FaceTouch: Practical Face Touch Detection with a Multimodal Wearable System for Epidemiological Surveillance

Abstract

In this paper, we propose FaceTouch, a low-power and versatile method that enables accurate face touch detection with a multimodal wearable system. FaceTouch consists of two sensing components, an inertial sensor on the wrist and a novel vibration sensor on the finger. We leverage the wrist inertial sensor to detect the face-touch gesture that the hand moves towards the face area. To achieve this goal in a computation-efficient manner, we develop a cascading classification model including three classifiers to filter out irrelevant gestures to significantly extend the battery life while keeping a high recall. Once a face-touch gesture is triggered, we activate the vibration sensor to detect touch events. We implement FaceTouch using commercial off-the-shelf hardware components and evaluate its performance with various user activities and false-positive behaviors. FaceTouch achieves 93.5% F-1 score of face touch detection. The entire system only consumes 60.89 μ W power on average in normal daily usage and 209.15 μ W in extremely heavy usage, which is several magnitudes lower than the state-of-the-art systems, and FaceTouch can continuously detect face-touch events for 79 – 273 days using a small 400 mWh battery depending on usage.