Motion generation system using interactive evolutionary computation and signal processing

Yuki Wakayama, Shigeru Takano, Yoshihiro Okada, Hiroaki Nishino

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

2 Citations (Scopus)

Abstract

This paper proposes new motion generation method by Interactive Evolutionary Computation based on Genetic Algorithm. This method generates new motions by combining some primitive motions, which are obtained by dividing already existing motions. This combining process is performed by IEC based on GA and then combined motions are generated according to the user preference. There is a problem that the variation of generated motions is very small if the number of already existing motions is too small. To compensate this problem, the authors also employ motion signal processing technique. Generated motions by combining primitive motions are modified through multi-level decomposition and composition of discrete wavelet-transform. When applying the composition process, each level wavelet coefficients are modified by their gain parameter which the user chooses through IEC and then motions modified by the user preference are generated. In this way, combinational use of IEC based on GA and motion signal processing technique allows the user to generate his/her required motions easily and intuitively.

Original languageEnglish
Title of host publicationNBiS 2009 - 12th International Conference on Network-Based Information Systems
Pages492-498
Number of pages7
DOIs
Publication statusPublished - 2009
EventNBiS 2009 - 12th International Conference on Network-Based Information Systems - Indianapolis, IN, United States
Duration: Aug 19 2009Aug 21 2009

Other

OtherNBiS 2009 - 12th International Conference on Network-Based Information Systems
CountryUnited States
CityIndianapolis, IN
Period8/19/098/21/09

Fingerprint

Evolutionary algorithms
Signal processing
Discrete wavelet transforms
Chemical analysis
Genetic algorithms
Decomposition

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Information Systems

Cite this

Wakayama, Y., Takano, S., Okada, Y., & Nishino, H. (2009). Motion generation system using interactive evolutionary computation and signal processing. In NBiS 2009 - 12th International Conference on Network-Based Information Systems (pp. 492-498). [5349956] https://doi.org/10.1109/NBiS.2009.97

Motion generation system using interactive evolutionary computation and signal processing. / Wakayama, Yuki; Takano, Shigeru; Okada, Yoshihiro; Nishino, Hiroaki.

NBiS 2009 - 12th International Conference on Network-Based Information Systems. 2009. p. 492-498 5349956.

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

Wakayama, Y, Takano, S, Okada, Y & Nishino, H 2009, Motion generation system using interactive evolutionary computation and signal processing. in NBiS 2009 - 12th International Conference on Network-Based Information Systems., 5349956, pp. 492-498, NBiS 2009 - 12th International Conference on Network-Based Information Systems, Indianapolis, IN, United States, 8/19/09. https://doi.org/10.1109/NBiS.2009.97
Wakayama Y, Takano S, Okada Y, Nishino H. Motion generation system using interactive evolutionary computation and signal processing. In NBiS 2009 - 12th International Conference on Network-Based Information Systems. 2009. p. 492-498. 5349956 https://doi.org/10.1109/NBiS.2009.97
Wakayama, Yuki ; Takano, Shigeru ; Okada, Yoshihiro ; Nishino, Hiroaki. / Motion generation system using interactive evolutionary computation and signal processing. NBiS 2009 - 12th International Conference on Network-Based Information Systems. 2009. pp. 492-498
@inproceedings{06a9a89a7d77421792aa2c990f5e7874,
title = "Motion generation system using interactive evolutionary computation and signal processing",
abstract = "This paper proposes new motion generation method by Interactive Evolutionary Computation based on Genetic Algorithm. This method generates new motions by combining some primitive motions, which are obtained by dividing already existing motions. This combining process is performed by IEC based on GA and then combined motions are generated according to the user preference. There is a problem that the variation of generated motions is very small if the number of already existing motions is too small. To compensate this problem, the authors also employ motion signal processing technique. Generated motions by combining primitive motions are modified through multi-level decomposition and composition of discrete wavelet-transform. When applying the composition process, each level wavelet coefficients are modified by their gain parameter which the user chooses through IEC and then motions modified by the user preference are generated. In this way, combinational use of IEC based on GA and motion signal processing technique allows the user to generate his/her required motions easily and intuitively.",
author = "Yuki Wakayama and Shigeru Takano and Yoshihiro Okada and Hiroaki Nishino",
year = "2009",
doi = "10.1109/NBiS.2009.97",
language = "English",
isbn = "9780769537672",
pages = "492--498",
booktitle = "NBiS 2009 - 12th International Conference on Network-Based Information Systems",

}

TY - GEN

T1 - Motion generation system using interactive evolutionary computation and signal processing

AU - Wakayama, Yuki

AU - Takano, Shigeru

AU - Okada, Yoshihiro

AU - Nishino, Hiroaki

PY - 2009

Y1 - 2009

N2 - This paper proposes new motion generation method by Interactive Evolutionary Computation based on Genetic Algorithm. This method generates new motions by combining some primitive motions, which are obtained by dividing already existing motions. This combining process is performed by IEC based on GA and then combined motions are generated according to the user preference. There is a problem that the variation of generated motions is very small if the number of already existing motions is too small. To compensate this problem, the authors also employ motion signal processing technique. Generated motions by combining primitive motions are modified through multi-level decomposition and composition of discrete wavelet-transform. When applying the composition process, each level wavelet coefficients are modified by their gain parameter which the user chooses through IEC and then motions modified by the user preference are generated. In this way, combinational use of IEC based on GA and motion signal processing technique allows the user to generate his/her required motions easily and intuitively.

AB - This paper proposes new motion generation method by Interactive Evolutionary Computation based on Genetic Algorithm. This method generates new motions by combining some primitive motions, which are obtained by dividing already existing motions. This combining process is performed by IEC based on GA and then combined motions are generated according to the user preference. There is a problem that the variation of generated motions is very small if the number of already existing motions is too small. To compensate this problem, the authors also employ motion signal processing technique. Generated motions by combining primitive motions are modified through multi-level decomposition and composition of discrete wavelet-transform. When applying the composition process, each level wavelet coefficients are modified by their gain parameter which the user chooses through IEC and then motions modified by the user preference are generated. In this way, combinational use of IEC based on GA and motion signal processing technique allows the user to generate his/her required motions easily and intuitively.

UR - http://www.scopus.com/inward/record.url?scp=74549152699&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=74549152699&partnerID=8YFLogxK

U2 - 10.1109/NBiS.2009.97

DO - 10.1109/NBiS.2009.97

M3 - Conference contribution

AN - SCOPUS:74549152699

SN - 9780769537672

SP - 492

EP - 498

BT - NBiS 2009 - 12th International Conference on Network-Based Information Systems

ER -