Analysis of various interestingness measures in classification rule mining for traffic prediction

Xianneng Li, Shingo Mabu, Huiyu Zhou, Kaoru Shimada, Kotaro Hirasawa

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Recently, an evolutionary algorithm named Genetic Network Programming with Estimation of Distribution Algorithm (GNP-EDA) has been proposed and applied to extract classification rules for solving traffic prediction problems. The measures such as the support, confidence and χ2 value are adopted to evaluate the interestingness of a large number of rules extracted from traffic databases in the above data mining method. In data mining, many other measures have been proposed to evaluate the interestingness of association patterns. These measures usually provide different and conflicting results. Many studies investigate that the effects of different measures depend on the concrete applications. We rarely know what measures are the appropriate ones for the traffic prediction application. Therefore, a novel approach to select the right measure for the classification rule mining has been proposed in this paper. The simulation results show that the proposed interestingness measure selection approach is a powerful tool to select the right measure for the traffic prediction application, leading to the increase of the classification accuracy.

Original languageEnglish
Title of host publicationProceedings of the SICE Annual Conference
Pages1969-1974
Number of pages6
Publication statusPublished - 2010
EventSICE Annual Conference 2010, SICE 2010 - Taipei
Duration: 2010 Aug 182010 Aug 21

Other

OtherSICE Annual Conference 2010, SICE 2010
CityTaipei
Period10/8/1810/8/21

Fingerprint

Data mining
Evolutionary algorithms
Concretes

Keywords

  • Classification rule mining
  • Estimation of distribution algorithm
  • Genetic network programming
  • Interestingness measure
  • Traffic prediction

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Control and Systems Engineering
  • Computer Science Applications

Cite this

Li, X., Mabu, S., Zhou, H., Shimada, K., & Hirasawa, K. (2010). Analysis of various interestingness measures in classification rule mining for traffic prediction. In Proceedings of the SICE Annual Conference (pp. 1969-1974). [5602741]

Analysis of various interestingness measures in classification rule mining for traffic prediction. / Li, Xianneng; Mabu, Shingo; Zhou, Huiyu; Shimada, Kaoru; Hirasawa, Kotaro.

Proceedings of the SICE Annual Conference. 2010. p. 1969-1974 5602741.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Li, X, Mabu, S, Zhou, H, Shimada, K & Hirasawa, K 2010, Analysis of various interestingness measures in classification rule mining for traffic prediction. in Proceedings of the SICE Annual Conference., 5602741, pp. 1969-1974, SICE Annual Conference 2010, SICE 2010, Taipei, 10/8/18.
Li X, Mabu S, Zhou H, Shimada K, Hirasawa K. Analysis of various interestingness measures in classification rule mining for traffic prediction. In Proceedings of the SICE Annual Conference. 2010. p. 1969-1974. 5602741
Li, Xianneng ; Mabu, Shingo ; Zhou, Huiyu ; Shimada, Kaoru ; Hirasawa, Kotaro. / Analysis of various interestingness measures in classification rule mining for traffic prediction. Proceedings of the SICE Annual Conference. 2010. pp. 1969-1974
@inproceedings{69df0777d9d144d4a2c5ff2aa00fea8a,
title = "Analysis of various interestingness measures in classification rule mining for traffic prediction",
abstract = "Recently, an evolutionary algorithm named Genetic Network Programming with Estimation of Distribution Algorithm (GNP-EDA) has been proposed and applied to extract classification rules for solving traffic prediction problems. The measures such as the support, confidence and χ2 value are adopted to evaluate the interestingness of a large number of rules extracted from traffic databases in the above data mining method. In data mining, many other measures have been proposed to evaluate the interestingness of association patterns. These measures usually provide different and conflicting results. Many studies investigate that the effects of different measures depend on the concrete applications. We rarely know what measures are the appropriate ones for the traffic prediction application. Therefore, a novel approach to select the right measure for the classification rule mining has been proposed in this paper. The simulation results show that the proposed interestingness measure selection approach is a powerful tool to select the right measure for the traffic prediction application, leading to the increase of the classification accuracy.",
keywords = "Classification rule mining, Estimation of distribution algorithm, Genetic network programming, Interestingness measure, Traffic prediction",
author = "Xianneng Li and Shingo Mabu and Huiyu Zhou and Kaoru Shimada and Kotaro Hirasawa",
year = "2010",
language = "English",
isbn = "9784907764364",
pages = "1969--1974",
booktitle = "Proceedings of the SICE Annual Conference",

}

TY - GEN

T1 - Analysis of various interestingness measures in classification rule mining for traffic prediction

AU - Li, Xianneng

AU - Mabu, Shingo

AU - Zhou, Huiyu

AU - Shimada, Kaoru

AU - Hirasawa, Kotaro

PY - 2010

Y1 - 2010

N2 - Recently, an evolutionary algorithm named Genetic Network Programming with Estimation of Distribution Algorithm (GNP-EDA) has been proposed and applied to extract classification rules for solving traffic prediction problems. The measures such as the support, confidence and χ2 value are adopted to evaluate the interestingness of a large number of rules extracted from traffic databases in the above data mining method. In data mining, many other measures have been proposed to evaluate the interestingness of association patterns. These measures usually provide different and conflicting results. Many studies investigate that the effects of different measures depend on the concrete applications. We rarely know what measures are the appropriate ones for the traffic prediction application. Therefore, a novel approach to select the right measure for the classification rule mining has been proposed in this paper. The simulation results show that the proposed interestingness measure selection approach is a powerful tool to select the right measure for the traffic prediction application, leading to the increase of the classification accuracy.

AB - Recently, an evolutionary algorithm named Genetic Network Programming with Estimation of Distribution Algorithm (GNP-EDA) has been proposed and applied to extract classification rules for solving traffic prediction problems. The measures such as the support, confidence and χ2 value are adopted to evaluate the interestingness of a large number of rules extracted from traffic databases in the above data mining method. In data mining, many other measures have been proposed to evaluate the interestingness of association patterns. These measures usually provide different and conflicting results. Many studies investigate that the effects of different measures depend on the concrete applications. We rarely know what measures are the appropriate ones for the traffic prediction application. Therefore, a novel approach to select the right measure for the classification rule mining has been proposed in this paper. The simulation results show that the proposed interestingness measure selection approach is a powerful tool to select the right measure for the traffic prediction application, leading to the increase of the classification accuracy.

KW - Classification rule mining

KW - Estimation of distribution algorithm

KW - Genetic network programming

KW - Interestingness measure

KW - Traffic prediction

UR - http://www.scopus.com/inward/record.url?scp=78649288966&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78649288966&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:78649288966

SN - 9784907764364

SP - 1969

EP - 1974

BT - Proceedings of the SICE Annual Conference

ER -