A method for estimating hunger degree based on meal and exercise logs

Isamu Sugita, Morihiko Tamai, Yutaka Arakawa, Keiichi Yasumoto

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

Abstract

If temporal variation of a person's hunger degree could be estimated, it would be possible to adjust his/her eating habits and/or prevent obesity. It is well-known that there is a negative correlation between a hunger degree and a blood glucose level. However, it is hard to measure a person's blood glucose level anytime and anywhere, because it relies usually on an invasive method (e.g., blood sampling). This paper proposes a method for estimating a person's hunger degree in a non-invasive way. Our proposed method is composed of (1) a blood glucose level estimation model based on logs of meals and exercises, and (2) a hunger degree estimation model based on the estimated glucose level. The former model is constructed by correlating an actual blood glucose level and logs of meals and exercises with a machine learning technique. Here, the actual blood glucose level is measured by a commercial blood glucose meter invasively. The latter model is constructed by associating the measured blood glucose level with a subjective hunger degree. We also design and develop a mobile application for facilitating a user to easily record meals and exercises information. Through an experiment with a subject, we confirmed that our system can estimate a blood glucose level within about 14% mean percentage error and finally estimate hunger degree within about 1.3 levels mean error among 10 levels.

Original languageEnglish
Title of host publicationProceedings of the 2014 4th International Conference on Wireless Mobile Communication and Healthcare - "Transforming Healthcare Through Innovations in Mobile and Wireless Technologies", MOBIHEALTH 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages11-14
Number of pages4
ISBN (Electronic)9781631900143
DOIs
Publication statusPublished - Jan 20 2015
Externally publishedYes
Event4th International Conference on Wireless Mobile Communication and Healthcare, MOBIHEALTH 2014 - Athens, Greece
Duration: Nov 3 2014Nov 5 2014

Publication series

NameProceedings of the 2014 4th International Conference on Wireless Mobile Communication and Healthcare - "Transforming Healthcare Through Innovations in Mobile and Wireless Technologies", MOBIHEALTH 2014

Conference

Conference4th International Conference on Wireless Mobile Communication and Healthcare, MOBIHEALTH 2014
CountryGreece
CityAthens
Period11/3/1411/5/14

Fingerprint

Hunger
Glucose
Meals
Blood Glucose
Blood
Mobile Applications
Feeding Behavior
Learning systems
Obesity
Sampling

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Computer Science Applications
  • Electrical and Electronic Engineering
  • Health Informatics

Cite this

Sugita, I., Tamai, M., Arakawa, Y., & Yasumoto, K. (2015). A method for estimating hunger degree based on meal and exercise logs. In Proceedings of the 2014 4th International Conference on Wireless Mobile Communication and Healthcare - "Transforming Healthcare Through Innovations in Mobile and Wireless Technologies", MOBIHEALTH 2014 (pp. 11-14). [7015896] (Proceedings of the 2014 4th International Conference on Wireless Mobile Communication and Healthcare - "Transforming Healthcare Through Innovations in Mobile and Wireless Technologies", MOBIHEALTH 2014). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/MOBIHEALTH.2014.7015896

A method for estimating hunger degree based on meal and exercise logs. / Sugita, Isamu; Tamai, Morihiko; Arakawa, Yutaka; Yasumoto, Keiichi.

Proceedings of the 2014 4th International Conference on Wireless Mobile Communication and Healthcare - "Transforming Healthcare Through Innovations in Mobile and Wireless Technologies", MOBIHEALTH 2014. Institute of Electrical and Electronics Engineers Inc., 2015. p. 11-14 7015896 (Proceedings of the 2014 4th International Conference on Wireless Mobile Communication and Healthcare - "Transforming Healthcare Through Innovations in Mobile and Wireless Technologies", MOBIHEALTH 2014).

