Bayesian MAP solution of the Inverse ECG problem with Sinus Rhythm Data: Evaluation of Simulated Training Sets
30th IEEE Signal Processing and Communications Applications Conference (SIU), Safranbolu, Türkiye, 15 - 18 Mayıs 2022, (Tam Metin Bildiri)
- Yayın Türü: Bildiri / Tam Metin Bildiri
- Doi Numarası: 10.1109/siu55565.2022.9864708
- Basıldığı Şehir: Safranbolu
- Basıldığı Ülke: Türkiye
- Orta Doğu Teknik Üniversitesi Adresli: Evet
Özet
The inverse problem of electrocardiography (ECG) aims to reconstruct cardiac electrical activity using body surface potential measurements and a mathematical model of the body. However, this problem is ill-posed; therefore, it is essential to use prior information and regularize the solution to get an accurate solution. Statistical estimation has been applied to the inverse ECG problem with success, but a "good" a priori probability model is required. There are deficiencies in the literature on how to obtain this a priori probability model, especially in sinus rhythm beats. In this study, Bayesian Maximum A Posteriori (MAP) estimation method is applied for solving the inverse ECG problem with data obtained under sinus rhythm conditions. Different training sets are constructed for MAP using measured and the simulated data and these MAP solutions are compared with Tikhonov regularization in terms of relative error and correlation coefficient.