Multimodal human-humanoid interaction using motions, brain NIRS and spike trains

Yasuo Matsuyama; Nimiko Ochiai; Takashi Hatakeyama; Keita Noguchi

doi:10.1145/1734454.1734529

Multimodal human-humanoid interaction using motions, brain NIRS and spike trains

Yasuo Matsuyama^*, Nimiko Ochiai, Takashi Hatakeyama, Keita Noguchi

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

Abstract

Heterogeneous bio-signals including human motions, brain NIRS and neural spike trains are utilized for operating biped humanoids. The Bayesian network comprising Hidden Markov Models and Support Vector Machines is designed for the signal integration. By this method, the system complexity is reduced so that that total operation is within the scope of PCs. The designed system is capable of transducing original sensory meaning to another. This leads to prosthesis, rehabilitation and gaming. In addition to the supervised mode, the humanoid can act autonomously for its own designed tasks.

Original language	English
Title of host publication	5th ACM/IEEE International Conference on Human-Robot Interaction, HRI 2010
Pages	173-174
Number of pages	2
DOIs	https://doi.org/10.1145/1734454.1734529
Publication status	Published - 2010
Event	5th ACM/IEEE International Conference on Human-Robot Interaction, HRI 2010 - Osaka Duration: 2010 Mar 2 → 2010 Mar 5

Other

Other	5th ACM/IEEE International Conference on Human-Robot Interaction, HRI 2010
City	Osaka
Period	10/3/2 → 10/3/5

Keywords

Brain NIRS
HMM/SVM-embedded BN
Human-humanoid interaction
Motion recognition
Multimodal
Neural spike train
Non-verbal
Sensory transducing

ASJC Scopus subject areas

Artificial Intelligence
Human-Computer Interaction

Access to Document

10.1145/1734454.1734529

Cite this

@inproceedings{26849f70dbf742d188b196564d76231d,

title = "Multimodal human-humanoid interaction using motions, brain NIRS and spike trains",

abstract = "Heterogeneous bio-signals including human motions, brain NIRS and neural spike trains are utilized for operating biped humanoids. The Bayesian network comprising Hidden Markov Models and Support Vector Machines is designed for the signal integration. By this method, the system complexity is reduced so that that total operation is within the scope of PCs. The designed system is capable of transducing original sensory meaning to another. This leads to prosthesis, rehabilitation and gaming. In addition to the supervised mode, the humanoid can act autonomously for its own designed tasks.",

keywords = "Brain NIRS, HMM/SVM-embedded BN, Human-humanoid interaction, Motion recognition, Multimodal, Neural spike train, Non-verbal, Sensory transducing",

author = "Yasuo Matsuyama and Nimiko Ochiai and Takashi Hatakeyama and Keita Noguchi",

year = "2010",

doi = "10.1145/1734454.1734529",

language = "English",

isbn = "9781424448937",

pages = "173--174",

booktitle = "5th ACM/IEEE International Conference on Human-Robot Interaction, HRI 2010",

note = "5th ACM/IEEE International Conference on Human-Robot Interaction, HRI 2010 ; Conference date: 02-03-2010 Through 05-03-2010",

}

TY - GEN

T1 - Multimodal human-humanoid interaction using motions, brain NIRS and spike trains

AU - Matsuyama, Yasuo

AU - Ochiai, Nimiko

AU - Hatakeyama, Takashi

AU - Noguchi, Keita

PY - 2010

Y1 - 2010

N2 - Heterogeneous bio-signals including human motions, brain NIRS and neural spike trains are utilized for operating biped humanoids. The Bayesian network comprising Hidden Markov Models and Support Vector Machines is designed for the signal integration. By this method, the system complexity is reduced so that that total operation is within the scope of PCs. The designed system is capable of transducing original sensory meaning to another. This leads to prosthesis, rehabilitation and gaming. In addition to the supervised mode, the humanoid can act autonomously for its own designed tasks.

AB - Heterogeneous bio-signals including human motions, brain NIRS and neural spike trains are utilized for operating biped humanoids. The Bayesian network comprising Hidden Markov Models and Support Vector Machines is designed for the signal integration. By this method, the system complexity is reduced so that that total operation is within the scope of PCs. The designed system is capable of transducing original sensory meaning to another. This leads to prosthesis, rehabilitation and gaming. In addition to the supervised mode, the humanoid can act autonomously for its own designed tasks.

KW - Brain NIRS

KW - HMM/SVM-embedded BN

KW - Human-humanoid interaction

KW - Motion recognition

KW - Multimodal

KW - Neural spike train

KW - Non-verbal

KW - Sensory transducing

UR - http://www.scopus.com/inward/record.url?scp=77951538303&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77951538303&partnerID=8YFLogxK

U2 - 10.1145/1734454.1734529

DO - 10.1145/1734454.1734529

M3 - Conference contribution

AN - SCOPUS:77951538303

SN - 9781424448937

SP - 173

EP - 174

BT - 5th ACM/IEEE International Conference on Human-Robot Interaction, HRI 2010

T2 - 5th ACM/IEEE International Conference on Human-Robot Interaction, HRI 2010

Y2 - 2 March 2010 through 5 March 2010

ER -

Multimodal human-humanoid interaction using motions, brain NIRS and spike trains

Abstract

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this