Application of Deep Learning for Ergonomic Data Augmentation and Human State Recognition

Yoshihiro Banchi; Takashi Kawai; Nagakazu Tomino; Tomohiro Yamagata

doi:10.1007/978-3-030-74611-7_68

Application of Deep Learning for Ergonomic Data Augmentation and Human State Recognition

Yoshihiro Banchi^*, Takashi Kawai, Nagakazu Tomino, Tomohiro Yamagata

^*Corresponding author for this work

School of Fundamental Science and Engineering

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

Abstract

In ergonomic experiments, a small number of participants is often a problem because a sufficient amount of data is not obtained. In recent years, human state recognition is wide-spread, and estimating the human state from biological information acquired from a wearable device, is useful for improving living behavior. While it is necessary to collect a sufficient amount of data in order to perform state estimation with a certain degree of accuracy, collecting the amount of data requires a considerable cost. This study attempted to expand physiological and psychological data using deep learning. Specifically, information on physiological indicators was added to ACGAN. From the verification using the actual experimental results, it was found that the accuracy of recognizing the human state was improved by using the augmented data compared to the case of learning with a small number of original data.

Original language	English
Title of host publication	Proceedings of the 21st Congress of the International Ergonomics Association, IEA 2021 - Healthcare and Healthy Work
Editors	Nancy L. Black, W. Patrick Neumann, Ian Noy
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	504-507
Number of pages	4
ISBN (Print)	9783030746100
DOIs	https://doi.org/10.1007/978-3-030-74611-7_68
Publication status	Published - 2021
Event	21st Congress of the International Ergonomics Association, IEA 2021 - Virtual, Online Duration: 2021 Jun 13 → 2021 Jun 18

Publication series

Name	Lecture Notes in Networks and Systems
Volume	222 LNNS
ISSN (Print)	2367-3370
ISSN (Electronic)	2367-3389

Conference

Conference	21st Congress of the International Ergonomics Association, IEA 2021
City	Virtual, Online
Period	21/6/13 → 21/6/18

Keywords

Data augmentation
Deep learning
Human state recognition

ASJC Scopus subject areas

Control and Systems Engineering
Signal Processing
Computer Networks and Communications

Access to Document

10.1007/978-3-030-74611-7_68

Cite this

Banchi, Y., Kawai, T., Tomino, N., & Yamagata, T. (2021). Application of Deep Learning for Ergonomic Data Augmentation and Human State Recognition. In N. L. Black, W. P. Neumann, & I. Noy (Eds.), Proceedings of the 21st Congress of the International Ergonomics Association, IEA 2021 - Healthcare and Healthy Work (pp. 504-507). (Lecture Notes in Networks and Systems; Vol. 222 LNNS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-030-74611-7_68

Application of Deep Learning for Ergonomic Data Augmentation and Human State Recognition. / Banchi, Yoshihiro ; Kawai, Takashi; Tomino, Nagakazu et al.

Proceedings of the 21st Congress of the International Ergonomics Association, IEA 2021 - Healthcare and Healthy Work. ed. / Nancy L. Black; W. Patrick Neumann; Ian Noy. Springer Science and Business Media Deutschland GmbH, 2021. p. 504-507 (Lecture Notes in Networks and Systems; Vol. 222 LNNS).

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

Banchi, Y , Kawai, T, Tomino, N & Yamagata, T 2021, Application of Deep Learning for Ergonomic Data Augmentation and Human State Recognition. in NL Black, WP Neumann & I Noy (eds), Proceedings of the 21st Congress of the International Ergonomics Association, IEA 2021 - Healthcare and Healthy Work. Lecture Notes in Networks and Systems, vol. 222 LNNS, Springer Science and Business Media Deutschland GmbH, pp. 504-507, 21st Congress of the International Ergonomics Association, IEA 2021, Virtual, Online, 21/6/13. https://doi.org/10.1007/978-3-030-74611-7_68

Banchi Y , Kawai T, Tomino N, Yamagata T. Application of Deep Learning for Ergonomic Data Augmentation and Human State Recognition. In Black NL, Neumann WP, Noy I, editors, Proceedings of the 21st Congress of the International Ergonomics Association, IEA 2021 - Healthcare and Healthy Work. Springer Science and Business Media Deutschland GmbH. 2021. p. 504-507. (Lecture Notes in Networks and Systems). doi: 10.1007/978-3-030-74611-7_68

Banchi, Yoshihiro ; Kawai, Takashi ; Tomino, Nagakazu et al. / Application of Deep Learning for Ergonomic Data Augmentation and Human State Recognition. Proceedings of the 21st Congress of the International Ergonomics Association, IEA 2021 - Healthcare and Healthy Work. editor / Nancy L. Black ; W. Patrick Neumann ; Ian Noy. Springer Science and Business Media Deutschland GmbH, 2021. pp. 504-507 (Lecture Notes in Networks and Systems).

