Využití hybridních metod pro zpracování plodového elektrokardiogramu

Abstract

This dissertation focuses on the design, implementation and subsequent verification of a new type of hybrid extraction system for noninvasive fetal electrocardiogram (NI-fECG) processing. The designed system combines the advantages of individual adaptive and non-adaptive methods. This thesis reviews two innovative hybrid systems called ICA-ANFIS-WT and ICA-RLS-WT. This is a combination of independent component analysis (ICA), adaptive neuro-fuzzy inference system (ANFIS) or recursive least squares (RLS) algorithm and wavelet transform (WT). The study was conducted on clinical practice data (extended abdominal and direct fetal electrocardiogram database (ADFECGDB) and Physionet Challenge 2013 database) from the perspective of non-invasive fetal heart rate (fHR) monitoring based on the determination of the overall probability of correct detection (ACC), sensitivity (SE), positive predictive value (PPV) and harmonic mean between SE and PPV (F1). System functionality was verified against a relevant reference obtained by annotations. The study showed that ICA-RLS-WT hybrid system achieve better results than ICA-ANFIS-WT. During experiment on ADFECGDB database, the ICA-RLS-WT hybrid system reached ACC > 80 % on 10 recordings out of 12 and the ICA-ANFIS-WT hybrid system reached ACC > 80 % only on 6 recordings out of 12. During experiment on Physionet Challenge 2013 database the ICA-RLS-WT hybrid system reached ACC > 80 % on 13 recordings out of 25 and the ICA-ANFIS-WT hybrid system reached ACC > 80 % only on 7 recordings out of 25. Both hybrid systems achieve provably better results than the individual methods tested in previous studies.