Performance of two adaptive subband filtering schemes for processing fetal phonocardiograms: influence of the wavelet and the level of decomposition

This work evaluates the influence of the wavelet and the level of decomposition on the performance of two Adaptive Subband Schemes for processing Fetal Phonocardiograms, based on Mutual Information (MI) and Wavelet Packets (WP). Three simulated fetal phococardiogram signals with different signal to noise ratio (SNR) were filtered using combinations of MI, WP, two levels of decomposition (N) and 36 wavelets. Two proposed indexes quantified the performance of the filtering schemes. The authors' results showed that WP and MI had better performance with N=3, MI proved to be better than WP, and Daubechies of sixth order seems to be the most suitable wavelet for different SNR.

[1]  I. Hartimo,et al.  A heart sound feature extraction algorithm based on wavelet decomposition and reconstruction , 1998, Proceedings of the 20th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Vol.20 Biomedical Engineering Towards the Year 2000 and Beyond (Cat. No.98CH36286).

[2]  F. Kovacs,et al.  An improved phonocardiographic method for fetal heart rate monitoring , 1998, Proceedings of the 20th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Vol.20 Biomedical Engineering Towards the Year 2000 and Beyond (Cat. No.98CH36286).

[3]  M. R. Ortiz,et al.  The use of wavelet packets to improve the detection of cardiac sounds from the fetal phonocardiogram , 1999, Computers in Cardiology 1999. Vol.26 (Cat. No.99CH37004).

[4]  L. Sakari,et al.  A heart sound segmentation algorithm using wavelet decomposition and reconstruction , 1997, Proceedings of the 19th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. 'Magnificent Milestones and Emerging Opportunities in Medical Engineering' (Cat. No.97CH36136).