Presentation | 2023-03-15 Real-time stress detection using Yuragi learning by multimodal integration of living-body information Risa Yoshida, Yuichi Ohsita, Masayuki Murata, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In recent years, psychological fatigue based on the working environment and mental strain has become an issue. Therefore, we believe that real-time detection of stress using multiple living-body information that can be acquired from wearable sensors can promote rest. However, such living-body information measured by wearable devices contains noise. In addition individual differences exist in such living-body information. In this paper, we propose a real-time stress detection method that can handle noise included in the monitored information and the individual differences. Our approach is based on ”Yuragi learning” and multimodal integration. Also, our methods select the information for each person and exclude the information that cannot distinguish the stress state. In this paper, we demonstrate that our method detect stress states accurately through experiments.The results show that our method can detect stress accurately, while the methods without selecting modalities and without avoiding using results with low confidence cause false negatives and false positives. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Living-body information / Real-time stress detection / Yuragi learning / BAM (Bayesian Attractor Model) / Multimodal integration |
Paper # | MBE2022-68 |
Date of Issue | 2023-03-06 (MBE) |
Conference Information | |
Committee | NC / MBE |
---|---|
Conference Date | 2023/3/13(3days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | The Univ. of Electro-Communications |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Brain architecture, General |
Chair | Hiroshi Yamakawa(Univ of Tokyo) / Junichi Hori(Niigata Univ.) |
Vice Chair | Hirokazu Tanaka(Tokyo City Univ.) / Hisashi Yoshida(Kinki Univ.) |
Secretary | Hirokazu Tanaka(NTT) / Hisashi Yoshida(NICT) |
Assistant | Yoshimasa Tawatsuji(Waseda Univ.) / Tomoki Kurikawa(KMU) / Emi Yuda(Tohoku Univ) / Miki Kaneko(Osaka Univ.) |
Paper Information | |
Registration To | Technical Committee on Neurocomputing / Technical Committee on ME and Bio Cybernetics |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Real-time stress detection using Yuragi learning by multimodal integration of living-body information |
Sub Title (in English) | |
Keyword(1) | Living-body information |
Keyword(2) | Real-time stress detection |
Keyword(3) | Yuragi learning |
Keyword(4) | BAM (Bayesian Attractor Model) |
Keyword(5) | Multimodal integration |
1st Author's Name | Risa Yoshida |
1st Author's Affiliation | Osaka University(Osaka Univ.) |
2nd Author's Name | Yuichi Ohsita |
2nd Author's Affiliation | Osaka University(Osaka Univ.) |
3rd Author's Name | Masayuki Murata |
3rd Author's Affiliation | Osaka University(Osaka Univ.) |
Date | 2023-03-15 |
Paper # | MBE2022-68 |
Volume (vol) | vol.122 |
Number (no) | MBE-424 |
Page | pp.pp.49-54(MBE), |
#Pages | 6 |
Date of Issue | 2023-03-06 (MBE) |