BACKGROUND: The utilization of non-invasive techniques for fetal cardiac health surveillance is pivotal in evaluating fetal well-being throughout the gestational period. This process requires clean and interpretable fetal Electrocardiogram (fECG) signals.
METHODS: The proposed work is the novel framework for the elicitation of fECG signals from abdominal ECG (aECG) recordings of the pregnant mother. The comprehensive approach encompasses pre-processing of the raw ECG signal, Blind Source Separation techniques (BSS), Decomposition techniques like Empirical Mode Decomposition (EMD), and its variants like Ensemble Empirical Mode Decomposition (EEMD), and Complete Ensemble Empirical Mode Decomposition with Additive Noise (CEEMDAN). The Robust Set Membership Affine Projection (RSMAP) Algorithm is deployed for the enhancement of the obtained fECG signal.
RESULTS: The results show significant improvements in the elicited fECG signal with a maximum Signal Noise Ratio (SNR) of 31.72 dB and correlation coefficient = 0.899, Maximum Heart Rate(MHR) obtained in the range of 108-142 bpm for all the records of abdominal ECG signals. The statistical test gave a p-value of 0.21 accepting the null hypothesis. The Abdominal and Direct Fetal Electrocardiogram Database (ABDFECGDB) from PhysioNet has been used for this analysis.
CONCLUSIONS: The proposed framework demonstrates a robust and effective method for the elicitation and enhancement of fECG signals from the abdominal recordings.

Intraday stock time series are noisier and more complex than other financial time series with longer time horizons, which makes it challenging to predict. We propose a hybrid CEGH model for intraday stock market forecasting. The CEGH model contains four stages. First, we use complete ensemble empirical mode decomposition (CEEMD) to decompose the original intraday stock market data into different intrinsic mode functions (IMFs). Then, we calculate the approximate entropy (ApEn) values and sample entropy (SampEn) values of each IMF to eliminate noise. After that, we group the retained IMFs into four groups and predict the comprehensive signals of those groups using a feedforward neural network (FNN) or gate recurrent unit with history attention (GRU-HA). Finally, we obtain the final prediction results by integrating the prediction results of each group. The experiments were conducted on the U.S. and China stock markets to evaluate the proposed model. The results demonstrate that the CEGH model improved forecasting performance considerably. The creation of a collaboration between CEEMD, entropy-based denoising, and GRU-HA is our major contribution. This hybrid model could improve the signal-to-noise ratio of stock data and extract global dependence more comprehensively in intraday stock market forecasting.

Electrooculography (EOG) is a method to concurrently obtain electrophysiological signals accompanying an Electroencephalography (EEG), where both methods have a common cerebral pattern and imply a similar medical significance. The most common electrophysiological signal source is EOG that contaminated the EEG signal and thereby decreases the accuracy of measurement and the predicated signal strength. In this study, we introduce a method to improve the correction efficiency for EOG artifacts (EOAs) on raw EEG recordings: We retrieve cerebral information from three EEG signals with high system performance and accuracy by applying feature engineering and a novel machine-learning (ML) procedure. To this end, we use two adaptive algorithms for signal decomposition to remove EOAs from multichannel EEG signals: empirical mode decomposition (EMD) and complete ensemble empirical mode decomposition (CEEMD), both using the Hilbert-Huang transform. First, the signal components are decomposed into multiple intrinsic mode functions. Next, statistical feature extraction and dimension reduction using principal component analysis are employed to select optimal feature sets for the ML procedure that is based on classification and regression models. The proposed CEEMD algorithm enhances the accuracy compared to the EMD algorithm and considerably improves the multi-sensory classification of EEG signals. Models of three different categories are applied, and the classification is based on a K-nearest neighbor (k-NN) algorithm, a decision tree (DT) algorithm, and a support vector machine (SVM) algorithm with accuracies of 94% for K-NN, 75% for DT, and 69% for SVM. For each classification model, a regression learner is used to assist as an evidence rule for the proposed artificial system and to influence the learning process from classification and regression models. The regression learning algorithms applied include algorithms based on an ensemble of trees (ET), a DT, and a SVM. We find that the ET-based regression model exhibits a determination coefficient R2 = 1.00 outperforming the other two approaches with R2 = 0.80 for DT and R2 = 0.76 for SVM.

