Research Area:  Machine Learning
Thanks to their ability to monitor physical activity and health-related parameters, wearable devices are becoming more and more popular. In addition to what they already offer, an interesting capability achievable through such devices is biometric recognition. The physiological traits recorded by wearable devices may in fact possess distinctive properties which could allow to recognize their legitimate users, and detect unauthorized usage. In this paper, the most recent advances accomplished in this field are reviewed, and a critical analysis on the current state of the art, as well as on the issues still open, is provided.
Keywords:  
Biometric Recognition
Wearable Devices
Deep Learning
Machine Learning
Author(s) Name:  Emanuele Maiorana
Journal name:  Pattern Recognition Letters
Conferrence name:  
Publisher name:  Elsevier
DOI:  10.1016/j.patrec.2022.03.002
Volume Information:  Volume 156, April 2022, Pages 29-37
Paper Link:   https://www.sciencedirect.com/science/article/abs/pii/S0167865522000617