Skip to content

Classifier generalization for comprehensive classifiers subsumption in XCS

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

Standard

Classifier generalization for comprehensive classifiers subsumption in XCS. / Zhang, Caili; Tatsumi, Takato; Sato, Hiyoyuki; Kovacs, Tim; Takadama, Keiki.

GECCO '18: Proceedings of the Genetic and Evolutionary Computation Conference Companion . Association for Computing Machinery (ACM), 2018. p. 1854-1861.

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

Harvard

Zhang, C, Tatsumi, T, Sato, H, Kovacs, T & Takadama, K 2018, Classifier generalization for comprehensive classifiers subsumption in XCS. in GECCO '18: Proceedings of the Genetic and Evolutionary Computation Conference Companion . Association for Computing Machinery (ACM), pp. 1854-1861, 2018 Genetic and Evolutionary Computation Conference, GECCO 2018, Kyoto, Japan, 15/07/18. https://doi.org/10.1145/3205651.3208260

APA

Zhang, C., Tatsumi, T., Sato, H., Kovacs, T., & Takadama, K. (2018). Classifier generalization for comprehensive classifiers subsumption in XCS. In GECCO '18: Proceedings of the Genetic and Evolutionary Computation Conference Companion (pp. 1854-1861). Association for Computing Machinery (ACM). https://doi.org/10.1145/3205651.3208260

Vancouver

Zhang C, Tatsumi T, Sato H, Kovacs T, Takadama K. Classifier generalization for comprehensive classifiers subsumption in XCS. In GECCO '18: Proceedings of the Genetic and Evolutionary Computation Conference Companion . Association for Computing Machinery (ACM). 2018. p. 1854-1861 https://doi.org/10.1145/3205651.3208260

Author

Zhang, Caili ; Tatsumi, Takato ; Sato, Hiyoyuki ; Kovacs, Tim ; Takadama, Keiki. / Classifier generalization for comprehensive classifiers subsumption in XCS. GECCO '18: Proceedings of the Genetic and Evolutionary Computation Conference Companion . Association for Computing Machinery (ACM), 2018. pp. 1854-1861

Bibtex

@inproceedings{c169e8005b5d4e67ad350efc91178a88,
title = "Classifier generalization for comprehensive classifiers subsumption in XCS",
abstract = "We proposed XCS-VRc3 that can extract useful rules (classifiers) from data and verify its effectiveness. The difficulty of mining real world data is that not only the type of the input state but also the number of instances varies. Although conventional method XCS-VRc is able to extract classifiers, the generalization of classifiers was insufficient and lack of human readability. The proposed XCS-VRc3 incorporating {"}generalization mechanism by comprehensive classifier subsumption{"} to solves this problem. Specifically, (1) All classifiers of the matching set subsume other classifiers, (2) Abolition of the inappropriate classifier deletion introduced by XCS-VRc (3) Preferentially select classifier with small variance of output in genetic algorithm. To verify the effectiveness of XCS-VRc3, we applied on care plan planning problem in a nursing home (in this case, identifying daytime behavior contributing to increase the ratio of deep sleep time). Comparing the association rules obtained by Apriori, and classifiers obtained by XCS-VRc3, the followings was found. First, abolishing the inappropriate classifier deletion and comprehensively subsuming promotes various degrees of generalization. Second, parent selection mechanism can obtain classifiers with small output variance. Finally, XCS-VRc3 is able to extract a small number classifiers equivalent to large number of rules found in Apriori.",
keywords = "Data mining, LCS, XCS",
author = "Caili Zhang and Takato Tatsumi and Hiyoyuki Sato and Tim Kovacs and Keiki Takadama",
year = "2018",
month = "7",
day = "6",
doi = "10.1145/3205651.3208260",
language = "English",
pages = "1854--1861",
booktitle = "GECCO '18: Proceedings of the Genetic and Evolutionary Computation Conference Companion",
publisher = "Association for Computing Machinery (ACM)",
address = "United States",

}

RIS - suitable for import to EndNote

TY - GEN

T1 - Classifier generalization for comprehensive classifiers subsumption in XCS

AU - Zhang, Caili

AU - Tatsumi, Takato

AU - Sato, Hiyoyuki

AU - Kovacs, Tim

AU - Takadama, Keiki

PY - 2018/7/6

Y1 - 2018/7/6

N2 - We proposed XCS-VRc3 that can extract useful rules (classifiers) from data and verify its effectiveness. The difficulty of mining real world data is that not only the type of the input state but also the number of instances varies. Although conventional method XCS-VRc is able to extract classifiers, the generalization of classifiers was insufficient and lack of human readability. The proposed XCS-VRc3 incorporating "generalization mechanism by comprehensive classifier subsumption" to solves this problem. Specifically, (1) All classifiers of the matching set subsume other classifiers, (2) Abolition of the inappropriate classifier deletion introduced by XCS-VRc (3) Preferentially select classifier with small variance of output in genetic algorithm. To verify the effectiveness of XCS-VRc3, we applied on care plan planning problem in a nursing home (in this case, identifying daytime behavior contributing to increase the ratio of deep sleep time). Comparing the association rules obtained by Apriori, and classifiers obtained by XCS-VRc3, the followings was found. First, abolishing the inappropriate classifier deletion and comprehensively subsuming promotes various degrees of generalization. Second, parent selection mechanism can obtain classifiers with small output variance. Finally, XCS-VRc3 is able to extract a small number classifiers equivalent to large number of rules found in Apriori.

AB - We proposed XCS-VRc3 that can extract useful rules (classifiers) from data and verify its effectiveness. The difficulty of mining real world data is that not only the type of the input state but also the number of instances varies. Although conventional method XCS-VRc is able to extract classifiers, the generalization of classifiers was insufficient and lack of human readability. The proposed XCS-VRc3 incorporating "generalization mechanism by comprehensive classifier subsumption" to solves this problem. Specifically, (1) All classifiers of the matching set subsume other classifiers, (2) Abolition of the inappropriate classifier deletion introduced by XCS-VRc (3) Preferentially select classifier with small variance of output in genetic algorithm. To verify the effectiveness of XCS-VRc3, we applied on care plan planning problem in a nursing home (in this case, identifying daytime behavior contributing to increase the ratio of deep sleep time). Comparing the association rules obtained by Apriori, and classifiers obtained by XCS-VRc3, the followings was found. First, abolishing the inappropriate classifier deletion and comprehensively subsuming promotes various degrees of generalization. Second, parent selection mechanism can obtain classifiers with small output variance. Finally, XCS-VRc3 is able to extract a small number classifiers equivalent to large number of rules found in Apriori.

KW - Data mining

KW - LCS

KW - XCS

UR - http://www.scopus.com/inward/record.url?scp=85051491492&partnerID=8YFLogxK

U2 - 10.1145/3205651.3208260

DO - 10.1145/3205651.3208260

M3 - Conference contribution

SP - 1854

EP - 1861

BT - GECCO '18: Proceedings of the Genetic and Evolutionary Computation Conference Companion

PB - Association for Computing Machinery (ACM)

ER -