Global warming is a leading world issue driving the common social objective of reducing carbon emissions. People have witnessed the melting of ice and abrupt changes in climate. Reducing electricity usage is one possible method of slowing these changes. In recent decades, there have been massive worldwide rollouts of smart meters that automatically capture the total electricity usage of houses and buildings. Electricity load disaggregation (ELD) helps to break down total electricity usage into that of individual appliances. Studies have implemented ELD models based on various artificial intelligence techniques using a single ELD dataset. In this paper, a powerline noise transformation approach based on optimized complete ensemble empirical model decomposition and wavelet packet transform (OCEEMD-WPT) is proposed to merge the ELD datasets. The practical implications are that the method increases the size of training datasets and provides mutual benefits when utilizing datasets collected from other sources (especially from different countries). To reveal the effectiveness of the proposed method, it was compared with CEEMD-WPT (fixed controlled coefficients), standalone CEEMD, standalone WPT, and other existing works. The results show that the proposed approach improves the signal-to-noise ratio (SNR) significantly.

To eliminate the influence of white noise in partial discharge (PD) detection, we propose a novel method based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and approximate entropy (ApEn). By introducing adaptive noise into the decomposition process, CEEMDAN can effectively separate the original signal into different intrinsic mode functions (IMFs) with distinctive frequency scales. Afterward, the approximate entropy value of each IMF is calculated to eliminate noisy IMFs. Then, correlation coefficient analysis is employed to select useful IMFs that represent dominant PD features. Finally, real IMFs are extracted for PD signal reconstruction. On the basis of EEMD, CEEMDAN can further improve reconstruction accuracy and reduce iteration numbers to solve mode mixing problems. The results on both simulated and on-site PD signals show that the proposed method can be effectively employed for noise suppression and successfully extract PD pulses. The fusion algorithm combines the CEEMDAN algorithm and the ApEn algorithm with their respective advantages and has a better de-noising effect than EMD and EEMD.

Complete and accurate separation of harmonic components from the ultrasonic radio frequency (RF) echo signals is essential to improve the quality of harmonic imaging. There are limitations in the existing two commonly used separation methods, that is, the subjectivity for the high-pass filtering (S_HPF) method and motion artifacts for the pulse inversion (S_PI) method. A novel separation method called S_CEEMDAN, based on the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) algorithm, is proposed to adaptively separate the second harmonic components for ultrasound tissue harmonic imaging. First, the ensemble size of the CEEMDAN algorithm is calculated adaptively according to the standard deviation of the added white noise. A set of intrinsic mode functions (IMFs) is then obtained by the CEEMDAN algorithm from the ultrasonic RF echo signals. According to the IMF spectra, the IMFs that contain both fundamental and harmonic components are further decomposed. The separation process is performed until all the obtained IMFs have been divided into either fundamental or harmonic categories. Finally, the fundamental and harmonic RF echo signals are obtained from the accumulations of signals from these two categories, respectively. In simulation experiments based on CREANUIS, the S_CEEMDAN-based results are similar to the S_HPF-based results, but better than the S_PI-based results. For the dynamic carotid artery measurements, the contrasts, contrast-to-noise ratios (CNRs), and tissue-to-clutter ratios (TCRs) of the harmonic images based on the S_CEEMDAN are averagely increased by 31.43% and 50.82%, 18.96% and 10.83%, as well as 34.23% and 44.18%, respectively, compared with those based on the S_HPF and S_PI methods. In conclusion, the S_CEEMDAN method provides improved harmonic images owing to its good adaptivity and lower motion artifacts, and is thus a potential alternative to the current methods for ultrasonic harmonic imaging.

The development of industrial civilization has greatly enriched the material and spiritual life of human beings, but it is accompanied by the intensification of the consumption of earth resources and environmental pollution. The smog that has emerged in various parts of China in recent years is a typical problem, which not only endangers human health but also affects normal human work and life. It is difficult to control smog in a short time productively, so people need to understand the rule of smog formation gradually, and effectively predict the PM2.5 index to help people continuously analyze relevant mechanisms and timely protect-related hazards. This paper proposes a hybrid model that uses the Complementary Ensemble Empirical Modal Decomposition algorithm to mine the information in the original PM2.5 sequence and then predicts the pertinent random forests. The trend of PM2.5 concentration during the decomposition process is effectively reflected, and the decomposition sequence is modeled by the high tolerance of the random forest to the noise data and the good fitting ability. In the modeling process, the parameters are optimized according to the evaluation function of the model on the verification set, and eventually, the prediction sequences are superimposed to obtain the final predicted PM2.5 concentration value. The validity of the model is verified by the data of several Chinese cities with different geographical features in the past 5 years. The results show that the recommendation model is higher than other comparison models in terms of model stability and prediction accuracy.