R2-BEAN: R2 indicator based evolutionary algorithm for noisy multiobjective optimization

Dung H. Phan; Junichi Suzuki

doi:10.1109/CISDA.2014.7035637

R2-BEAN: R2 indicator based evolutionary algorithm for noisy multiobjective optimization

Dung H. Phan
, Junichi Suzuki

Computer Science

University of Massachusetts Boston

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This paper proposes and evaluates an indicator-based and noise-aware dominance operator for evolutionary algorithms to solve the multiobjective optimization problems (MOPs) that contain noise in their objective functions. The proposed operator, U_R2-dominance operator is designed with (1) a quality indicator, called R2 indicator, which quantifies the goodness of a given solution candidate (individual) and (2) a non-parametric (i.e., distribution-free) statistical significance test called the Mann-Whitney U-test. The U_R2-dominance operator takes samples of given two individuals in the objective space, calculates the R2 indicator value for each sample, estimates the impacts of noise on the R2 values with a U-test, and determines which individual is statistically superior/inferior. Experimental results show that it operates reliably in noisy MOPs and outperforms existing noise-aware dominance operators particularly when many outliers exist under asymmetric noise distributions.

Original language	English
Title of host publication	Proceedings of the 2014 7th IEEE Symposium on Computational Intelligence for Security and Defense Applications, CISDA 2014
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781479954315
DOIs	https://doi.org/10.1109/CISDA.2014.7035637
State	Published - Feb 6 2015
Event	7th IEEE Symposium on Computational Intelligence for Security and Defense Applications, CISDA 2014 - Hanoi, Viet Nam Duration: Dec 14 2014 → Dec 17 2014

Publication series

Name	Proceedings of the 2014 7th IEEE Symposium on Computational Intelligence for Security and Defense Applications, CISDA 2014

Conference

Conference	7th IEEE Symposium on Computational Intelligence for Security and Defense Applications, CISDA 2014
Country/Territory	Viet Nam
City	Hanoi
Period	12/14/14 → 12/17/14

ASJC Scopus Subject Areas

Artificial Intelligence
Computational Theory and Mathematics
Computer Science Applications
Safety, Risk, Reliability and Quality

Access to Document

10.1109/CISDA.2014.7035637

Cite this

Phan, D. H., & Suzuki, J. (2015). R2-BEAN: R2 indicator based evolutionary algorithm for noisy multiobjective optimization. In Proceedings of the 2014 7th IEEE Symposium on Computational Intelligence for Security and Defense Applications, CISDA 2014 Article 7035637 (Proceedings of the 2014 7th IEEE Symposium on Computational Intelligence for Security and Defense Applications, CISDA 2014). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CISDA.2014.7035637

R2-BEAN: R2 indicator based evolutionary algorithm for noisy multiobjective optimization. / Phan, Dung H.; Suzuki, Junichi.
Proceedings of the 2014 7th IEEE Symposium on Computational Intelligence for Security and Defense Applications, CISDA 2014. Institute of Electrical and Electronics Engineers Inc., 2015. 7035637 (Proceedings of the 2014 7th IEEE Symposium on Computational Intelligence for Security and Defense Applications, CISDA 2014).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Phan, DH & Suzuki, J 2015, R2-BEAN: R2 indicator based evolutionary algorithm for noisy multiobjective optimization. in Proceedings of the 2014 7th IEEE Symposium on Computational Intelligence for Security and Defense Applications, CISDA 2014., 7035637, Proceedings of the 2014 7th IEEE Symposium on Computational Intelligence for Security and Defense Applications, CISDA 2014, Institute of Electrical and Electronics Engineers Inc., 7th IEEE Symposium on Computational Intelligence for Security and Defense Applications, CISDA 2014, Hanoi, Viet Nam, 12/14/14. https://doi.org/10.1109/CISDA.2014.7035637

Phan DH, Suzuki J. R2-BEAN: R2 indicator based evolutionary algorithm for noisy multiobjective optimization. In Proceedings of the 2014 7th IEEE Symposium on Computational Intelligence for Security and Defense Applications, CISDA 2014. Institute of Electrical and Electronics Engineers Inc. 2015. 7035637. (Proceedings of the 2014 7th IEEE Symposium on Computational Intelligence for Security and Defense Applications, CISDA 2014). doi: 10.1109/CISDA.2014.7035637

Phan, Dung H. ; Suzuki, Junichi. / R2-BEAN : R2 indicator based evolutionary algorithm for noisy multiobjective optimization. Proceedings of the 2014 7th IEEE Symposium on Computational Intelligence for Security and Defense Applications, CISDA 2014. Institute of Electrical and Electronics Engineers Inc., 2015. (Proceedings of the 2014 7th IEEE Symposium on Computational Intelligence for Security and Defense Applications, CISDA 2014).

