Wearable technology has great potential to develop human-centric healthcare applications. It reshapes our lifestyle by providing information related to physical activities, sleep monitoring, or heartbeat rhythms. In this paper, we present an innovative model for oral healthcare, which is prevention-focused to notify individuals about cleaning teeth activity. It is based on a wrist-worn accelerometer device and has two components—first, a computationally lightweight feature extractor—secondly, a robust feed-forward neural network to recognize the cleaning teeth activity. The model performance is measured using standard performance metric F_1-score (i.e., 98), which shows the applicability in a real-life scenario. The trained model can reside inside the smartwatch as a wrist-worn wearable. It would generate personalized notifications if s/he skipped the toothbrush activity. Furthermore, it notifies the users to change the toothbrush after three months, reducing the cognitive burden.
|Name||Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC): Proceedings|
|Conference||44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2022|
|Period||11/07/2022 → 15/07/2022|
- Wearable device
- Oral Health
- Machine Learning