Structure-adaptive SOM to classify 3-dimensional point light actors' gender

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

Abstract

Classifying the patterns of moving point lights attached on actor's bodies with self-organizing map often fails to get successful results with its original unsupervised learning algorithm. This paper exploits a structure-adaptive self-organizing map (SASOM) which adaptively updates the weights, structure and size of the map, resulting in remarkable improvement of pattern classification performance. We have compared the results with those of conventional pattern classifiers and human subjects. SASOM turns out to be the best classifier producing 97.1% of recognition rate on the 312 test data from 26 subjects.

Original languageEnglish
Title of host publicationICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing
Subtitle of host publicationComputational Intelligence for the E-Age
EditorsLipo Wang, Kunihiko Fukushima, Jagath C. Rajapakse, Soo-Young Lee, Xin Yao
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages949-953
Number of pages5
ISBN (Electronic)9810475241, 9789810475246
DOIs
Publication statusPublished - 2002 Jan 1
Event9th International Conference on Neural Information Processing, ICONIP 2002 - Singapore, Singapore
Duration: 2002 Nov 182002 Nov 22

Publication series

NameICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age
Volume2

Other

Other9th International Conference on Neural Information Processing, ICONIP 2002
CountrySingapore
CitySingapore
Period02/11/1802/11/22

Fingerprint

Self organizing maps
Classifiers
Unsupervised learning
Learning algorithms
Pattern recognition

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Cite this

Cho, S. B. (2002). Structure-adaptive SOM to classify 3-dimensional point light actors' gender. In L. Wang, K. Fukushima, J. C. Rajapakse, S-Y. Lee, & X. Yao (Eds.), ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age (pp. 949-953). [1198201] (ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age; Vol. 2). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICONIP.2002.1198201
Cho, Sung Bae. / Structure-adaptive SOM to classify 3-dimensional point light actors' gender. ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age. editor / Lipo Wang ; Kunihiko Fukushima ; Jagath C. Rajapakse ; Soo-Young Lee ; Xin Yao. Institute of Electrical and Electronics Engineers Inc., 2002. pp. 949-953 (ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age).
@inproceedings{6f56dc28b93c431699d9fe4cc9560b9b,
title = "Structure-adaptive SOM to classify 3-dimensional point light actors' gender",
abstract = "Classifying the patterns of moving point lights attached on actor's bodies with self-organizing map often fails to get successful results with its original unsupervised learning algorithm. This paper exploits a structure-adaptive self-organizing map (SASOM) which adaptively updates the weights, structure and size of the map, resulting in remarkable improvement of pattern classification performance. We have compared the results with those of conventional pattern classifiers and human subjects. SASOM turns out to be the best classifier producing 97.1{\%} of recognition rate on the 312 test data from 26 subjects.",
author = "Cho, {Sung Bae}",
year = "2002",
month = "1",
day = "1",
doi = "10.1109/ICONIP.2002.1198201",
language = "English",
series = "ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "949--953",
editor = "Lipo Wang and Kunihiko Fukushima and Rajapakse, {Jagath C.} and Soo-Young Lee and Xin Yao",
booktitle = "ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing",
address = "United States",

}

Cho, SB 2002, Structure-adaptive SOM to classify 3-dimensional point light actors' gender. in L Wang, K Fukushima, JC Rajapakse, S-Y Lee & X Yao (eds), ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age., 1198201, ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age, vol. 2, Institute of Electrical and Electronics Engineers Inc., pp. 949-953, 9th International Conference on Neural Information Processing, ICONIP 2002, Singapore, Singapore, 02/11/18. https://doi.org/10.1109/ICONIP.2002.1198201

Structure-adaptive SOM to classify 3-dimensional point light actors' gender. / Cho, Sung Bae.

ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age. ed. / Lipo Wang; Kunihiko Fukushima; Jagath C. Rajapakse; Soo-Young Lee; Xin Yao. Institute of Electrical and Electronics Engineers Inc., 2002. p. 949-953 1198201 (ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age; Vol. 2).

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

TY - GEN

T1 - Structure-adaptive SOM to classify 3-dimensional point light actors' gender

AU - Cho, Sung Bae

PY - 2002/1/1

Y1 - 2002/1/1

N2 - Classifying the patterns of moving point lights attached on actor's bodies with self-organizing map often fails to get successful results with its original unsupervised learning algorithm. This paper exploits a structure-adaptive self-organizing map (SASOM) which adaptively updates the weights, structure and size of the map, resulting in remarkable improvement of pattern classification performance. We have compared the results with those of conventional pattern classifiers and human subjects. SASOM turns out to be the best classifier producing 97.1% of recognition rate on the 312 test data from 26 subjects.

AB - Classifying the patterns of moving point lights attached on actor's bodies with self-organizing map often fails to get successful results with its original unsupervised learning algorithm. This paper exploits a structure-adaptive self-organizing map (SASOM) which adaptively updates the weights, structure and size of the map, resulting in remarkable improvement of pattern classification performance. We have compared the results with those of conventional pattern classifiers and human subjects. SASOM turns out to be the best classifier producing 97.1% of recognition rate on the 312 test data from 26 subjects.

UR - http://www.scopus.com/inward/record.url?scp=84964506806&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84964506806&partnerID=8YFLogxK

U2 - 10.1109/ICONIP.2002.1198201

DO - 10.1109/ICONIP.2002.1198201

M3 - Conference contribution

AN - SCOPUS:84964506806

T3 - ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age

SP - 949

EP - 953

BT - ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing

A2 - Wang, Lipo

A2 - Fukushima, Kunihiko

A2 - Rajapakse, Jagath C.

A2 - Lee, Soo-Young

A2 - Yao, Xin

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Cho SB. Structure-adaptive SOM to classify 3-dimensional point light actors' gender. In Wang L, Fukushima K, Rajapakse JC, Lee S-Y, Yao X, editors, ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age. Institute of Electrical and Electronics Engineers Inc. 2002. p. 949-953. 1198201. (ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age). https://doi.org/10.1109/ICONIP.2002.1198201