Multi-Day Analysis of Wrist Electromyogram-Based Biometrics for Authentication and Personal Identification

Abstract

Recently, electromyogram (EMG) has been proposed for addressing some key limitations of current biometrics. Wrist-worn wearable sensors can provide a non-invasive method for acquiring EMG signals for gesture recognition or biometric applications. EMG signals contain individuals' information and can facilitate multi-length codes or passwords (for example, by performing a combination of hand gestures). However, current EMG-based biometric research has two critical limitations: small subject-pool for analysis and limited to single-session datasets. In this study, wrist EMG data were collected from 43 participants over three different days (Days 1, 8, and 29) while performing static hand/wrist gestures. Multi-day analysis involving training data and testing data from different days was employed to test the robustness of the EMG-based biometrics. The multi-day authentication resulted in a median equal error rate (EER) of 0.039 when the code is unknown, and an EER of 0.068 when the code is known to intruders. The multi-day identification achieved a median rank-5 accuracy of 93.0%. With intruders, a threshold-based identification resulted in a median rank-5 accuracy of 91.7% while intruders were denied access at a median rejection rate of 71.7%. These results demonstrated the potential of EMG-based biometrics in practical applications and bolster further research on EMG-based biometrics.