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

Sugita, I, Tamai, M, Arakawa, Y & Yasumoto, K 2015, A method for estimating hunger degree based on meal and exercise logs. in Proceedings of the 2014 4th International Conference on Wireless Mobile Communication and Healthcare - "Transforming Healthcare Through Innovations in Mobile and Wireless Technologies", MOBIHEALTH 2014., 7015896, Proceedings of the 2014 4th International Conference on Wireless Mobile Communication and Healthcare - "Transforming Healthcare Through Innovations in Mobile and Wireless Technologies", MOBIHEALTH 2014, Institute of Electrical and Electronics Engineers Inc., pp. 11-14, 4th International Conference on Wireless Mobile Communication and Healthcare, MOBIHEALTH 2014, Athens, Greece, 11/3/14. https://doi.org/10.1109/MOBIHEALTH.2014.7015896
Sugita I, Tamai M, Arakawa Y, Yasumoto K. A method for estimating hunger degree based on meal and exercise logs. In Proceedings of the 2014 4th International Conference on Wireless Mobile Communication and Healthcare - "Transforming Healthcare Through Innovations in Mobile and Wireless Technologies", MOBIHEALTH 2014. Institute of Electrical and Electronics Engineers Inc. 2015. p. 11-14. 7015896. (Proceedings of the 2014 4th International Conference on Wireless Mobile Communication and Healthcare - "Transforming Healthcare Through Innovations in Mobile and Wireless Technologies", MOBIHEALTH 2014). https://doi.org/10.1109/MOBIHEALTH.2014.7015896
Sugita, Isamu ; Tamai, Morihiko ; Arakawa, Yutaka ; Yasumoto, Keiichi. / A method for estimating hunger degree based on meal and exercise logs. Proceedings of the 2014 4th International Conference on Wireless Mobile Communication and Healthcare - "Transforming Healthcare Through Innovations in Mobile and Wireless Technologies", MOBIHEALTH 2014. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 11-14 (Proceedings of the 2014 4th International Conference on Wireless Mobile Communication and Healthcare - "Transforming Healthcare Through Innovations in Mobile and Wireless Technologies", MOBIHEALTH 2014).
@inproceedings{b0aad5de0a0f4505ab0945fd1eb990f7,
title = "A method for estimating hunger degree based on meal and exercise logs",
abstract = "If temporal variation of a person's hunger degree could be estimated, it would be possible to adjust his/her eating habits and/or prevent obesity. It is well-known that there is a negative correlation between a hunger degree and a blood glucose level. However, it is hard to measure a person's blood glucose level anytime and anywhere, because it relies usually on an invasive method (e.g., blood sampling). This paper proposes a method for estimating a person's hunger degree in a non-invasive way. Our proposed method is composed of (1) a blood glucose level estimation model based on logs of meals and exercises, and (2) a hunger degree estimation model based on the estimated glucose level. The former model is constructed by correlating an actual blood glucose level and logs of meals and exercises with a machine learning technique. Here, the actual blood glucose level is measured by a commercial blood glucose meter invasively. The latter model is constructed by associating the measured blood glucose level with a subjective hunger degree. We also design and develop a mobile application for facilitating a user to easily record meals and exercises information. Through an experiment with a subject, we confirmed that our system can estimate a blood glucose level within about 14{\%} mean percentage error and finally estimate hunger degree within about 1.3 levels mean error among 10 levels.",
author = "Isamu Sugita and Morihiko Tamai and Yutaka Arakawa and Keiichi Yasumoto",
year = "2015",
month = "1",
day = "20",
doi = "10.1109/MOBIHEALTH.2014.7015896",
language = "English",
series = "Proceedings of the 2014 4th International Conference on Wireless Mobile Communication and Healthcare - {"}Transforming Healthcare Through Innovations in Mobile and Wireless Technologies{"}, MOBIHEALTH 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "11--14",
booktitle = "Proceedings of the 2014 4th International Conference on Wireless Mobile Communication and Healthcare - {"}Transforming Healthcare Through Innovations in Mobile and Wireless Technologies{"}, MOBIHEALTH 2014",
address = "United States",

}

TY - GEN

T1 - A method for estimating hunger degree based on meal and exercise logs

AU - Sugita, Isamu

AU - Tamai, Morihiko

AU - Arakawa, Yutaka

AU - Yasumoto, Keiichi

PY - 2015/1/20

Y1 - 2015/1/20

N2 - If temporal variation of a person's hunger degree could be estimated, it would be possible to adjust his/her eating habits and/or prevent obesity. It is well-known that there is a negative correlation between a hunger degree and a blood glucose level. However, it is hard to measure a person's blood glucose level anytime and anywhere, because it relies usually on an invasive method (e.g., blood sampling). This paper proposes a method for estimating a person's hunger degree in a non-invasive way. Our proposed method is composed of (1) a blood glucose level estimation model based on logs of meals and exercises, and (2) a hunger degree estimation model based on the estimated glucose level. The former model is constructed by correlating an actual blood glucose level and logs of meals and exercises with a machine learning technique. Here, the actual blood glucose level is measured by a commercial blood glucose meter invasively. The latter model is constructed by associating the measured blood glucose level with a subjective hunger degree. We also design and develop a mobile application for facilitating a user to easily record meals and exercises information. Through an experiment with a subject, we confirmed that our system can estimate a blood glucose level within about 14% mean percentage error and finally estimate hunger degree within about 1.3 levels mean error among 10 levels.

AB - If temporal variation of a person's hunger degree could be estimated, it would be possible to adjust his/her eating habits and/or prevent obesity. It is well-known that there is a negative correlation between a hunger degree and a blood glucose level. However, it is hard to measure a person's blood glucose level anytime and anywhere, because it relies usually on an invasive method (e.g., blood sampling). This paper proposes a method for estimating a person's hunger degree in a non-invasive way. Our proposed method is composed of (1) a blood glucose level estimation model based on logs of meals and exercises, and (2) a hunger degree estimation model based on the estimated glucose level. The former model is constructed by correlating an actual blood glucose level and logs of meals and exercises with a machine learning technique. Here, the actual blood glucose level is measured by a commercial blood glucose meter invasively. The latter model is constructed by associating the measured blood glucose level with a subjective hunger degree. We also design and develop a mobile application for facilitating a user to easily record meals and exercises information. Through an experiment with a subject, we confirmed that our system can estimate a blood glucose level within about 14% mean percentage error and finally estimate hunger degree within about 1.3 levels mean error among 10 levels.

UR - http://www.scopus.com/inward/record.url?scp=84925372846&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84925372846&partnerID=8YFLogxK

U2 - 10.1109/MOBIHEALTH.2014.7015896

DO - 10.1109/MOBIHEALTH.2014.7015896

M3 - Conference contribution

AN - SCOPUS:84925372846

T3 - Proceedings of the 2014 4th International Conference on Wireless Mobile Communication and Healthcare - "Transforming Healthcare Through Innovations in Mobile and Wireless Technologies", MOBIHEALTH 2014

SP - 11

EP - 14

BT - Proceedings of the 2014 4th International Conference on Wireless Mobile Communication and Healthcare - "Transforming Healthcare Through Innovations in Mobile and Wireless Technologies", MOBIHEALTH 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -