Abstract
The electrocardiogram (ECG) signals bear fundamental information for making decisions about different kinds of heart diseases. Therefore, many efforts were made during decades to extract features of heartbeats via ECG records with high accuracy and efficiency using different strategies and methods. In this paper, we solve the problem in discrete-time state-space using a novel q-lag unbiased finite impulse response (UFIR) smoother, which we adapt to the ECG signal shape via the time-varying optimal averaging horizon. It is shown that the adaptive UFIR smoother performs better in applications to ECG signals than the standard techniques such as the Savitsky-Golay, wavelet-based, low-pass, band-pass, notch, and median filters. Applications are given for the PhysioBank data benchmark, which contains several records taken from different databases such as the MIT-BIH Arrhythmia (MITDB). A complete statistical analysis is provided via normalized histograms and statistical classifiers. It is shown in a comparison with other methods that the adaptive UFIR smoother has a higher accuracy in denoising, features extraction, and features classification for ECG records with normal rhythm and atrial fibrillation (AF).
Highlights
It is known that the electrocardiogram (ECG) signals bear essential information about different kinds of heart diseases
ECG SIGNAL DATABASE AND MODEL We base our investigation on the MIT-BIH Arrhythmia benchmark [51], which contains several records taken from different databases such as the MIT-BIH Arrhythmia (MITDB)
ECG SIGNAL FEATURES EXTRACTION IN STATE SPACE Features extraction from ECG signals in state space using Algorithm III-C is provided in five stages (Fig. 2): 1) detrending, 2) QRS-complex detection, 3) segmentation, 4) adaptive iterative unbiased finite impulse response (UFIR) smoothing, and 5) windowing of ECG waves
Summary
It is known that the electrocardiogram (ECG) signals bear essential information about different kinds of heart diseases. The modification is akin to the optimal UFIR filter [46], which produces a maximum likelihood estimate [47] Because both these solutions require information about noise, which is not well studied in ECG signals, the use of the UFIR smoother becomes more preferable. The UFIR [43] and Savitsky-Golay [37] smoothers were designed to de-noise signal with no extra information about the ECG signal state required to facilitate features extraction. The iterative UFIR smoother [48] provides much more information than the batch UFIR [43] and Savitsky-Golay [37] structures, its development for features extraction in ECG signals still has not been addresses in the literature that motivates our present work.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
