A multi-objective extremal optimisation approach applied to RFID antenna design

Pedro Gomez-Meneses, Marcus Randall, Andrew Lewis

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

4 Citations (Scopus)
67 Downloads (Pure)

Abstract

Extremal Optimisation (EO) is a recent nature-inspired meta-heuristic whose search method is especially suitable to solve combinatorial optimisation problems. This paper presents the implementation of a multi-objective version of EO to solve the real-world Radio Frequency IDentification (RFID) antenna design problem, which must maximise efficiency and minimise resonant frequency. The approach we take produces novel modified meander line antenna designs. Another important contribution of this work is the incorporation of an inseparable fitness evaluation technique to perform the fitness evaluation of the components of solutions. This is due to the use of the NEC evaluation suite, which works as a black box process. When the results are compared with those generated by previous implementations based on Ant Colony Optimisation (ACO) and Differential Evolution (DE), it is evident that our approach is able to obtain competitive results, especially in the generation of antennas with high efficiency. These results indicate that our approach is able to perform well on this problem; however, these results can still be improved, as demonstrated through a manual local search process.

Original languageEnglish
Title of host publicationEvolve: A bridge between probability, set oriented numerics, and evolutionary computation II
Subtitle of host publicationAdvances in intelligent systems and computing
EditorsO Schutze, CAC Coello, AA Tantar, E Tantar, P Bouvry, P DelMoral, P Legrand
PublisherSpringer
Pages431-446
Number of pages16
Volume175 ADVANCES
ISBN (Print)9783642315183
DOIs
Publication statusPublished - 2013
EventEVOLVE 2012 International Conference: A bridge between Probability, Set Oriented Numerics and Evolutionary Computation - Mexico City, Mexico City, Mexico
Duration: 7 Aug 20129 Aug 2012
http://evolve.cinvestav.mx/

Publication series

NameAdvances in Intelligent Systems and Computing
PublisherSPRINGER-VERLAG BERLIN
Volume175
ISSN (Print)2194-5357

Conference

ConferenceEVOLVE 2012 International Conference
CountryMexico
CityMexico City
Period7/08/129/08/12
Internet address

Cite this

Gomez-Meneses, P., Randall, M., & Lewis, A. (2013). A multi-objective extremal optimisation approach applied to RFID antenna design. In O. Schutze, CAC. Coello, AA. Tantar, E. Tantar, P. Bouvry, P. DelMoral, & P. Legrand (Eds.), Evolve: A bridge between probability, set oriented numerics, and evolutionary computation II : Advances in intelligent systems and computing (Vol. 175 ADVANCES, pp. 431-446). (Advances in Intelligent Systems and Computing; Vol. 175). Springer. https://doi.org/10.1007/978-3-642-31519-0_28
Gomez-Meneses, Pedro ; Randall, Marcus ; Lewis, Andrew. / A multi-objective extremal optimisation approach applied to RFID antenna design. Evolve: A bridge between probability, set oriented numerics, and evolutionary computation II : Advances in intelligent systems and computing. editor / O Schutze ; CAC Coello ; AA Tantar ; E Tantar ; P Bouvry ; P DelMoral ; P Legrand. Vol. 175 ADVANCES Springer, 2013. pp. 431-446 (Advances in Intelligent Systems and Computing).
@inproceedings{e927c82e909f47f89ff160d9c9b6f1da,
title = "A multi-objective extremal optimisation approach applied to RFID antenna design",
abstract = "Extremal Optimisation (EO) is a recent nature-inspired meta-heuristic whose search method is especially suitable to solve combinatorial optimisation problems. This paper presents the implementation of a multi-objective version of EO to solve the real-world Radio Frequency IDentification (RFID) antenna design problem, which must maximise efficiency and minimise resonant frequency. The approach we take produces novel modified meander line antenna designs. Another important contribution of this work is the incorporation of an inseparable fitness evaluation technique to perform the fitness evaluation of the components of solutions. This is due to the use of the NEC evaluation suite, which works as a black box process. When the results are compared with those generated by previous implementations based on Ant Colony Optimisation (ACO) and Differential Evolution (DE), it is evident that our approach is able to obtain competitive results, especially in the generation of antennas with high efficiency. These results indicate that our approach is able to perform well on this problem; however, these results can still be improved, as demonstrated through a manual local search process.",
author = "Pedro Gomez-Meneses and Marcus Randall and Andrew Lewis",
year = "2013",
doi = "10.1007/978-3-642-31519-0_28",
language = "English",
isbn = "9783642315183",
volume = "175 ADVANCES",
series = "Advances in Intelligent Systems and Computing",
publisher = "Springer",
pages = "431--446",
editor = "O Schutze and CAC Coello and AA Tantar and E Tantar and P Bouvry and P DelMoral and P Legrand",
booktitle = "Evolve: A bridge between probability, set oriented numerics, and evolutionary computation II",
address = "Germany",

