An Improved Model-Based Bayesian Framework for ECG Processing in Non-Stationary Environments

Extended Kalman filter (EKF) is a well-known nonlinear Bayesian framework that has been deployed in various fields of ECG processing. However, it’s not very effective in removing non-stationary noises such as muscle artifacts (MA) which are common in ECG recordings. This paper addresses this issue by proposing a new ECG dynamic model (EDM) and a novel formulation for EKF which improves its performance in non-stationary environments. In the new EDM, the measurement model is modified to include non-Gaussian, non-stationary additive noises as well as stationary ones. The proposed formulation for EKF algorithm in this paper enables it to perform better than standard EKF in removing non-stationary contaminants. The proposed filter also preserves the clinical characteristics of ECG signals better than standard EKF. In order to show the effectiveness of the proposed EKF algorithm, its denoising performance was evaluated on MIT-BIH Normal Sinus Rhythm database (NSRDB) in the presence of two different types of non-stationary contaminants; synthetic pink noise and real muscle artifact noise. The results showed that the proposed EKF framework in this paper has a significant outperformance over the standard EKF framework in non-stationary environments from both SNR improvement and MSEWPRD viewpoints.