Reducing Face-Touches to Limit COVID-19 Outbreak: an Overview of Solutions

Face touch monitoring using an instrumented wristband using dynamic time warping and k-nearest neighbours

“…The sensitivity, precision, and accuracy obtained with the DTW-KNN method for detecting the hand gesture and distinguishing the face touch from the confounding gestures in our present study were in the same range with the ones previously obtained for face touch and other type of hand motion. Our obtained sensitivity, precision, and accuracy agreed with the results presented in studies that investigated the validity of face touch detection using wearable sensors [27][28][29][30][31][32][33][34] and in the one that classified smoking gesture using the recordings of a wristworn IMU [16]. Notably, the wrist-worn IMU in our study showed high accuracy in detecting face touch and distinguish it from several confounding gestures performed by eleven participants in our experimental procedure.…”

“…and finger motion with high accuracy, sensitivity, and specificity. Additionally, there are studies that specifically investigated the ability of wearable systems to recognize hand-to-face motion [27][28][29][30][31][32][33][34]. Studies that investigated face touch detection were tabulated and compared to our proposed method in Table 3.…”

“…Studies that investigated face touch detection were tabulated and compared to our proposed method in Table 3. The feasibility of using several methods in detecting and monitoring face touch was investigated in the mentioned studies [27][28][29][30][31][32][33][34]. These studies validated their developed methods using different metrics in the context of their experimental procedure.…”

“…Wearable sensors were also used to detect face touch. Previous research studies proposed methods for face touch detection using an accelerometer, magnetometer, and acoustic-based system and studied the validity of these methods [27][28][29][30][31][32][33]. Marullo et al [27] proposed recurrent neural network (RNN) based methods to detect face touch and provide real-time feedback using accelerometer readouts collected from a smartwatch.…”

“…In this study, 10 participants were instructed to perform face touch and confounding gestures during sitting, standing, and walking trials. Most of the methods available in the literature [27][28][29][30][31][32][33][34] showed high accuracy in detecting face touch during their designed experimental procedure.…”