Multi-factor authentication for improved efficiency in ECG: Based login

Abstract

Electrocardiogram (ECG) based biometrics have proven to be a reliable source of identification. ECG can now be measured off-the-person, requiring nothing more than dry electrodes or conductive fabrics to acquire a usable ECG signal. However, identification still has a relatively poor performance when using large user databases. In this paper we suggest using ECG authentication associated with a smartphone security token in order to improve performance and decrease the time required for the recognition. This paper reposts the implementation of this technique in a user authentication scenario for a Windows login using normal Bluetooth (BT) and Bluetooth Low Energy (BLE). This paper also uses Intel Edison’s mobility features to create a more versatile environment. Results proved our solution to be feasible and present improvements in authentication times when compared to a simple ECG identification