@inproceedings{0ab0ccc1569748fba19f593b4fe0d2c3,

title = "R2-BEAN: R2 indicator based evolutionary algorithm for noisy multiobjective optimization",

abstract = "This paper proposes and evaluates an indicator-based and noise-aware dominance operator for evolutionary algorithms to solve the multiobjective optimization problems (MOPs) that contain noise in their objective functions. The proposed operator, UR2-dominance operator is designed with (1) a quality indicator, called R2 indicator, which quantifies the goodness of a given solution candidate (individual) and (2) a non-parametric (i.e., distribution-free) statistical significance test called the Mann-Whitney U-test. The UR2-dominance operator takes samples of given two individuals in the objective space, calculates the R2 indicator value for each sample, estimates the impacts of noise on the R2 values with a U-test, and determines which individual is statistically superior/inferior. Experimental results show that it operates reliably in noisy MOPs and outperforms existing noise-aware dominance operators particularly when many outliers exist under asymmetric noise distributions.",

author = "Phan, \{Dung H.\} and Junichi Suzuki",

note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 7th IEEE Symposium on Computational Intelligence for Security and Defense Applications, CISDA 2014 ; Conference date: 14-12-2014 Through 17-12-2014",

year = "2015",

month = feb,

day = "6",

doi = "10.1109/CISDA.2014.7035637",

language = "English",

series = "Proceedings of the 2014 7th IEEE Symposium on Computational Intelligence for Security and Defense Applications, CISDA 2014",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "Proceedings of the 2014 7th IEEE Symposium on Computational Intelligence for Security and Defense Applications, CISDA 2014",

}

TY - GEN

T1 - R2-BEAN

T2 - 7th IEEE Symposium on Computational Intelligence for Security and Defense Applications, CISDA 2014

AU - Phan, Dung H.

AU - Suzuki, Junichi

PY - 2015/2/6

Y1 - 2015/2/6

N2 - This paper proposes and evaluates an indicator-based and noise-aware dominance operator for evolutionary algorithms to solve the multiobjective optimization problems (MOPs) that contain noise in their objective functions. The proposed operator, UR2-dominance operator is designed with (1) a quality indicator, called R2 indicator, which quantifies the goodness of a given solution candidate (individual) and (2) a non-parametric (i.e., distribution-free) statistical significance test called the Mann-Whitney U-test. The UR2-dominance operator takes samples of given two individuals in the objective space, calculates the R2 indicator value for each sample, estimates the impacts of noise on the R2 values with a U-test, and determines which individual is statistically superior/inferior. Experimental results show that it operates reliably in noisy MOPs and outperforms existing noise-aware dominance operators particularly when many outliers exist under asymmetric noise distributions.

AB - This paper proposes and evaluates an indicator-based and noise-aware dominance operator for evolutionary algorithms to solve the multiobjective optimization problems (MOPs) that contain noise in their objective functions. The proposed operator, UR2-dominance operator is designed with (1) a quality indicator, called R2 indicator, which quantifies the goodness of a given solution candidate (individual) and (2) a non-parametric (i.e., distribution-free) statistical significance test called the Mann-Whitney U-test. The UR2-dominance operator takes samples of given two individuals in the objective space, calculates the R2 indicator value for each sample, estimates the impacts of noise on the R2 values with a U-test, and determines which individual is statistically superior/inferior. Experimental results show that it operates reliably in noisy MOPs and outperforms existing noise-aware dominance operators particularly when many outliers exist under asymmetric noise distributions.

UR - https://www.scopus.com/pages/publications/84924322804

UR - https://www.scopus.com/pages/publications/84924322804#tab=citedBy

U2 - 10.1109/CISDA.2014.7035637

DO - 10.1109/CISDA.2014.7035637

M3 - Conference contribution

AN - SCOPUS:84924322804

T3 - Proceedings of the 2014 7th IEEE Symposium on Computational Intelligence for Security and Defense Applications, CISDA 2014

BT - Proceedings of the 2014 7th IEEE Symposium on Computational Intelligence for Security and Defense Applications, CISDA 2014

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 14 December 2014 through 17 December 2014

ER -

R2-BEAN: R2 indicator based evolutionary algorithm for noisy multiobjective optimization

Abstract

Publication series

Conference

ASJC Scopus Subject Areas

Access to Document

Other files and links

Fingerprint

Cite this