Fusion of gait and ECG for biometric user authentication

Abstract

A new multi-modal biometric authentication approach using gait and electrocardiogram (ECG) signals as biometric traits is proposed. The individual comparison scores derived from the gait and ECG are normalized using several methods (min-max, z-score, median absolute deviation, tangent hyperbolic) and then four fusion approaches (simple sum, user-weighting, maximum score and minimum core) are applied. Gait samples are obtained by using a inbuilt accelerometer sensor from a mobile device attached to the hip. ECG signals are collected by a wireless ECG sensor, which is based on a 2 led ECG signals attached on the breast. The fusion results of these two biometrics show an improved performance and a large step closer for user authentication for biometric user authentication.