Extracting atrial fibrillation signal from single-lead ECG for wireless monitoring

This paper proposed a novel atrial fibrillation signal extraction algorithm from single-lead ECG for wireless monitoring aims. The proposed method firstly expands single-lead ECG to multidimensional space using the Gaussian function, and then extracts and judge the AF signal using blind source extraction algorithm and power spectral estimation. The experimental results show that the proposed algorithm is feasible and effective. Compared with the template matching method, the proposed method is much less affected by the morphology of ECG and more robust underthe noisy cases. © 2013 Springer-Verlag.