Research Article
Daily Health Condition Estimation Using a Smart Toothbrush with Halitosis Sensor
@INPROCEEDINGS{10.1007/978-3-030-94822-1_43, author={Satoshi Yoshimura and Teruhiro Mizumoto and Yuki Matsuda and Keita Ueda and Akira Takeyama}, title={Daily Health Condition Estimation Using a Smart Toothbrush with Halitosis Sensor}, proceedings={Mobile and Ubiquitous Systems: Computing, Networking and Services. 18th EAI International Conference, MobiQuitous 2021, Virtual Event, November 8-11, 2021, Proceedings}, proceedings_a={MOBIQUITOUS}, year={2022}, month={2}, keywords={Recovery estimation Smart toothbrush Measurement system}, doi={10.1007/978-3-030-94822-1_43} }- Satoshi Yoshimura
Teruhiro Mizumoto
Yuki Matsuda
Keita Ueda
Akira Takeyama
Year: 2022
Daily Health Condition Estimation Using a Smart Toothbrush with Halitosis Sensor
MOBIQUITOUS
Springer
DOI: 10.1007/978-3-030-94822-1_43
Abstract
The number of occupational injury claims and certifications for mental disorders increases every year. Therefore, the Ministry of Health, Labour and Welfare of Japan (MHLW) has mandated annual stress checks as a countermeasure. This gives rise to the having a daily health measurement using IoT devices. However, it has been found that managing multiple devices and active measurement behavior decreases users’ motivation. This paper proposes a health measurement system that can be integrated with traditional brushing tools enabling a smooth gauging of health measures. This is done while people are performing their daily teeth brushing activity without any extra overhead. The proposed method estimates the recovery index for fatigue based on halitosis collecting by a smart toothbrush with a halitosis sensor. To evaluate the proposed method, we collected halitosis data and questionnaires about recovery index from 12 subjects every day for approximately two months and constructed a model to estimate each item of the questionnaires by Random Forest based on the halitosis data. As a result, we found a significant difference between the halitosis data and two measures of the recovery experience (MA and PD); furthermore, we achieved MA with an f-score of 0.60, PD with an F-score of 0.58 for three value classification, and sleep quality with an F-score of 0.71 with binary classification.
