Biometric recognition using wearable devices in real-life settings

The popularity of wearable devices, such as smart glasses, chestbands, and wristbands, is nowadaysrapidly growing, thanks to the fact that they can be used to track physical activity and monitor users’health. Recently, researchers have proposed to exploit their capability to collect physiological signalsfor enabling automatic user recognition. Wearable devices inherently provide the means for detectingtheir unauthorized usage, or for being used as front-end in biometric recognition systems controllingthe access to either physical or virtual locations and services. The present work evaluates the feasi-bility of performing biometric recognition using signals captured by wearable devices, consideringdata collected through off-the-shelf commercial wristbands, and comparing recordings taken duringtwo distinct sessions separated by an average time of 7 days. In more detail, recognition is performedleveraging on electrodermal activity (EDA) and blood volume pulse (BVP), considering measure-ments taken from 17 subjects performing natural activities such as attending or teaching lectures.Several tests have been carried out to determine the most effective representation of the consideredEDA and BVP signals, as well as the most suitable classifier. The best recognition performance hasbeen achieved exploiting convolutional neural networks to extract discriminative characteristics fromthe combined spectrograms of the employed EDA and BVP data, guaranteeing average correct identi-fication rate of 98.58% for test samples lasting 30 seconds.