Human identification using ECG feature extracted from innovation signal of Extended Kalman Filter

Electrocardiogram is one of the most prominent cardiac signals being capable to be utilized for medical uses such as arrhythmia detection. Over the years, the feasibility of using this signal for human identification issue has been investigated, and some methods have been proposed. In this Paper a novel approach is proposed for electrocardiogram (ECG) based human identification using Extended Kalman Filter (EKF). The innovation signal of EKF has been considered as feature which is used to classify different subjects. In this paper a general issue, human identification, is summarized to a classification problem in which the proposed features of each subject is calculated, and the classification based on extracted features is done via Artificial Neural Network. In order to assess the proposed method, the algorithm is applied to 10 normal subjects of MIT-BIH Database using single lead data, and a 95.6% human identification rate is reached. The main advantage of the proposed method is that it guarantees high accuracy even in noisy data in comparison to existing methods. EKF is a robust tool used for ECG denoising, and is able to eliminate the noise of signal even in high noise power contaminating the signal. Afterwards noisy data with various SNRs is generated simply by adding artificial white noise to signals. The proposed method is evaluated on noisy data, and the results show that the method is nearly accurate in SNRs above 0dB in normal subjects.