A group emotion control system based on reinforcement learning

Kee Hoon Kim, Sung Bae Cho

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

Abstract

Recently, ubiquitous computing and related sensor technology have significantly progressed. On the other side, the relationship between human emotion and sensory stimuli has been investigated. With this background, we propose sensory stimuli control system to adjust group emotion to given target emotion. Valence-arousal model was adapted for defining group emotion, and survey of 73-papers and onsite-investigation had done for domain knowledge. The proposed system is based on the partially observable Markov decision process to deal with the uncertain states of group emotion, and reinforcement learning approach to learn the criterion of decision in real time. To evaluate the proposed system, we collected 160-minutes data from kindergarten where the music and math classes are ongoing with 10 prescholers and 1 caregiver are participating. Our system produced 55.17% of accuracy, which outperfomed the original system by 15.51%p.

Original languageEnglish
Title of host publicationProceedings of the 2015 7th International Conference of Soft Computing and Pattern Recognition, SoCPaR 2015
EditorsMario Koppen, Azah Kamilah Muda, Kun Ma, Bing Xue, Hideyuki Takagi, Ajith Abraham
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages303-307
Number of pages5
ISBN (Electronic)9781467393607
DOIs
Publication statusPublished - 2016 Jun 15
Event7th International Conference of Soft Computing and Pattern Recognition, SoCPaR 2015 - Fukuoka, Japan
Duration: 2015 Nov 132015 Nov 15

Publication series

NameProceedings of the 2015 7th International Conference of Soft Computing and Pattern Recognition, SoCPaR 2015

Other

Other7th International Conference of Soft Computing and Pattern Recognition, SoCPaR 2015
CountryJapan
CityFukuoka
Period15/11/1315/11/15

Fingerprint

Reinforcement learning
Ubiquitous computing
Reinforcement Learning
Control System
Control systems
Sensors
Partially Observable Markov Decision Process
Ubiquitous Computing
Domain Knowledge
Music
Emotion
Sensor
Target
Evaluate

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Control and Optimization
  • Modelling and Simulation

Cite this

Kim, K. H., & Cho, S. B. (2016). A group emotion control system based on reinforcement learning. In M. Koppen, A. K. Muda, K. Ma, B. Xue, H. Takagi, & A. Abraham (Eds.), Proceedings of the 2015 7th International Conference of Soft Computing and Pattern Recognition, SoCPaR 2015 (pp. 303-307). [7492826] (Proceedings of the 2015 7th International Conference of Soft Computing and Pattern Recognition, SoCPaR 2015). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SOCPAR.2015.7492826
Kim, Kee Hoon ; Cho, Sung Bae. / A group emotion control system based on reinforcement learning. Proceedings of the 2015 7th International Conference of Soft Computing and Pattern Recognition, SoCPaR 2015. editor / Mario Koppen ; Azah Kamilah Muda ; Kun Ma ; Bing Xue ; Hideyuki Takagi ; Ajith Abraham. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 303-307 (Proceedings of the 2015 7th International Conference of Soft Computing and Pattern Recognition, SoCPaR 2015).
@inproceedings{9071f0086d5b40bca6ade97798a1d63d,
title = "A group emotion control system based on reinforcement learning",
abstract = "Recently, ubiquitous computing and related sensor technology have significantly progressed. On the other side, the relationship between human emotion and sensory stimuli has been investigated. With this background, we propose sensory stimuli control system to adjust group emotion to given target emotion. Valence-arousal model was adapted for defining group emotion, and survey of 73-papers and onsite-investigation had done for domain knowledge. The proposed system is based on the partially observable Markov decision process to deal with the uncertain states of group emotion, and reinforcement learning approach to learn the criterion of decision in real time. To evaluate the proposed system, we collected 160-minutes data from kindergarten where the music and math classes are ongoing with 10 prescholers and 1 caregiver are participating. Our system produced 55.17{\%} of accuracy, which outperfomed the original system by 15.51{\%}p.",
author = "Kim, {Kee Hoon} and Cho, {Sung Bae}",
year = "2016",
month = "6",
day = "15",
doi = "10.1109/SOCPAR.2015.7492826",
language = "English",
series = "Proceedings of the 2015 7th International Conference of Soft Computing and Pattern Recognition, SoCPaR 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "303--307",
editor = "Mario Koppen and Muda, {Azah Kamilah} and Kun Ma and Bing Xue and Hideyuki Takagi and Ajith Abraham",
booktitle = "Proceedings of the 2015 7th International Conference of Soft Computing and Pattern Recognition, SoCPaR 2015",
address = "United States",

