Article

A Genetic Algorithm-Based Solution for the Problem of Small Disjuncts

Authors:

Deborah R. Carvalho,

Alex Alves FreitasAuthors Info & Claims

PKDD '00: Proceedings of the 4th European Conference on Principles of Data Mining and Knowledge Discovery

Pages 345 - 352

Published: 13 September 2000 Publication History

Abstract

In essence, small disjuncts are rules covering a small number of examples. Hence, these rules are usually error-prone, which contributes to a decrease in predictive accuracy. The problem is particularly serious because, although each small disjuncts covers few examples, the set of small disjuncts can cover a large number of examples. This paper proposes a solution to the problem of discovering accurate small-disjunct rules based on genetic algorithms. The basic idea of our method is to use a hybrid decision tree / genetic algorithm approach for classification. More precisely, examples belonging to large disjuncts are classified by rules produced by a decision-tree algorithm, while examples belonging to small disjuncts are classified by a new genetic algorithm, particularly designed for discovering small-disjunct rules.

References

[1]

CARVALHO, D.R. and FREITAS, A.A. A hybrid decision tree/genetic algorithm for coping with the problem of small disjuncts in data mining. To appear in Proc. 2000 Genetic and Evolutionary Computation Conf. (GECCO-2000). Las Vegas, NV, USA. July 2000.

Google Scholar

[2]

COVER, T.M., THOMAS, J.A. (1991) Elements of Information Theory. John Wiley & Sons.

Digital Library

Google Scholar

[3]

DANYLUK, A., P. and PROVOST, F.,J. (1993). Small Disjuncts in Action: Learning to Diagnose Errors in the Local Loop of the Telephone Network, Proc. 10th International Conference Machine Learning, 81-88.

Crossref

Google Scholar

[4]

FREITAS, A.A. (2000) Evolutionary Algorithms. Chapter of forthcoming Handbook of Data Mining and Knowledge Discovery. Oxford University Press, 2000.

Google Scholar

[5]

FREITAS, A.A. and LAVINGTON, S.H. (1998) Mining Very Large Databases with Parallel Processing. Kluwer.

Digital Library

Google Scholar

[6]

HAND, D.J.(1997) Construction and Assessment of Classification Rules. John Wiley & Sons.

Google Scholar

[7]

HOLTE, R.C.; ACKER, L.E. and PORTER, B.W. (1989). Concept Learning and the Problem of Small Disjuncts, Proc. IJCAI - 89, 813-818.

Digital Library

Google Scholar

[8]

MICHALEWICZ, Z. (1996) Genetic Algorithms + Data Structures = Evolution Programs. 3rd Ed. Springer-Verlag.

Digital Library

Google Scholar

[9]

NAZAR, K. and BRAMER, M.A. (1999) Estimating concept difficulty with cross entropy. In: Bramer, M.A. (Ed.) Knowledge Discovery and Data Mining, 3-31. London: IEE.

Digital Library

Google Scholar

[10]

NODA, E.; LOPES, H.S.; FREITAS, A.A. (1999) Discovering interesting prediction rules with a genetic algorithm. Proc. Congress on Evolutionary Comput. (CEC-99), 1322-1329.

Crossref

Google Scholar

[11]

PROVOST, F. and ARONIS, J.M. (1996). Scaling up inductive learning with massive parallelism. Machine Learning 23(1), Apr. 1996, 33-46.

Digital Library

Google Scholar

[12]

QUINLAN, J.R. (1993). C4.5: Programs for Machine Learning, Morgan Kaufmann.

Digital Library

Google Scholar

[13]

RENDELL, L. and SESHU, R. (1990) Learning hard concepts through constructive induction: framework and rationale. Computational Intelligence 6, 247-270.

Digital Library

Google Scholar

Cited By

View all

Jacques JTaillard JDelerue DJourdan LDhaenens CAlba E(2013)The benefits of using multi-objectivization for mining pittsburgh partial classification rules in imbalanced and discrete dataProceedings of the 15th annual conference on Genetic and evolutionary computation10.1145/2463372.2463432(543-550)Online publication date: 6-Jul-2013
https://dl.acm.org/doi/10.1145/2463372.2463432
do Amaral LSadoyama GEspindola Fde Oliveira G(2008)Oncogenes classification measured by microarray using Genetic AlgorithmsProceedings of the 26th IASTED International Conference on Artificial Intelligence and Applications10.5555/1712759.1712776(79-84)Online publication date: 6-Feb-2008
https://dl.acm.org/doi/10.5555/1712759.1712776
Geng LHamilton H(2006)Interestingness measures for data miningACM Computing Surveys10.1145/1132960.113296338:3(9-es)Online publication date: 30-Sep-2006
https://dl.acm.org/doi/10.1145/1132960.1132963
Show More Cited By

