Sparse Representation for Fetal QRS Detection in Abdominal ECG Recordings

In this work, we consider the problem of detection of fetal heart beats from abdominal, non-invasive mixture recordings. We propose a new method for the separation of maternal and fetal beats based on the sparse decomposition in an over-complete dictionary of Gaussian-like functions. To increase the detection capability, we also use Independent Component Analysis (ICA) after maternal template subtraction. We show that the proposed detection method can be applied on the original mixture with a sensitivity close to 95%. Moreover, our method may be used also for single channel abdominal ECG signals, and also used in real-time applications.