Lourenço, AndréSilva, HugoFred, Ana2013-10-152013-10-152012Lourenço, André; SILVA, Hugo; FRED, Ana - ECG-Based biometrics: a real time classification approach. 2012 IEEE International Workshop on Machine Learning for Signal Processing. ISBN 978-1-4673-1026-0. (2013).978-1-4673-1026-0http://hdl.handle.net/10400.21/2732Behavioral biometrics is one of the areas with growing interest within the biosignal research community. A recent trend in the field is ECG-based biometrics, where electrocardiographic (ECG) signals are used as input to the biometric system. Previous work has shown this to be a promising trait, with the potential to serve as a good complement to other existing, and already more established modalities, due to its intrinsic characteristics. In this paper, we propose a system for ECG biometrics centered on signals acquired at the subject's hand. Our work is based on a previously developed custom, non-intrusive sensing apparatus for data acquisition at the hands, and involved the pre-processing of the ECG signals, and evaluation of two classification approaches targeted at real-time or near real-time applications. Preliminary results show that this system leads to competitive results both for authentication and identification, and further validate the potential of ECG signals as a complementary modality in the toolbox of the biometric system designer.engBiometric SystemsECG signalReal Time Recognition SystemsSVM classifiersIdentificationconference object