No Face-Touch: Exploiting Wearable Devices and Machine Learning for Gesture Detection
S. Marullo, T. Lisini Baldi, G. Paolocci, N. D’Aurizio, D. Prattichizzo
Abstract
Avoiding face-touches has been one of the most common medical recommendations since the beginning of the COVID-19 pandemic. This work aims at providing people with help in contrasting this widespread, yet noxious habit. The solution we present exploits wearable devices to detect hand motions ending up into a face-touch and promptly notify the user exploiting haptic feedback. To this aim, we propose a recurrent neural network taking as input temporal sequences of accelerometer data acquired by a smartwatch worn by the user. The trained RNN (NFT_RNN) achieves good generalization capabilities to data coming from different users, besides a lower false detections rate with respect to a rule-based detection algorithm. The suggested solution is ready-to-use and large-scale deployable, being portable on smartwatches, fitness bands and DIY devices.
BibTeX
@inproceedings{icra2021_nofacetouchexplo,
title = {No Face-Touch: Exploiting Wearable Devices and Machine Learning for Gesture Detection},
author = {S. Marullo and T. Lisini Baldi and G. Paolocci and N. D’Aurizio and D. Prattichizzo},
booktitle = {ICRA 2021},
year = {2021}
}