@inproceedings{b55094727e604957b47a55eb6f57430c,

title = "Application of Deep Learning for Ergonomic Data Augmentation and Human State Recognition",

abstract = "In ergonomic experiments, a small number of participants is often a problem because a sufficient amount of data is not obtained. In recent years, human state recognition is wide-spread, and estimating the human state from biological information acquired from a wearable device, is useful for improving living behavior. While it is necessary to collect a sufficient amount of data in order to perform state estimation with a certain degree of accuracy, collecting the amount of data requires a considerable cost. This study attempted to expand physiological and psychological data using deep learning. Specifically, information on physiological indicators was added to ACGAN. From the verification using the actual experimental results, it was found that the accuracy of recognizing the human state was improved by using the augmented data compared to the case of learning with a small number of original data.",

keywords = "Data augmentation, Deep learning, Human state recognition",

author = "Yoshihiro Banchi and Takashi Kawai and Nagakazu Tomino and Tomohiro Yamagata",

note = "Publisher Copyright: {\textcopyright} 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.; 21st Congress of the International Ergonomics Association, IEA 2021 ; Conference date: 13-06-2021 Through 18-06-2021",

year = "2021",

doi = "10.1007/978-3-030-74611-7_68",

language = "English",

isbn = "9783030746100",

series = "Lecture Notes in Networks and Systems",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "504--507",

editor = "Black, {Nancy L.} and Neumann, {W. Patrick} and Ian Noy",

booktitle = "Proceedings of the 21st Congress of the International Ergonomics Association, IEA 2021 - Healthcare and Healthy Work",

}

TY - GEN

T1 - Application of Deep Learning for Ergonomic Data Augmentation and Human State Recognition

AU - Banchi, Yoshihiro

AU - Kawai, Takashi

AU - Tomino, Nagakazu

AU - Yamagata, Tomohiro

PY - 2021

Y1 - 2021

N2 - In ergonomic experiments, a small number of participants is often a problem because a sufficient amount of data is not obtained. In recent years, human state recognition is wide-spread, and estimating the human state from biological information acquired from a wearable device, is useful for improving living behavior. While it is necessary to collect a sufficient amount of data in order to perform state estimation with a certain degree of accuracy, collecting the amount of data requires a considerable cost. This study attempted to expand physiological and psychological data using deep learning. Specifically, information on physiological indicators was added to ACGAN. From the verification using the actual experimental results, it was found that the accuracy of recognizing the human state was improved by using the augmented data compared to the case of learning with a small number of original data.

AB - In ergonomic experiments, a small number of participants is often a problem because a sufficient amount of data is not obtained. In recent years, human state recognition is wide-spread, and estimating the human state from biological information acquired from a wearable device, is useful for improving living behavior. While it is necessary to collect a sufficient amount of data in order to perform state estimation with a certain degree of accuracy, collecting the amount of data requires a considerable cost. This study attempted to expand physiological and psychological data using deep learning. Specifically, information on physiological indicators was added to ACGAN. From the verification using the actual experimental results, it was found that the accuracy of recognizing the human state was improved by using the augmented data compared to the case of learning with a small number of original data.

KW - Data augmentation

KW - Deep learning

KW - Human state recognition

UR - http://www.scopus.com/inward/record.url?scp=85111158955&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85111158955&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-74611-7_68

DO - 10.1007/978-3-030-74611-7_68

M3 - Conference contribution

AN - SCOPUS:85111158955

SN - 9783030746100

T3 - Lecture Notes in Networks and Systems

SP - 504

EP - 507

BT - Proceedings of the 21st Congress of the International Ergonomics Association, IEA 2021 - Healthcare and Healthy Work

A2 - Black, Nancy L.

A2 - Neumann, W. Patrick

A2 - Noy, Ian

PB - Springer Science and Business Media Deutschland GmbH

T2 - 21st Congress of the International Ergonomics Association, IEA 2021

Y2 - 13 June 2021 through 18 June 2021

ER -

Application of Deep Learning for Ergonomic Data Augmentation and Human State Recognition

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this