}

Gomez-Meneses, P, Randall, M & Lewis, A 2013, A multi-objective extremal optimisation approach applied to RFID antenna design. in O Schutze, CAC Coello, AA Tantar, E Tantar, P Bouvry, P DelMoral & P Legrand (eds), Evolve: A bridge between probability, set oriented numerics, and evolutionary computation II : Advances in intelligent systems and computing. vol. 175 ADVANCES, Advances in Intelligent Systems and Computing, vol. 175, Springer, pp. 431-446, EVOLVE 2012 International Conference, Mexico City, Mexico, 7/08/12. https://doi.org/10.1007/978-3-642-31519-0_28

A multi-objective extremal optimisation approach applied to RFID antenna design. / Gomez-Meneses, Pedro; Randall, Marcus; Lewis, Andrew.

Evolve: A bridge between probability, set oriented numerics, and evolutionary computation II : Advances in intelligent systems and computing. ed. / O Schutze; CAC Coello; AA Tantar; E Tantar; P Bouvry; P DelMoral; P Legrand. Vol. 175 ADVANCES Springer, 2013. p. 431-446 (Advances in Intelligent Systems and Computing; Vol. 175).

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

TY - GEN

T1 - A multi-objective extremal optimisation approach applied to RFID antenna design

AU - Gomez-Meneses, Pedro

AU - Randall, Marcus

AU - Lewis, Andrew

PY - 2013

Y1 - 2013

N2 - Extremal Optimisation (EO) is a recent nature-inspired meta-heuristic whose search method is especially suitable to solve combinatorial optimisation problems. This paper presents the implementation of a multi-objective version of EO to solve the real-world Radio Frequency IDentification (RFID) antenna design problem, which must maximise efficiency and minimise resonant frequency. The approach we take produces novel modified meander line antenna designs. Another important contribution of this work is the incorporation of an inseparable fitness evaluation technique to perform the fitness evaluation of the components of solutions. This is due to the use of the NEC evaluation suite, which works as a black box process. When the results are compared with those generated by previous implementations based on Ant Colony Optimisation (ACO) and Differential Evolution (DE), it is evident that our approach is able to obtain competitive results, especially in the generation of antennas with high efficiency. These results indicate that our approach is able to perform well on this problem; however, these results can still be improved, as demonstrated through a manual local search process.

AB - Extremal Optimisation (EO) is a recent nature-inspired meta-heuristic whose search method is especially suitable to solve combinatorial optimisation problems. This paper presents the implementation of a multi-objective version of EO to solve the real-world Radio Frequency IDentification (RFID) antenna design problem, which must maximise efficiency and minimise resonant frequency. The approach we take produces novel modified meander line antenna designs. Another important contribution of this work is the incorporation of an inseparable fitness evaluation technique to perform the fitness evaluation of the components of solutions. This is due to the use of the NEC evaluation suite, which works as a black box process. When the results are compared with those generated by previous implementations based on Ant Colony Optimisation (ACO) and Differential Evolution (DE), it is evident that our approach is able to obtain competitive results, especially in the generation of antennas with high efficiency. These results indicate that our approach is able to perform well on this problem; however, these results can still be improved, as demonstrated through a manual local search process.

UR - http://www.scopus.com/inward/record.url?scp=84872555951&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-31519-0_28

DO - 10.1007/978-3-642-31519-0_28

M3 - Conference contribution

SN - 9783642315183

VL - 175 ADVANCES

T3 - Advances in Intelligent Systems and Computing

SP - 431

EP - 446

BT - Evolve: A bridge between probability, set oriented numerics, and evolutionary computation II

A2 - Schutze, O

A2 - Coello, CAC

A2 - Tantar, AA

A2 - Tantar, E

A2 - Bouvry, P

A2 - DelMoral, P

A2 - Legrand, P

PB - Springer

ER -

Gomez-Meneses P, Randall M, Lewis A. A multi-objective extremal optimisation approach applied to RFID antenna design. In Schutze O, Coello CAC, Tantar AA, Tantar E, Bouvry P, DelMoral P, Legrand P, editors, Evolve: A bridge between probability, set oriented numerics, and evolutionary computation II : Advances in intelligent systems and computing. Vol. 175 ADVANCES. Springer. 2013. p. 431-446. (Advances in Intelligent Systems and Computing). https://doi.org/10.1007/978-3-642-31519-0_28