Visualization of EC landscape to accelerate EC conversion and evaluation of its effect

F. Boschetti, Hideyuki Takagi

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

6 Citations (Scopus)

Abstract

We evaluate how visualization of an evolutionary computation (EC) landscape is effective using a geophysical task. This technique allows us to actively participate in EC optimization by viewing the distribution of searching points on 2-D space mapped from an n-D EC landscape, and indicating where in the EC is the possible global optimum. We construct a Visualized GA system that includes self-organizing maps for visualization and compare its performance with that of a normal GA using the geophysical simulation task. Sign tests for the comparisons show that the Visualized GA converges significantly faster than the normal EC (p < 001), which suggests further extensions to enhance user interactivity.

Original languageEnglish
Title of host publicationProceedings of the IEEE Conference on Evolutionary Computation, ICEC
Pages880-886
Number of pages7
Volume2
Publication statusPublished - 2001
Externally publishedYes
EventCongress on Evolutionary Computation 2001 - Seoul, Korea, Republic of
Duration: May 27 2001May 30 2001

Other

OtherCongress on Evolutionary Computation 2001
CountryKorea, Republic of
CitySeoul
Period5/27/015/30/01

Fingerprint

Evolutionary algorithms
Visualization
Self organizing maps

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Engineering(all)

Cite this

Boschetti, F., & Takagi, H. (2001). Visualization of EC landscape to accelerate EC conversion and evaluation of its effect. In Proceedings of the IEEE Conference on Evolutionary Computation, ICEC (Vol. 2, pp. 880-886)

Visualization of EC landscape to accelerate EC conversion and evaluation of its effect. / Boschetti, F.; Takagi, Hideyuki.

Proceedings of the IEEE Conference on Evolutionary Computation, ICEC. Vol. 2 2001. p. 880-886.

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

Boschetti, F & Takagi, H 2001, Visualization of EC landscape to accelerate EC conversion and evaluation of its effect. in Proceedings of the IEEE Conference on Evolutionary Computation, ICEC. vol. 2, pp. 880-886, Congress on Evolutionary Computation 2001, Seoul, Korea, Republic of, 5/27/01.
Boschetti F, Takagi H. Visualization of EC landscape to accelerate EC conversion and evaluation of its effect. In Proceedings of the IEEE Conference on Evolutionary Computation, ICEC. Vol. 2. 2001. p. 880-886
Boschetti, F. ; Takagi, Hideyuki. / Visualization of EC landscape to accelerate EC conversion and evaluation of its effect. Proceedings of the IEEE Conference on Evolutionary Computation, ICEC. Vol. 2 2001. pp. 880-886
@inproceedings{c09293f40f924976b235b86a3545ddad,
title = "Visualization of EC landscape to accelerate EC conversion and evaluation of its effect",
abstract = "We evaluate how visualization of an evolutionary computation (EC) landscape is effective using a geophysical task. This technique allows us to actively participate in EC optimization by viewing the distribution of searching points on 2-D space mapped from an n-D EC landscape, and indicating where in the EC is the possible global optimum. We construct a Visualized GA system that includes self-organizing maps for visualization and compare its performance with that of a normal GA using the geophysical simulation task. Sign tests for the comparisons show that the Visualized GA converges significantly faster than the normal EC (p < 001), which suggests further extensions to enhance user interactivity.",
author = "F. Boschetti and Hideyuki Takagi",
year = "2001",
language = "English",
volume = "2",
pages = "880--886",
booktitle = "Proceedings of the IEEE Conference on Evolutionary Computation, ICEC",

}

TY - GEN

T1 - Visualization of EC landscape to accelerate EC conversion and evaluation of its effect

AU - Boschetti, F.

AU - Takagi, Hideyuki

PY - 2001

Y1 - 2001

N2 - We evaluate how visualization of an evolutionary computation (EC) landscape is effective using a geophysical task. This technique allows us to actively participate in EC optimization by viewing the distribution of searching points on 2-D space mapped from an n-D EC landscape, and indicating where in the EC is the possible global optimum. We construct a Visualized GA system that includes self-organizing maps for visualization and compare its performance with that of a normal GA using the geophysical simulation task. Sign tests for the comparisons show that the Visualized GA converges significantly faster than the normal EC (p < 001), which suggests further extensions to enhance user interactivity.

AB - We evaluate how visualization of an evolutionary computation (EC) landscape is effective using a geophysical task. This technique allows us to actively participate in EC optimization by viewing the distribution of searching points on 2-D space mapped from an n-D EC landscape, and indicating where in the EC is the possible global optimum. We construct a Visualized GA system that includes self-organizing maps for visualization and compare its performance with that of a normal GA using the geophysical simulation task. Sign tests for the comparisons show that the Visualized GA converges significantly faster than the normal EC (p < 001), which suggests further extensions to enhance user interactivity.

UR - http://www.scopus.com/inward/record.url?scp=0034863341&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034863341&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0034863341

VL - 2

SP - 880

EP - 886

BT - Proceedings of the IEEE Conference on Evolutionary Computation, ICEC

ER -