Evaluating learning models with transitions of human interests based on objective rule evaluation indices.

Hidenao Abe, Hideto Yokoi, Shusaku Tsumoto, Miho Ohsaki, Takahira Yamaguchi

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

This paper presents a method to support the evaluation procedure of a data mining process using human-system interaction. The post-processing of mined results is one of the key factors for successful data mining process. However, it is difficult for human experts to completely evaluate several thousands of rules from a large dataset containing noise. We have designed a method based on objective rule evaluation indices to support the rule evaluation procedure; the indices are calculated to evaluate each if-then rule mathematically. We have evaluated five representative learning algorithms to construct rule evaluation models of the actual data mining results from a chronic hepatitis data set. Further, we discuss the relationship between the transitions of the subjective criterion of a medical expert and the performances of the rule evaluation models.

Original languageEnglish
Title of host publicationMedinfo. MEDINFO
Pages581-585
Number of pages5
Volume12
EditionPt 1
Publication statusPublished - 2007

Fingerprint

Learning
Data Mining
Chronic Hepatitis
Noise
Datasets

ASJC Scopus subject areas

  • Medicine(all)

Cite this

Abe, H., Yokoi, H., Tsumoto, S., Ohsaki, M., & Yamaguchi, T. (2007). Evaluating learning models with transitions of human interests based on objective rule evaluation indices. In Medinfo. MEDINFO (Pt 1 ed., Vol. 12, pp. 581-585)

Evaluating learning models with transitions of human interests based on objective rule evaluation indices. / Abe, Hidenao; Yokoi, Hideto; Tsumoto, Shusaku; Ohsaki, Miho; Yamaguchi, Takahira.

Medinfo. MEDINFO. Vol. 12 Pt 1. ed. 2007. p. 581-585.

Research output: Chapter in Book/Report/Conference proceedingChapter

Abe, H, Yokoi, H, Tsumoto, S, Ohsaki, M & Yamaguchi, T 2007, Evaluating learning models with transitions of human interests based on objective rule evaluation indices. in Medinfo. MEDINFO. Pt 1 edn, vol. 12, pp. 581-585.
Abe H, Yokoi H, Tsumoto S, Ohsaki M, Yamaguchi T. Evaluating learning models with transitions of human interests based on objective rule evaluation indices. In Medinfo. MEDINFO. Pt 1 ed. Vol. 12. 2007. p. 581-585
Abe, Hidenao ; Yokoi, Hideto ; Tsumoto, Shusaku ; Ohsaki, Miho ; Yamaguchi, Takahira. / Evaluating learning models with transitions of human interests based on objective rule evaluation indices. Medinfo. MEDINFO. Vol. 12 Pt 1. ed. 2007. pp. 581-585
@inbook{6b2adf43bc294a2abbfc79437956b0f8,
title = "Evaluating learning models with transitions of human interests based on objective rule evaluation indices.",
abstract = "This paper presents a method to support the evaluation procedure of a data mining process using human-system interaction. The post-processing of mined results is one of the key factors for successful data mining process. However, it is difficult for human experts to completely evaluate several thousands of rules from a large dataset containing noise. We have designed a method based on objective rule evaluation indices to support the rule evaluation procedure; the indices are calculated to evaluate each if-then rule mathematically. We have evaluated five representative learning algorithms to construct rule evaluation models of the actual data mining results from a chronic hepatitis data set. Further, we discuss the relationship between the transitions of the subjective criterion of a medical expert and the performances of the rule evaluation models.",
author = "Hidenao Abe and Hideto Yokoi and Shusaku Tsumoto and Miho Ohsaki and Takahira Yamaguchi",
year = "2007",
language = "English",
volume = "12",
pages = "581--585",
booktitle = "Medinfo. MEDINFO",
edition = "Pt 1",

}

TY - CHAP

T1 - Evaluating learning models with transitions of human interests based on objective rule evaluation indices.

AU - Abe, Hidenao

AU - Yokoi, Hideto

AU - Tsumoto, Shusaku

AU - Ohsaki, Miho

AU - Yamaguchi, Takahira

PY - 2007

Y1 - 2007

N2 - This paper presents a method to support the evaluation procedure of a data mining process using human-system interaction. The post-processing of mined results is one of the key factors for successful data mining process. However, it is difficult for human experts to completely evaluate several thousands of rules from a large dataset containing noise. We have designed a method based on objective rule evaluation indices to support the rule evaluation procedure; the indices are calculated to evaluate each if-then rule mathematically. We have evaluated five representative learning algorithms to construct rule evaluation models of the actual data mining results from a chronic hepatitis data set. Further, we discuss the relationship between the transitions of the subjective criterion of a medical expert and the performances of the rule evaluation models.

AB - This paper presents a method to support the evaluation procedure of a data mining process using human-system interaction. The post-processing of mined results is one of the key factors for successful data mining process. However, it is difficult for human experts to completely evaluate several thousands of rules from a large dataset containing noise. We have designed a method based on objective rule evaluation indices to support the rule evaluation procedure; the indices are calculated to evaluate each if-then rule mathematically. We have evaluated five representative learning algorithms to construct rule evaluation models of the actual data mining results from a chronic hepatitis data set. Further, we discuss the relationship between the transitions of the subjective criterion of a medical expert and the performances of the rule evaluation models.

UR - http://www.scopus.com/inward/record.url?scp=38449101902&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=38449101902&partnerID=8YFLogxK

M3 - Chapter

C2 - 17911783

AN - SCOPUS:38449101902

VL - 12

SP - 581

EP - 585

BT - Medinfo. MEDINFO

ER -