Feasibility of Genetic Algorithms in 2D Ultrasound Array Optimization

Bakary Diarra, Ravi Samikannu, Didier Vray, Christian Cachard, Joseph Chuma, Abid Yahya, Herve Liebgott

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

Abstract

The optimization of 2D ultrasound arrays can be efficiently realized through the use of simulated annealing (SA) as reported in many recent works. The main limitation of SA resides in the amount of resources required and the optimization time. In this work, the application of the genetic algorithms (GA) in 2D arrays optimization is presented to evaluate the potential of these algorithms compared to the simulated annealing in terms of processing time and output beam profiles. GA have been used in the optimization of multivariable cost functions in many applications as power systems analysis, wireless sensor arrays in telecommunication and they provided satisfactory results in a relative short time. The 2D ultrasound arrays optimization can also be formulated in a similar way as the problems occurring in these domains, making genetic algorithms a potential candidate to solve them. Although GA are reported to not be as efficient as SA in the optimization of medium and large 2D arrays, the aim of this paper is to evaluate their real ability when compared to the SA. Preliminary results showed a fast convergence time of genetic algorithm for comparable acoustical properties for the optimized arrays compared to SA.

Original languageEnglish
Title of host publication2018 IEEE International Ultrasonics Symposium, IUS 2018
PublisherIEEE Computer Society
ISBN (Electronic)9781538634257
DOIs
Publication statusPublished - Dec 17 2018
Externally publishedYes
Event2018 IEEE International Ultrasonics Symposium, IUS 2018 - Kobe, Japan
Duration: Oct 22 2018Oct 25 2018

Publication series

NameIEEE International Ultrasonics Symposium, IUS
Volume2018-October
ISSN (Print)1948-5719
ISSN (Electronic)1948-5727

Conference

Conference2018 IEEE International Ultrasonics Symposium, IUS 2018
CountryJapan
CityKobe
Period10/22/1810/25/18

Fingerprint

simulated annealing
genetic algorithms
optimization
systems analysis
telecommunication
resources
costs
output
sensors
profiles

All Science Journal Classification (ASJC) codes

  • Acoustics and Ultrasonics

Cite this

Diarra, B., Samikannu, R., Vray, D., Cachard, C., Chuma, J., Yahya, A., & Liebgott, H. (2018). Feasibility of Genetic Algorithms in 2D Ultrasound Array Optimization. In 2018 IEEE International Ultrasonics Symposium, IUS 2018 [8579952] (IEEE International Ultrasonics Symposium, IUS; Vol. 2018-October). IEEE Computer Society. https://doi.org/10.1109/ULTSYM.2018.8579952
Diarra, Bakary ; Samikannu, Ravi ; Vray, Didier ; Cachard, Christian ; Chuma, Joseph ; Yahya, Abid ; Liebgott, Herve. / Feasibility of Genetic Algorithms in 2D Ultrasound Array Optimization. 2018 IEEE International Ultrasonics Symposium, IUS 2018. IEEE Computer Society, 2018. (IEEE International Ultrasonics Symposium, IUS).
@inproceedings{0d2ae47b69f04561ab6e2e801dac9ddb,
title = "Feasibility of Genetic Algorithms in 2D Ultrasound Array Optimization",
abstract = "The optimization of 2D ultrasound arrays can be efficiently realized through the use of simulated annealing (SA) as reported in many recent works. The main limitation of SA resides in the amount of resources required and the optimization time. In this work, the application of the genetic algorithms (GA) in 2D arrays optimization is presented to evaluate the potential of these algorithms compared to the simulated annealing in terms of processing time and output beam profiles. GA have been used in the optimization of multivariable cost functions in many applications as power systems analysis, wireless sensor arrays in telecommunication and they provided satisfactory results in a relative short time. The 2D ultrasound arrays optimization can also be formulated in a similar way as the problems occurring in these domains, making genetic algorithms a potential candidate to solve them. Although GA are reported to not be as efficient as SA in the optimization of medium and large 2D arrays, the aim of this paper is to evaluate their real ability when compared to the SA. Preliminary results showed a fast convergence time of genetic algorithm for comparable acoustical properties for the optimized arrays compared to SA.",
author = "Bakary Diarra and Ravi Samikannu and Didier Vray and Christian Cachard and Joseph Chuma and Abid Yahya and Herve Liebgott",
year = "2018",
month = "12",
day = "17",
doi = "10.1109/ULTSYM.2018.8579952",
language = "English",
series = "IEEE International Ultrasonics Symposium, IUS",
publisher = "IEEE Computer Society",
booktitle = "2018 IEEE International Ultrasonics Symposium, IUS 2018",
address = "United States",

