Evaluating learning algorithms composed by a constructive meta-learning scheme for a rule evaluation support method

Hidenao Abe, Shusaku Tsumoto, Miho Ohsaki, Takahira Yamaguchi

Research output: Chapter in Book/Report/Conference proceedingChapter

1 Citation (Scopus)

Abstract

The Post-processing of mined patterns such as rules, trees and so forth is one of the key operations in a data mining process. However, it is difficult for human experts to completely evaluate several thousand rules from a large dataset with noise. To reduce the cost of this kind of rule evaluation task, we have developed a rule evaluation support method with rule evaluation models that learn from objective indices for mined classification rules and evaluations by a human expert for each rule. In this paper, we present an evaluation of the learning algorithms of our rule evaluation support method for the post-processing of mined patterns with rule evaluation models based on objective indices. To enhance the adaptability of these rule evaluation models, we introduced a constructive meta-learning system for the construction of appropriate learning algorithms. We then have performed case studies using the meningitis as an actual problem. Furthermore, we evaluated our method with the eight rule sets obtained from eight UCI datasets. With regard to these results, we show the applicability of the constrictive meta-learning scheme as a learning algorithm selection method for our rule evaluation support method.

Original languageEnglish
Title of host publicationStudies in Computational Intelligence
Pages95-111
Number of pages17
Volume165
DOIs
Publication statusPublished - 2009

Publication series

NameStudies in Computational Intelligence
Volume165
ISSN (Print)1860949X

Fingerprint

Learning algorithms
Processing
Data mining
Learning systems
Costs

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

Abe, H., Tsumoto, S., Ohsaki, M., & Yamaguchi, T. (2009). Evaluating learning algorithms composed by a constructive meta-learning scheme for a rule evaluation support method. In Studies in Computational Intelligence (Vol. 165, pp. 95-111). (Studies in Computational Intelligence; Vol. 165). https://doi.org/10.1007/978-3-540-88067-7_6

Evaluating learning algorithms composed by a constructive meta-learning scheme for a rule evaluation support method. / Abe, Hidenao; Tsumoto, Shusaku; Ohsaki, Miho; Yamaguchi, Takahira.

Studies in Computational Intelligence. Vol. 165 2009. p. 95-111 (Studies in Computational Intelligence; Vol. 165).

Research output: Chapter in Book/Report/Conference proceedingChapter

Abe, H, Tsumoto, S, Ohsaki, M & Yamaguchi, T 2009, Evaluating learning algorithms composed by a constructive meta-learning scheme for a rule evaluation support method. in Studies in Computational Intelligence. vol. 165, Studies in Computational Intelligence, vol. 165, pp. 95-111. https://doi.org/10.1007/978-3-540-88067-7_6
Abe H, Tsumoto S, Ohsaki M, Yamaguchi T. Evaluating learning algorithms composed by a constructive meta-learning scheme for a rule evaluation support method. In Studies in Computational Intelligence. Vol. 165. 2009. p. 95-111. (Studies in Computational Intelligence). https://doi.org/10.1007/978-3-540-88067-7_6
Abe, Hidenao ; Tsumoto, Shusaku ; Ohsaki, Miho ; Yamaguchi, Takahira. / Evaluating learning algorithms composed by a constructive meta-learning scheme for a rule evaluation support method. Studies in Computational Intelligence. Vol. 165 2009. pp. 95-111 (Studies in Computational Intelligence).
@inbook{aec14ae026dd4c31988925cda5b860f7,
title = "Evaluating learning algorithms composed by a constructive meta-learning scheme for a rule evaluation support method",
abstract = "The Post-processing of mined patterns such as rules, trees and so forth is one of the key operations in a data mining process. However, it is difficult for human experts to completely evaluate several thousand rules from a large dataset with noise. To reduce the cost of this kind of rule evaluation task, we have developed a rule evaluation support method with rule evaluation models that learn from objective indices for mined classification rules and evaluations by a human expert for each rule. In this paper, we present an evaluation of the learning algorithms of our rule evaluation support method for the post-processing of mined patterns with rule evaluation models based on objective indices. To enhance the adaptability of these rule evaluation models, we introduced a constructive meta-learning system for the construction of appropriate learning algorithms. We then have performed case studies using the meningitis as an actual problem. Furthermore, we evaluated our method with the eight rule sets obtained from eight UCI datasets. With regard to these results, we show the applicability of the constrictive meta-learning scheme as a learning algorithm selection method for our rule evaluation support method.",
author = "Hidenao Abe and Shusaku Tsumoto and Miho Ohsaki and Takahira Yamaguchi",
year = "2009",
doi = "10.1007/978-3-540-88067-7_6",
language = "English",
isbn = "9783540880660",
volume = "165",
series = "Studies in Computational Intelligence",
pages = "95--111",
booktitle = "Studies in Computational Intelligence",

}

TY - CHAP

T1 - Evaluating learning algorithms composed by a constructive meta-learning scheme for a rule evaluation support method

AU - Abe, Hidenao

AU - Tsumoto, Shusaku

AU - Ohsaki, Miho

AU - Yamaguchi, Takahira

PY - 2009

Y1 - 2009

N2 - The Post-processing of mined patterns such as rules, trees and so forth is one of the key operations in a data mining process. However, it is difficult for human experts to completely evaluate several thousand rules from a large dataset with noise. To reduce the cost of this kind of rule evaluation task, we have developed a rule evaluation support method with rule evaluation models that learn from objective indices for mined classification rules and evaluations by a human expert for each rule. In this paper, we present an evaluation of the learning algorithms of our rule evaluation support method for the post-processing of mined patterns with rule evaluation models based on objective indices. To enhance the adaptability of these rule evaluation models, we introduced a constructive meta-learning system for the construction of appropriate learning algorithms. We then have performed case studies using the meningitis as an actual problem. Furthermore, we evaluated our method with the eight rule sets obtained from eight UCI datasets. With regard to these results, we show the applicability of the constrictive meta-learning scheme as a learning algorithm selection method for our rule evaluation support method.

AB - The Post-processing of mined patterns such as rules, trees and so forth is one of the key operations in a data mining process. However, it is difficult for human experts to completely evaluate several thousand rules from a large dataset with noise. To reduce the cost of this kind of rule evaluation task, we have developed a rule evaluation support method with rule evaluation models that learn from objective indices for mined classification rules and evaluations by a human expert for each rule. In this paper, we present an evaluation of the learning algorithms of our rule evaluation support method for the post-processing of mined patterns with rule evaluation models based on objective indices. To enhance the adaptability of these rule evaluation models, we introduced a constructive meta-learning system for the construction of appropriate learning algorithms. We then have performed case studies using the meningitis as an actual problem. Furthermore, we evaluated our method with the eight rule sets obtained from eight UCI datasets. With regard to these results, we show the applicability of the constrictive meta-learning scheme as a learning algorithm selection method for our rule evaluation support method.

UR - http://www.scopus.com/inward/record.url?scp=54549125667&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=54549125667&partnerID=8YFLogxK

U2 - 10.1007/978-3-540-88067-7_6

DO - 10.1007/978-3-540-88067-7_6

M3 - Chapter

AN - SCOPUS:54549125667

SN - 9783540880660

VL - 165

T3 - Studies in Computational Intelligence

SP - 95

EP - 111

BT - Studies in Computational Intelligence

ER -