Biomedical Signal Processing / Medical Signal Processing / Biosignal Processing
Amir Reza Asadi; Aboozar Ghaffari
Volume 16, Issue 4 , March 2023, , Pages 41-50
Abstract
One of the procedures for estimating fetal heart rate (FHR) is the use of an electrocardiogram (ECG). The ECG is a safe, inexpensive, and convenient method that can be used for remote monitoring, so maternal abdominal ECG recording (AECG) is used. The AECG signal, in addition to the fetal ECG (FECG), ...
Read More
One of the procedures for estimating fetal heart rate (FHR) is the use of an electrocardiogram (ECG). The ECG is a safe, inexpensive, and convenient method that can be used for remote monitoring, so maternal abdominal ECG recording (AECG) is used. The AECG signal, in addition to the fetal ECG (FECG), includes the maternal ECG (MECG), maternal or fetal muscle activity, fetal brain activity, and noise, making it difficult to estimate the fetal heart rate based on the abdominal signal. In this study, the fetal heart rate is estimated from the single-channel AECG signal utilizing non-negative matrix factorization (NMF). In this method, the short-time Fourier transform (STFT) is used to obtain time-frequency information of the abdominal signal. Next, the NMF utilizes the STFT matrix as input. The rows of the non-negative matrix resulting from the NMF contain the content of maternal, fetal, and noise, which are used to detect R-peak and FHR. It performs well when MECG and FECG amplitudes are close together, which is one of the advantages of this method. The robustness and performance of the proposed algorithm have been compared with other state-of-the-art single-channel approaches, including deep learning models, on two databases, ADFECGDB and PCDB. Statistical analysis demonstrates that the proposed method is capable of estimating FHR and R-peak accurately. As a result, the proposed method is suitable for long-term fetal monitoring.
