Oral hygiene is very important for a healthy life. Proper toothbrushing is one of the most important measures against dental problems. Poor toothbrushing methods can lead to tooth decay and other gum diseases. Unfortunately, many people do not brush their teeth properly and there is very limited technology available to assist them in compliance with the standard toothbrushing procedure. Sensor-based human activity recognition techniques have seen tremendous growth recently and are being used in various applications. In this work, we treat the compliance to the standard toothbrushing method as an activity recognition problem. We divide the toothbrushing activity into 16 sub-activities and use a machine learning model to recognize those activities. We introduce an off-body sensing solution that uses a detachable Inertial Measurement Unit (IMU), attached to the handle of the brush. The sensor captures the movements of the brush while reaching different parts of the teeth. Then a machine learning pipeline is trained to predict the brushing of different parts of the teeth. We evaluated the performance of the proposed approach in real-world scenarios and performed experiments with 10 different users. We collected our own data set and compared our approach with the wearable-based approach. The results show that our approach performs better than wearable-based approaches and can recognize the toothbrushing activities with 97.15% accuracy. We also evaluated our model for different types of brushes (manual and electric) and the results show that the proposed approach can work independently from the brush types.
Medication non-adherence is a major healthcare challenge globally, with over half of patients with chronic conditions in developed countries failing to follow their prescribed medication regimen. This can lead to poor disease outcomes, increased hospital visits, and a significant financial burden on healthcare systems [1]. These issues have driven a recent wave of research, including the development of smart adherence products [6] that can be incorporated into a patient’s daily life to monitor medication adherence. In this work, we present a radar-based system for user identification while taking medication, which extends our recent work [5]. we conducted preliminary experiments examining semi-medication-taking activities executed by 6 subjects. Our system achieved 80% accuracy in identifying who has taken the medication in a group of 3 subjects.