著者

Haoyu Zhuang Liqiang Xu Yuuki Nishiyama Kaoru Sezaki

雑誌

研究報告ユビキタスコンピューティングシステム(UBI) (ISSN:21888698)

巻号頁・発行日

vol.2022-UBI-75, no.27, pp.1-7, 2022-08-29

---

Under the epidemic of COVID-19, it is important to automatically detect epidemic protective behaviors without a user's intention. Existing studies utilized only sensor data from IMU for detecting epidemic protection behaviors. However, the performance of the classification for similar behaviors could be unsatisfactory due to the single data dimension. It is well known that washing hands and hand sterilization are essential personal hygiene behaviors. In this paper, we use multiple sensor data from an off-the-shelf smartwatch and smartphone for detecting these three behaviors. Our performance evaluation indicated that our proposed method has improved accuracy for classifying the target epidemic protective behaviors over previous methods. Furthermore, for applying our method in reality, we developed a prototype for detecting these behaviors on a wearable device, which allows us to utilize our method widely in health habits monitoring.