Classifying 3-dimensional point light actors' gender using structure-adaptive self-organizing map

Sung-Bae Cho, Jungwon Ryu

Research output: Contribution to journalArticle

Abstract

As a basic step to understand human behavior, we search for an optimal classifier to recognize the biological movements using moving point lights attached on actor's bodies. Classifying the patterns with self-organizing map often fails to get successful results with its original unsupervised learning algorithm. This paper presents 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. Two physical input features of the movement patterns have been used: positions and velocities of six locations. We have compared the results with those of conventional pattern classifiers and human subjects by obtaining the recognition accuracy, discrim-inability and efficiency. SASOM turns out to be the best classifier producing 97.1% of recognition rate on the 312 test data from 26 subjects.

Original languageEnglish
Pages (from-to)877-887
Number of pages11
JournalInternational Journal of Innovative Computing, Information and Control
Volume5
Issue number4
Publication statusPublished - 2009 Apr 1

Fingerprint

Self organizing maps
Self-organizing Map
Classifiers
Classifier
Unsupervised learning
Unsupervised Learning
Pattern Classification
Human Behavior
Learning algorithms
Pattern recognition
Learning Algorithm
Update
Gender
Actors
Movement

All Science Journal Classification (ASJC) codes

  • Software
  • Theoretical Computer Science
  • Information Systems
  • Computational Theory and Mathematics

Cite this

@article{4e55c0c9e13146c6b7cd85597064721e,
title = "Classifying 3-dimensional point light actors' gender using structure-adaptive self-organizing map",
abstract = "As a basic step to understand human behavior, we search for an optimal classifier to recognize the biological movements using moving point lights attached on actor's bodies. Classifying the patterns with self-organizing map often fails to get successful results with its original unsupervised learning algorithm. This paper presents 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. Two physical input features of the movement patterns have been used: positions and velocities of six locations. We have compared the results with those of conventional pattern classifiers and human subjects by obtaining the recognition accuracy, discrim-inability and efficiency. SASOM turns out to be the best classifier producing 97.1{\%} of recognition rate on the 312 test data from 26 subjects.",
author = "Sung-Bae Cho and Jungwon Ryu",
year = "2009",
month = "4",
day = "1",
language = "English",
volume = "5",
pages = "877--887",
journal = "International Journal of Innovative Computing, Information and Control",
issn = "1349-4198",
publisher = "IJICIC Editorial Office",
number = "4",

}

TY - JOUR

T1 - Classifying 3-dimensional point light actors' gender using structure-adaptive self-organizing map

AU - Cho, Sung-Bae

AU - Ryu, Jungwon

PY - 2009/4/1

Y1 - 2009/4/1

N2 - As a basic step to understand human behavior, we search for an optimal classifier to recognize the biological movements using moving point lights attached on actor's bodies. Classifying the patterns with self-organizing map often fails to get successful results with its original unsupervised learning algorithm. This paper presents 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. Two physical input features of the movement patterns have been used: positions and velocities of six locations. We have compared the results with those of conventional pattern classifiers and human subjects by obtaining the recognition accuracy, discrim-inability and efficiency. SASOM turns out to be the best classifier producing 97.1% of recognition rate on the 312 test data from 26 subjects.

AB - As a basic step to understand human behavior, we search for an optimal classifier to recognize the biological movements using moving point lights attached on actor's bodies. Classifying the patterns with self-organizing map often fails to get successful results with its original unsupervised learning algorithm. This paper presents 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. Two physical input features of the movement patterns have been used: positions and velocities of six locations. We have compared the results with those of conventional pattern classifiers and human subjects by obtaining the recognition accuracy, discrim-inability and efficiency. 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=64349085377&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=64349085377&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:64349085377

VL - 5

SP - 877

EP - 887

JO - International Journal of Innovative Computing, Information and Control

JF - International Journal of Innovative Computing, Information and Control

SN - 1349-4198

IS - 4

ER -