A two-phase evolutionary algorithm for multiobjective mining of classification rules

Yung Hsiang Chan; Tsung Che Chiang; Li Chen Fu

doi:10.1109/CEC.2010.5586523

A two-phase evolutionary algorithm for multiobjective mining of classification rules

Yung Hsiang Chan^*, Tsung Che Chiang, Li Chen Fu

^*此作品的通信作者

研究成果: 書貢獻/報告類型 › 會議論文篇章

20 引文斯高帕斯（Scopus）

摘要

Classification rule mining, addressed a lot in machine learning and statistics communities, is an important task to extract knowledge from data. Most existing approaches do not particularly deal with data instances matched by more than one rule, which results in restricted performance. We present a two-phase multiobjective evolutionary algorithm which first aims at searching decent rules and then takes the rule interaction into account to produce the final rule sets. The algorithm incorporates the concept of Pareto dominance to deal with trade-off relations in both phases. Through computational experiments, the proposed algorithm shows competitive to the state-of-the-art. We also study the effect of a niching mechanism.

原文	英語
主出版物標題	2010 IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 IEEE Congress on Evolutionary Computation, CEC 2010
DOIs	https://doi.org/10.1109/CEC.2010.5586523
出版狀態	已發佈 - 2010
對外發佈	是
事件	2010 6th IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 IEEE Congress on Evolutionary Computation, CEC 2010 - Barcelona, 西班牙持續時間: 2010 7月 18 → 2010 7月 23

出版系列

名字	2010 IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 IEEE Congress on Evolutionary Computation, CEC 2010

其他

其他	2010 6th IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 IEEE Congress on Evolutionary Computation, CEC 2010
國家/地區	西班牙
城市	Barcelona
期間	2010/07/18 → 2010/07/23

ASJC Scopus subject areas

計算機理論與數學
應用數學

存取文件

10.1109/CEC.2010.5586523

其它文件與鏈接

引用此

Chan, Y. H., Chiang, T. C., & Fu, L. C. (2010). A two-phase evolutionary algorithm for multiobjective mining of classification rules. 於 2010 IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 IEEE Congress on Evolutionary Computation, CEC 2010 文章 5586523 (2010 IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 IEEE Congress on Evolutionary Computation, CEC 2010). https://doi.org/10.1109/CEC.2010.5586523

A two-phase evolutionary algorithm for multiobjective mining of classification rules. / Chan, Yung Hsiang; Chiang, Tsung Che; Fu, Li Chen.
2010 IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 IEEE Congress on Evolutionary Computation, CEC 2010. 2010. 5586523 (2010 IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 IEEE Congress on Evolutionary Computation, CEC 2010).

研究成果: 書貢獻/報告類型 › 會議論文篇章

Chan, YH, Chiang, TC & Fu, LC 2010, A two-phase evolutionary algorithm for multiobjective mining of classification rules. 於 2010 IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 IEEE Congress on Evolutionary Computation, CEC 2010., 5586523, 2010 IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 IEEE Congress on Evolutionary Computation, CEC 2010, 2010 6th IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 IEEE Congress on Evolutionary Computation, CEC 2010, Barcelona, 西班牙, 2010/07/18. https://doi.org/10.1109/CEC.2010.5586523

Chan YH, Chiang TC, Fu LC. A two-phase evolutionary algorithm for multiobjective mining of classification rules. 於 2010 IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 IEEE Congress on Evolutionary Computation, CEC 2010. 2010. 5586523. (2010 IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 IEEE Congress on Evolutionary Computation, CEC 2010). doi: 10.1109/CEC.2010.5586523

Chan, Yung Hsiang ; Chiang, Tsung Che ; Fu, Li Chen. / A two-phase evolutionary algorithm for multiobjective mining of classification rules. 2010 IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 IEEE Congress on Evolutionary Computation, CEC 2010. 2010. (2010 IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 IEEE Congress on Evolutionary Computation, CEC 2010).

@inproceedings{b8d8c6e024b74b47867e64009ccc2c9f,

title = "A two-phase evolutionary algorithm for multiobjective mining of classification rules",

abstract = "Classification rule mining, addressed a lot in machine learning and statistics communities, is an important task to extract knowledge from data. Most existing approaches do not particularly deal with data instances matched by more than one rule, which results in restricted performance. We present a two-phase multiobjective evolutionary algorithm which first aims at searching decent rules and then takes the rule interaction into account to produce the final rule sets. The algorithm incorporates the concept of Pareto dominance to deal with trade-off relations in both phases. Through computational experiments, the proposed algorithm shows competitive to the state-of-the-art. We also study the effect of a niching mechanism.",

author = "Chan, {Yung Hsiang} and Chiang, {Tsung Che} and Fu, {Li Chen}",

year = "2010",

doi = "10.1109/CEC.2010.5586523",

language = "English",

isbn = "9781424469109",

series = "2010 IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 IEEE Congress on Evolutionary Computation, CEC 2010",

booktitle = "2010 IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 IEEE Congress on Evolutionary Computation, CEC 2010",

note = "2010 6th IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 IEEE Congress on Evolutionary Computation, CEC 2010 ; Conference date: 18-07-2010 Through 23-07-2010",

}

TY - GEN

T1 - A two-phase evolutionary algorithm for multiobjective mining of classification rules

AU - Chan, Yung Hsiang

AU - Chiang, Tsung Che

AU - Fu, Li Chen

PY - 2010

Y1 - 2010

N2 - Classification rule mining, addressed a lot in machine learning and statistics communities, is an important task to extract knowledge from data. Most existing approaches do not particularly deal with data instances matched by more than one rule, which results in restricted performance. We present a two-phase multiobjective evolutionary algorithm which first aims at searching decent rules and then takes the rule interaction into account to produce the final rule sets. The algorithm incorporates the concept of Pareto dominance to deal with trade-off relations in both phases. Through computational experiments, the proposed algorithm shows competitive to the state-of-the-art. We also study the effect of a niching mechanism.

AB - Classification rule mining, addressed a lot in machine learning and statistics communities, is an important task to extract knowledge from data. Most existing approaches do not particularly deal with data instances matched by more than one rule, which results in restricted performance. We present a two-phase multiobjective evolutionary algorithm which first aims at searching decent rules and then takes the rule interaction into account to produce the final rule sets. The algorithm incorporates the concept of Pareto dominance to deal with trade-off relations in both phases. Through computational experiments, the proposed algorithm shows competitive to the state-of-the-art. We also study the effect of a niching mechanism.

UR - http://www.scopus.com/inward/record.url?scp=79959480959&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79959480959&partnerID=8YFLogxK

U2 - 10.1109/CEC.2010.5586523

DO - 10.1109/CEC.2010.5586523

M3 - Conference contribution

AN - SCOPUS:79959480959

SN - 9781424469109

T3 - 2010 IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 IEEE Congress on Evolutionary Computation, CEC 2010

BT - 2010 IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 IEEE Congress on Evolutionary Computation, CEC 2010

T2 - 2010 6th IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 IEEE Congress on Evolutionary Computation, CEC 2010

Y2 - 18 July 2010 through 23 July 2010

ER -

A two-phase evolutionary algorithm for multiobjective mining of classification rules

摘要

出版系列

其他

ASJC Scopus subject areas

存取文件

其它文件與鏈接

指紋

引用此