Electrocardiography Denoising via Sparse Dictionary Learning from Small Datasets

Abstract Wearable electrocardiography monitors, e.g. embedded in textile shirts, offer new approaches in diagnosis but suffers upon limited computational capacities. Hence, we propose and evaluate a lightweight algorithm for electrocardiography denoising via sparse dictionary learning, targeting two types of noise: baseline wander and muscle artifacts. For each type of noise a dictionary is built using K-singular value decomposition. This iterative method alternates between finding a sparse representation for every training signal and then updating every atom of the dictionary on its own. A sparse representation is found using the orthogonal matching pursuit algorithm. The atoms are updated exploiting the properties of the singular value decomposition. For further sparse approximation, we use the basis pursuit denoising algorithm. Electrocardiography data stems from synthetically-generated signals as well as the freely-available Brno University of Technology ECG Quality Database. Noise is added to the signals using the MIT-BIH Noise Stress Database. Our results regarding baseline wander demonstrate that the algorithm outperforms the American Heart Association-recommended bandpass filter w.r.t. signal-to-noise ratio. Moreover, a small number of training data is sufficient for satisfying results which indicates the suitability of the method for wearable hardware with low memory and power specifications.