Gender recognition of human behaviors using neural ensembles

J. Ryu, S. B. Cho

Research output: Contribution to conferencePaper

2 Citations (Scopus)

Abstract

In this paper, we have developed two ensembles of neural network classifiers in order to recognize actors' gender from their biological movements. One is the ensemble of modular MLPs (experts), the other is the ensemble of modular MLPs and an inductive decision tree which combines the output of experts. The human movement database consists of 13 males' and 13 females' movements, and contains 10 repetitions of knocking, waving and lifting movements both in neutral and angry style. Features have been extracted with 4 different representations such as the 2D and 3D velocities and positions, recorded from 6 point lights attached on body. We have compared the results of ensembles to the regular classifiers such as MLP, decision tree, self-organizing map and support vector machine. Furthermore, the discriminability and efficiency have been calculated for the comparison with the human performance that has been obtained with the same experiment. Our experimental results indicate that the ensemble models are superior to the conventional classifiers and human participants.

Original languageEnglish
Pages571-576
Number of pages6
Publication statusPublished - 2001 Jan 1
EventInternational Joint Conference on Neural Networks (IJCNN'01) - Washington, DC, United States
Duration: 2001 Jul 152001 Jul 19

Other

OtherInternational Joint Conference on Neural Networks (IJCNN'01)
CountryUnited States
CityWashington, DC
Period01/7/1501/7/19

Fingerprint

Classifiers
Decision trees
Self organizing maps
Support vector machines
Neural networks
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence

Cite this

Ryu, J., & Cho, S. B. (2001). Gender recognition of human behaviors using neural ensembles. 571-576. Paper presented at International Joint Conference on Neural Networks (IJCNN'01), Washington, DC, United States.
Ryu, J. ; Cho, S. B. / Gender recognition of human behaviors using neural ensembles. Paper presented at International Joint Conference on Neural Networks (IJCNN'01), Washington, DC, United States.6 p.
@conference{554226249956418eb7a1a740c4120795,
title = "Gender recognition of human behaviors using neural ensembles",
abstract = "In this paper, we have developed two ensembles of neural network classifiers in order to recognize actors' gender from their biological movements. One is the ensemble of modular MLPs (experts), the other is the ensemble of modular MLPs and an inductive decision tree which combines the output of experts. The human movement database consists of 13 males' and 13 females' movements, and contains 10 repetitions of knocking, waving and lifting movements both in neutral and angry style. Features have been extracted with 4 different representations such as the 2D and 3D velocities and positions, recorded from 6 point lights attached on body. We have compared the results of ensembles to the regular classifiers such as MLP, decision tree, self-organizing map and support vector machine. Furthermore, the discriminability and efficiency have been calculated for the comparison with the human performance that has been obtained with the same experiment. Our experimental results indicate that the ensemble models are superior to the conventional classifiers and human participants.",
author = "J. Ryu and Cho, {S. B.}",
year = "2001",
month = "1",
day = "1",
language = "English",
pages = "571--576",
note = "International Joint Conference on Neural Networks (IJCNN'01) ; Conference date: 15-07-2001 Through 19-07-2001",

}

Ryu, J & Cho, SB 2001, 'Gender recognition of human behaviors using neural ensembles', Paper presented at International Joint Conference on Neural Networks (IJCNN'01), Washington, DC, United States, 01/7/15 - 01/7/19 pp. 571-576.

Gender recognition of human behaviors using neural ensembles. / Ryu, J.; Cho, S. B.

2001. 571-576 Paper presented at International Joint Conference on Neural Networks (IJCNN'01), Washington, DC, United States.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Gender recognition of human behaviors using neural ensembles

AU - Ryu, J.

AU - Cho, S. B.

PY - 2001/1/1

Y1 - 2001/1/1

N2 - In this paper, we have developed two ensembles of neural network classifiers in order to recognize actors' gender from their biological movements. One is the ensemble of modular MLPs (experts), the other is the ensemble of modular MLPs and an inductive decision tree which combines the output of experts. The human movement database consists of 13 males' and 13 females' movements, and contains 10 repetitions of knocking, waving and lifting movements both in neutral and angry style. Features have been extracted with 4 different representations such as the 2D and 3D velocities and positions, recorded from 6 point lights attached on body. We have compared the results of ensembles to the regular classifiers such as MLP, decision tree, self-organizing map and support vector machine. Furthermore, the discriminability and efficiency have been calculated for the comparison with the human performance that has been obtained with the same experiment. Our experimental results indicate that the ensemble models are superior to the conventional classifiers and human participants.

AB - In this paper, we have developed two ensembles of neural network classifiers in order to recognize actors' gender from their biological movements. One is the ensemble of modular MLPs (experts), the other is the ensemble of modular MLPs and an inductive decision tree which combines the output of experts. The human movement database consists of 13 males' and 13 females' movements, and contains 10 repetitions of knocking, waving and lifting movements both in neutral and angry style. Features have been extracted with 4 different representations such as the 2D and 3D velocities and positions, recorded from 6 point lights attached on body. We have compared the results of ensembles to the regular classifiers such as MLP, decision tree, self-organizing map and support vector machine. Furthermore, the discriminability and efficiency have been calculated for the comparison with the human performance that has been obtained with the same experiment. Our experimental results indicate that the ensemble models are superior to the conventional classifiers and human participants.

UR - http://www.scopus.com/inward/record.url?scp=0034858220&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034858220&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0034858220

SP - 571

EP - 576

ER -

Ryu J, Cho SB. Gender recognition of human behaviors using neural ensembles. 2001. Paper presented at International Joint Conference on Neural Networks (IJCNN'01), Washington, DC, United States.