Real-time heartbeat outlier removal in electrocardiogram (ECG) biometrie system

Electrocardiogram signal is prone to noise interference. Processing noisy signals in an automated system such as biometric systems negatively affects its performance. In this paper, we developed a real-time abnormal electrocardiogram heartbeat detection and removal. The proposed technique eliminates outliers in real-time while subjects data are being collected. We used Gaussian mixture model to model normal electrocardiogram heartbeat. A Gaussian mixture of 2 components achieved the least equal error rate of 12% in separating normal from abnormal heartbeats. We utilized this outlier removal method in a biometric system and examined it on a fingertip acquired ECG signals database. The designed biometric system had an equal error rate of 5.94% in comparison to 12.30% in a state of the art approach.