A Genetic Algorithm-Based Solution for the Problem of Small Disjuncts
1. Computing methodologies
  1. Artificial intelligence
    1. Search methodologies

Recommendations

An improved genetic algorithm with conditional genetic operators and its application to set-covering problem

The genetic algorithm (GA) is a popular, biologically inspired optimization method. However, in the GA there is no rule of thumb to design the GA operators and select GA parameters. Instead, trial-and-error has to be applied. In this paper we present an ...
A hybrid decision tree/genetic algorithm for coping with the problem of small disjuncts in data mining
GECCO'00: Proceedings of the 2nd Annual Conference on Genetic and Evolutionary Computation

The problem of small disjuncts is a serious challenge for data mining algorithms. In essence, small disjuncts are rules covering a small number of examples. Due to their nature, small disjuncts tend to be error prone and contribute to a decrease in ...
Solving the Graph Planarization Problem Using an Improved Genetic Algorithm

An improved genetic algorithm for solving the graph planarization problem is presented. The improved genetic algorithm which is designed to embed a graph on a plane, performs crossover and mutation conditionally instead of probability. The improved ...

Comments

Information & Contributors

Information

Published In

PKDD '00: Proceedings of the 4th European Conference on Principles of Data Mining and Knowledge Discovery

September 2000

698 pages

ISBN:354041066X

Publisher

Springer-Verlag

Berlin, Heidelberg

Publication History

Published: 13 September 2000

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

7
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 25 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

View all

Jacques JTaillard JDelerue DJourdan LDhaenens CAlba E(2013)The benefits of using multi-objectivization for mining pittsburgh partial classification rules in imbalanced and discrete dataProceedings of the 15th annual conference on Genetic and evolutionary computation10.1145/2463372.2463432(543-550)Online publication date: 6-Jul-2013
https://dl.acm.org/doi/10.1145/2463372.2463432
do Amaral LSadoyama GEspindola Fde Oliveira G(2008)Oncogenes classification measured by microarray using Genetic AlgorithmsProceedings of the 26th IASTED International Conference on Artificial Intelligence and Applications10.5555/1712759.1712776(79-84)Online publication date: 6-Feb-2008
https://dl.acm.org/doi/10.5555/1712759.1712776
Geng LHamilton H(2006)Interestingness measures for data miningACM Computing Surveys10.1145/1132960.113296338:3(9-es)Online publication date: 30-Sep-2006
https://dl.acm.org/doi/10.1145/1132960.1132963
Carvalho DFreitas A(2005)Evaluating Six Candidate Solutions for the Small-Disjunct Problem and Choosing the Best Solution via Meta-LearningArtificial Intelligence Review10.1007/s10462-005-1586-724:1(61-98)Online publication date: 1-Sep-2005
https://dl.acm.org/doi/10.1007/s10462-005-1586-7
Carvalho DFreitas A(2004)A hybrid decision tree/genetic algorithm method for data miningInformation Sciences: an International Journal10.1016/j.ins.2003.03.013163:1-3(13-35)Online publication date: 14-Jun-2004
https://dl.acm.org/doi/10.1016/j.ins.2003.03.013
Park BKargupta HJohnson ESanseverino EHershberger DSilvestre L(2001)Distributed, Collaborative Data Analysis from Heterogeneous Sites Using a Scalable Evolutionary TechniqueApplied Intelligence10.1023/A:101281332651916:1(19-42)Online publication date: 20-Nov-2001
https://dl.acm.org/doi/10.1023/A%3A1012813326519
Freitas A(2001)Understanding the Crucial Role of AttributeInteraction in Data MiningArtificial Intelligence Review10.1023/A:101199621020716:3(177-199)Online publication date: 22-Nov-2001
https://dl.acm.org/doi/10.1023/A%3A1011996210207

Abstract

References

Cited By

Recommendations

An improved genetic algorithm with conditional genetic operators and its application to set-covering problem

A hybrid decision tree/genetic algorithm for coping with the problem of small disjuncts in data mining

Solving the Graph Planarization Problem Using an Improved Genetic Algorithm

Comments

Information

Published In

Publisher

Publication History

Qualifiers

Contributors

Other Metrics

Bibliometrics

Article Metrics

Other Metrics

Citations

Cited By

View options

Share

Share this Publication link

Share on social media

Affiliations