:
2011

Citing 11
Cited 0

C4.5: programs for machine learning

C4.5: programs for machine learning
Data preparation for data mining

Data preparation for data mining
Mining the most interesting rules

KDD '99 Proceedings of the fifth ACM SIGKDD international conference on Knowledge discovery and data mining
Genetic Algorithms in Search, Optimization and Machine Learning

Genetic Algorithms in Search, Optimization and Machine Learning
The CN2 Induction Algorithm

Machine Learning
CMAR: Accurate and Efficient Classification Based on Multiple Class-Association Rules

ICDM '01 Proceedings of the 2001 IEEE International Conference on Data Mining
Mining Optimal Class Association Rule Set

PAKDD '01 Proceedings of the 5th Pacific-Asia Conference on Knowledge Discovery and Data Mining
Data Mining: Concepts and Techniques

Data Mining: Concepts and Techniques
Application of elitist multi-objective genetic algorithm for classification rule generation

Applied Soft Computing
Genetic algorithm-based strategy for identifying association rules without specifying actual minimum support

Expert Systems with Applications: An International Journal
Multiobjective evolutionary algorithms: a comparative case studyand the strength Pareto approach

IEEE Transactions on Evolutionary Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

Classification rule mining is one of the important data mining tasks. Optimized Rule Set (ORS) generation is a major challenge. Multi Objective Genetic Algorithm (MOGA) has been used to search available data effectively and among many objectives instead of single objective with its real coded elitist version along with special operator. Some Data Sets (DSs) having missing attribute values. In some of their earlier work researchers are either considered DS without any missing attributes values or eliminated records having missing attribute values at data preprocessing phase, considered missing values as one category of value, replaced missing values with the most common value of the attribute or assigned probability to each of the possible values to replace missing values. In this work these are not required. During training and testing phase attributes having valid values have been used for ORS generation and testing.