Noise‐aware dictionary‐learning‐based sparse representation framework for detection and removal of single and combined noises from ECG signal

Abstract

Automatic electrocardiogram (ECG) signal enhancement has become a crucial pre-processing step in most ECG signal analysis applications. In this Letter, the authors propose an automated noise-aware dictionary learning-based generalised ECG signal enhancement framework which can automatically learn the dictionaries based on the ECG noise type for effective representation of ECG signal and noises, and can reduce the computational load of sparse representation-based ECG enhancement system. The proposed framework consists of noise detection and identification, noise-aware dictionary learning, sparse signal decomposition and reconstruction. The noise detection and identification is performed based on the moving average filter, first-order difference, and temporal features such as number of turning points, maximum absolute amplitude, zerocrossings, and autocorrelation features. The representation dictionary is learned based on the type of noise identified in the previous stage. The proposed framework is evaluated using noise-free and noisy ECG signals. Results demonstrate that the proposed method can significantly reduce computational load as compared with conventional dictionary learning-based ECG denoising approaches. Further, comparative results show that the method outperforms existing methods in automatically removing noises such as baseline wanders, power-line interference, muscle artefacts and their combinations without distorting the morphological content of local waves of ECG signal.

Hybrid approach for ECG signal enhancement using dictionary learning‐based sparse representation

“…However, in practical, ECG signals are contaminated with several artefacts during acquisition and transmission [4]. The commonly existing noises in a clinical ECG are baseline wander (BW), white Gaussian noise (WGN), power‐line interference (PLI) and muscle artefact (MA) [5]. BW is a low‐frequency noise which fluctuates the baseline of the ECG record from zero value.…”

“…Finally, noises are separated from the signal by using the sparse vectors and corresponding dictionaries. The sparse representation‐based denoising scheme proposed by Satija et al [5] uses elementary sine and cosine waveforms for generation of dictionaries corresponding to noises and ECG components. The applied PLI dictionary contains a limited number of atoms which include only the frequency range of 47–53 Hz.…”

“…Hence, the introduction of a regularisation parameter () is considered which controls the operation of BPDN. In this work, the value of is empirically chosen 0.1 and for BW/PLI filters and WGN/MA filters, respectively, as in [5, 24]. The details of BP and BPDN are presented in [23].…”

An Algorithm Based on Sparse Decomposition for Estimating Harmonic and Interharmonic Components of Stationary Signals in Power Systems

“…In the last decade, numerous applications in signal processing have used the Sparse Signal Decomposition (SSD) technique with Overcomplete Hybrid Dictionary (OHD) for detection and classification of modulated signals [16], analysis of ultrasound signals [17], [18], automatic target recognition in radar images [19], denoising and analysis of biomedical signals as electrocardiogram (ECG) [20], [21] and electroencephalogram (EEG) [22], among others. In the analysis of signals in power systems, [23] presents a study for compression and denoising of signals with power quality disturbances, while [24] does the detection and classification of these disturbances.…”

An Efficient Method to Learn Overcomplete Multi-Scale Dictionaries of ECG Signals

“…Throughout the paper, we concentrate on the description of the proposed method without focusing on any particular application. However, note that the constructed dictionary can be useful in many practical applications: lossy compression of ECG signals for their storage and transmission [17,20], denoising of ECGs contaminated by different types of interferences using sparse inference techniques [23], compressed sampling and sparse inference for heart rate variability analysis [24], sparse coding for atrial fibrillation (AF) classification [25], etc.…”