Illanes Alfredo, Haritopoulos Michel
Annu Int Conf IEEE Eng Med Biol Soc. 2015 Aug;2015:5842-5. doi: 10.1109/EMBC.2015.7319720.
The main objective of this work is to perform an autoregressive model (AR)-based power spectral analysis of the fetal heart rate (FHR) signal for the extraction of significant features for fetal welfare assessment. A group of features is directly computed from the AR-based spectrum while another group is computed from the poles representation. The presented method is applied to real cardiotocographic (CTG) signals and for different frequency bands, and the obtained results are very promising as they exhibit direct correlations between the extracted features and the fetal welfare in terms of umbilical pH.
这项工作的主要目标是对胎儿心率（FHR）信号进行基于自回归模型（AR）的功率谱分析，以提取用于评估胎儿健康状况的重要特征。一组特征直接从基于AR的频谱中计算得出，而另一组特征则从极点表示中计算得出。所提出的方法应用于实际的产程图（CTG）信号和不同频段，所获得的结果非常有前景，因为它们在脐动脉血pH值方面展示了提取的特征与胎儿健康状况之间的直接相关性。