}

Diarra, B, Samikannu, R, Vray, D, Cachard, C, Chuma, J, Yahya, A & Liebgott, H 2018, Feasibility of Genetic Algorithms in 2D Ultrasound Array Optimization. in 2018 IEEE International Ultrasonics Symposium, IUS 2018., 8579952, IEEE International Ultrasonics Symposium, IUS, vol. 2018-October, IEEE Computer Society, 2018 IEEE International Ultrasonics Symposium, IUS 2018, Kobe, Japan, 10/22/18. https://doi.org/10.1109/ULTSYM.2018.8579952

Feasibility of Genetic Algorithms in 2D Ultrasound Array Optimization. / Diarra, Bakary; Samikannu, Ravi; Vray, Didier; Cachard, Christian; Chuma, Joseph; Yahya, Abid; Liebgott, Herve.

2018 IEEE International Ultrasonics Symposium, IUS 2018. IEEE Computer Society, 2018. 8579952 (IEEE International Ultrasonics Symposium, IUS; Vol. 2018-October).

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

TY - GEN

T1 - Feasibility of Genetic Algorithms in 2D Ultrasound Array Optimization

AU - Diarra, Bakary

AU - Samikannu, Ravi

AU - Vray, Didier

AU - Cachard, Christian

AU - Chuma, Joseph

AU - Yahya, Abid

AU - Liebgott, Herve

PY - 2018/12/17

Y1 - 2018/12/17

N2 - The optimization of 2D ultrasound arrays can be efficiently realized through the use of simulated annealing (SA) as reported in many recent works. The main limitation of SA resides in the amount of resources required and the optimization time. In this work, the application of the genetic algorithms (GA) in 2D arrays optimization is presented to evaluate the potential of these algorithms compared to the simulated annealing in terms of processing time and output beam profiles. GA have been used in the optimization of multivariable cost functions in many applications as power systems analysis, wireless sensor arrays in telecommunication and they provided satisfactory results in a relative short time. The 2D ultrasound arrays optimization can also be formulated in a similar way as the problems occurring in these domains, making genetic algorithms a potential candidate to solve them. Although GA are reported to not be as efficient as SA in the optimization of medium and large 2D arrays, the aim of this paper is to evaluate their real ability when compared to the SA. Preliminary results showed a fast convergence time of genetic algorithm for comparable acoustical properties for the optimized arrays compared to SA.

AB - The optimization of 2D ultrasound arrays can be efficiently realized through the use of simulated annealing (SA) as reported in many recent works. The main limitation of SA resides in the amount of resources required and the optimization time. In this work, the application of the genetic algorithms (GA) in 2D arrays optimization is presented to evaluate the potential of these algorithms compared to the simulated annealing in terms of processing time and output beam profiles. GA have been used in the optimization of multivariable cost functions in many applications as power systems analysis, wireless sensor arrays in telecommunication and they provided satisfactory results in a relative short time. The 2D ultrasound arrays optimization can also be formulated in a similar way as the problems occurring in these domains, making genetic algorithms a potential candidate to solve them. Although GA are reported to not be as efficient as SA in the optimization of medium and large 2D arrays, the aim of this paper is to evaluate their real ability when compared to the SA. Preliminary results showed a fast convergence time of genetic algorithm for comparable acoustical properties for the optimized arrays compared to SA.

UR - http://www.scopus.com/inward/record.url?scp=85060571140&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060571140&partnerID=8YFLogxK

U2 - 10.1109/ULTSYM.2018.8579952

DO - 10.1109/ULTSYM.2018.8579952

M3 - Conference contribution

AN - SCOPUS:85060571140

T3 - IEEE International Ultrasonics Symposium, IUS

BT - 2018 IEEE International Ultrasonics Symposium, IUS 2018

PB - IEEE Computer Society

ER -

Diarra B, Samikannu R, Vray D, Cachard C, Chuma J, Yahya A et al. Feasibility of Genetic Algorithms in 2D Ultrasound Array Optimization. In 2018 IEEE International Ultrasonics Symposium, IUS 2018. IEEE Computer Society. 2018. 8579952. (IEEE International Ultrasonics Symposium, IUS). https://doi.org/10.1109/ULTSYM.2018.8579952