No abstract

The QRS complex is the most distinctive feature in an electrocardiogram (ECG) signal. Therefore, its detection serves as the starting point for various applications, such as detection of other waves and segments, heart-rate calculation, derivation of respiration, etc. In this paper, a novel technique for QRS detection is proposed. The technique is based on the recently proposed synchrosqueezed wavelet transform (SSWT), which is obtained by application of a post-processing technique known as synchrosqueezing to the continuous wavelet transform. Following SSWT, various other processing steps are applied, including a nonlinear mapping technique, which is novel in the context of QRS detection, to finally detect the R-peaks. The proposed algorithm is evaluated on the MIT-BIH arrhythmia database and overall sensitivity, positive predictivity and error rate obtained are 99.92%, 99.93%, and 0.15%, respectively.

No abstract

Detection of QRS complexes in ECG signals is required for various purposes such as determination of heart rate, feature extraction and classification. The problem of automatic QRS detection in ECG signals is complicated by the presence of noise spectrally overlapping with the QRS frequency range. As a solution to this problem, we propose the use of least-squares-optimisation-based smoothing techniques that suppress the noise peaks in the ECG while preserving the QRS complexes. We also propose a novel nonlinear transformation technique that is applied after the smoothing operations, which equalises the QRS amplitudes without boosting the supressed noise peaks. After these preprocessing operations, the R-peaks can finally be detected with high accuracy. The proposed technique has a low computational load and, therefore, it can be used for real-time QRS detection in a wearable device such as a Holter monitor or for fast offline QRS detection. The offline and real-time versions of the proposed technique have been evaluated on the standard MIT-BIH database. The offline implementation is found to perform better than state-of-the-art techniques based on wavelet transforms, empirical mode decomposition, etc. and the real-time implementation also shows improved performance over existing real-time QRS detection techniques.

No abstract