}

Kim, KH & Cho, SB 2016, A group emotion control system based on reinforcement learning. in M Koppen, AK Muda, K Ma, B Xue, H Takagi & A Abraham (eds), Proceedings of the 2015 7th International Conference of Soft Computing and Pattern Recognition, SoCPaR 2015., 7492826, Proceedings of the 2015 7th International Conference of Soft Computing and Pattern Recognition, SoCPaR 2015, Institute of Electrical and Electronics Engineers Inc., pp. 303-307, 7th International Conference of Soft Computing and Pattern Recognition, SoCPaR 2015, Fukuoka, Japan, 15/11/13. https://doi.org/10.1109/SOCPAR.2015.7492826

A group emotion control system based on reinforcement learning. / Kim, Kee Hoon; Cho, Sung Bae.

Proceedings of the 2015 7th International Conference of Soft Computing and Pattern Recognition, SoCPaR 2015. ed. / Mario Koppen; Azah Kamilah Muda; Kun Ma; Bing Xue; Hideyuki Takagi; Ajith Abraham. Institute of Electrical and Electronics Engineers Inc., 2016. p. 303-307 7492826 (Proceedings of the 2015 7th International Conference of Soft Computing and Pattern Recognition, SoCPaR 2015).

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

TY - GEN

T1 - A group emotion control system based on reinforcement learning

AU - Kim, Kee Hoon

AU - Cho, Sung Bae

PY - 2016/6/15

Y1 - 2016/6/15

N2 - Recently, ubiquitous computing and related sensor technology have significantly progressed. On the other side, the relationship between human emotion and sensory stimuli has been investigated. With this background, we propose sensory stimuli control system to adjust group emotion to given target emotion. Valence-arousal model was adapted for defining group emotion, and survey of 73-papers and onsite-investigation had done for domain knowledge. The proposed system is based on the partially observable Markov decision process to deal with the uncertain states of group emotion, and reinforcement learning approach to learn the criterion of decision in real time. To evaluate the proposed system, we collected 160-minutes data from kindergarten where the music and math classes are ongoing with 10 prescholers and 1 caregiver are participating. Our system produced 55.17% of accuracy, which outperfomed the original system by 15.51%p.

AB - Recently, ubiquitous computing and related sensor technology have significantly progressed. On the other side, the relationship between human emotion and sensory stimuli has been investigated. With this background, we propose sensory stimuli control system to adjust group emotion to given target emotion. Valence-arousal model was adapted for defining group emotion, and survey of 73-papers and onsite-investigation had done for domain knowledge. The proposed system is based on the partially observable Markov decision process to deal with the uncertain states of group emotion, and reinforcement learning approach to learn the criterion of decision in real time. To evaluate the proposed system, we collected 160-minutes data from kindergarten where the music and math classes are ongoing with 10 prescholers and 1 caregiver are participating. Our system produced 55.17% of accuracy, which outperfomed the original system by 15.51%p.

UR - http://www.scopus.com/inward/record.url?scp=84979297322&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84979297322&partnerID=8YFLogxK

U2 - 10.1109/SOCPAR.2015.7492826

DO - 10.1109/SOCPAR.2015.7492826

M3 - Conference contribution

AN - SCOPUS:84979297322

T3 - Proceedings of the 2015 7th International Conference of Soft Computing and Pattern Recognition, SoCPaR 2015

SP - 303

EP - 307

BT - Proceedings of the 2015 7th International Conference of Soft Computing and Pattern Recognition, SoCPaR 2015

A2 - Koppen, Mario

A2 - Muda, Azah Kamilah

A2 - Ma, Kun

A2 - Xue, Bing

A2 - Takagi, Hideyuki

A2 - Abraham, Ajith

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Kim KH, Cho SB. A group emotion control system based on reinforcement learning. In Koppen M, Muda AK, Ma K, Xue B, Takagi H, Abraham A, editors, Proceedings of the 2015 7th International Conference of Soft Computing and Pattern Recognition, SoCPaR 2015. Institute of Electrical and Electronics Engineers Inc. 2016. p. 303-307. 7492826. (Proceedings of the 2015 7th International Conference of Soft Computing and Pattern Recognition, SoCPaR 2015). https://doi.org/10.1109/SOCPAR.2015.7492826