Downloads: 61

Files in This Item:
File Description SizeFormat 
2251-1865_CBP17.35.pdf898.41 kBAdobe PDFView/Open
Title: An Estimation Method of Intellectual Work Performance by Using Physiological Indices
Authors: Kunimasa, Shutaro
Seo, Kyoichi
Shimoda, Hiroshi  kyouindb  KAKEN_id  orcid https://orcid.org/0000-0002-5231-4955 (unconfirmed)
Ishii, Hirotake  kyouindb  KAKEN_id  orcid https://orcid.org/0000-0002-5638-4862 (unconfirmed)
Author's alias: 國政, 秀太郎
瀬尾, 恭一
下田, 宏
石井, 裕剛
Keywords: Intellectual Productivity
Machine Learning
Pyshiological Indices
Pupil Diameter
Heart Rate Variability
Issue Date: 2017
Publisher: Global Science & Technology Forum (GSTF)
Journal title: 6th Annual International Conference on Cognitive and Behavioral Psychology
Volume: 6
Start page: 111
End page: 117
Abstract: In order to evaluate the intellectual productivity quantitatively, most of conventional studies have utilized task performance of cognitive tasks. Meanwhile, more and more studies use physiological indices which reflect cognitive load so as to evaluate the intellectual productivity quantitatively. In this study, the method which evaluates task performance of intellectual workers by using several physiological indices (pupil diameter and heart rate variability) has been proposed. As estimation models of task performance, two machine learning models, Support Vector Regression (SVR) and Random Forests (RF), have been employed. As the result of a subject experiment, it was found that coefficient of determination (R²) of SVR was 0.875 and higher than that of RF (p<0.01). The result suggested that pupil diameter and heart rate variability were effective as the explanatory variables and SVR estimation was also effective in task performance evaluation.
Description: 6th Annual International Conference on Cognitive and Behavioral Psychology (CBP2017): Mar 6, 2017- Mar 7, 2017, Singapore.
Rights: GSTF © 2017. By default, GSTF publishes these articles under a Creative Commons Attribution NonCommercial (CC-BY-NC 3.0) license that allows reuse subject only to the use being non-commercial and to the article being fully attributed (http://creativecommons.org/licenses/by-nc/3.0) to GSTF. Articles funded by certain organizations that mandate publication with a Creative Commons Attribution (CC BY 3.0) license, which may require reuse for commercial purposes are allowed, subject to the article being fully attributed to GSTF.
URI: http://hdl.handle.net/2433/236029
DOI(Published Version): 10.5176/2251-1865_CBP17.35
Appears in Collections:Journal Articles

Show full item record

Export to RefWorks


Export Format: 


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.