Denoising and baseline correction of ECG signals using sparse representation

Removing noise and other artifacts in the electrocardiogram (ECG) is a critical preprocessing step for further heart disease analysis and diagnosis. In this paper, we propose a sparse representation based ECG signal denoising and baseline wandering (BW) correction algorithm. Unlike the traditional filtering-based methods, like Fourier or Wavelet transform, which use fixed basis, the proposed algorithm models the ECG signal as superposition of few inner structures plus additive random noise, while those structures can be learned from the input signal or a training set. Using those learned inner structures and their properties, we can accurately approximate the original ECG signal and remove noise and other artifacts like baseline wandering. To demonstrate the robustness and efficacy of the proposed algorithm, we compare it to several state-of-the-art algorithms through both simulated and real-life ECG recordings.