Independent Analysis of Decelerations and Resting Periods through CEEMDAN and Spectral-Based Feature Extraction Improves Cardiotocographic Assessment

Abstract

Fetal monitoring is commonly based on the joint recording of the fetal heart rate (FHR) and uterine contraction signals obtained with a cardiotocograph (CTG). Unfortunately, CTG analysis is difficult, and the interpretation problems are mainly associated with the analysis of FHR decelerations. From that perspective, several approaches have been proposed to improve its analysis; however, the results obtained are not satisfactory enough for their implementation in clinical practice. Current clinical research indicates that a correct CTG assessment requires a good understanding of the fetal compensatory mechanisms. In previous works, we have shown that the complete ensemble empirical mode decomposition with adaptive noise, in combination with time-varying autoregressive modeling, may be useful for the analysis of those characteristics. In this work, based on this methodology, we propose to analyze the FHR deceleration episodes separately. The main hypothesis is that the proposed feature extraction strategy applied separately to the complete signal, deceleration episodes, and resting periods (between contractions), improves the CTG classification performance compared with the analysis of only the complete signal. Results reveal that by considering the complete signal, the classification performance achieved 81.7% quality. Then, including information extracted from resting periods, it improved to 83.2%.

Short-Term PV Power Prediction Based on Optimized VMD and LSTM

“…Although the IPSO can optimize the parameter of SVM, the CEEMDAN and SVM is not suitable to predict the PV power in this paper. The reason is that for the CEEMDAN, the decomposed IMF maybe contain residue noise and spurious mode due to the interaction between the signal and the added white noise [48][49], it maybe effect the prediction of PV power. In addition, for the SVM, the hyperplane is fixed when the training is over.…”

Investigating an Optimal Signal Epoch Length for Cardiotocographic Classification

“…The proposed approach makes use of the signal feature extraction and evaluation strategy presented in [6]. This section first presents a brief explanation concerning the CTG dataset used in this work (Section 2.1).…”

“…The proposed approach is based mainly on two signal processing techniques: ICEEMDAN and TV-AR modelling. The performed feature extraction strategy, explained in detail in [6], can be summarized as follows.…”

“…First, in order to deal with signal loss and outliers resulting from the signal acquisition procedure, we perform a signal preprocessing step, which is applied to the FHR and UC signals. For the FHR signal, we employ the artefact rejection method proposed by [10], which allows removing inconsistent FHR signal values (outside the range between 50 bpm and 210 bpm) and interpolate loss-of-signal data ≤ 75 s. For the UC signal, we interpolate loss-of-signal ≤ 25 s in length, and then, the signal is filtered by a moving average filter of 15 s window length [6].…”

“…This approach aims to investigate an optimal FHR epoch for an automatic CTG analysis. For this purpose, following [6], we employ a signal feature extraction strategy based mainly on two signal processing techniques, such as the Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN) and time-varying autoregressive (TV-AR) modelling. In this work, we examine different FHR segments, which are evaluated according to their performance in CTG classification based on a support vector machine (SVM) classifier.…”