Fetal ECG extraction using hybrid BSS techniques

In the task of extracting the fetal ECG from abdominal ECG, often blind source separation is used as an intermediate step. To solve this problem is generally employed PCA and ICA. The COMBI and MULTI-COMBI algorithms offer novel schemes for combining PCA and ICA, enabling exploit the strengths of both techniques. In this work, the performance of the algorithms COMBI, MULTICOMBI, EFICA and traditional JADE algorithm are compared. We used a semi-synthetic database. In all case, it is found that the COMBI and MULTICOMBI algorithms show better performance than the JADE, and EFICA algorithms.