Deep learning precipitation prediction models combined with feature analysis.

Precise rainfall forecasting modeling assumes a pivotal role in water resource planning and management. Conducting a comprehensive analysis of the rainfall time series and making appropriate adjustments to the forecast model settings based on the characterization results of the rainfall series significantly enhance the accuracy of the forecast model. This paper employed the Mann-Kendall and sliding T mutation tests to identify the mutational components in rainfall between 1961 and 2013 at four meteorological stations located in Henan Province. Wavelet analysis was utilized to determine the periodicity of the precipitation series. The model parameters were adjusted based on the mutation and periodicity findings, and appropriate training and test sets were selected accordingly. Rainfall simulation in Henan Province, China, was conducted using a combination of complementary ensemble empirical mode decomposition (CEEMD) and bi-directional long short-term memory (BiLSTM) networks. The integrated approach aimed at predicting rainfall in the region. The findings of this study demonstrate that the CEEMD-BiLSTM model, coupled with feature analysis, yielded favorable results in terms of prediction accuracy. The model achieved a mean MAE (mean absolute error) of 131.210, a mean MRE (mean relative error) of 0.637, a mean RMSE (root mean square error) of 187.776, and an NSE (Nash-Sutcliffe efficiency) above 0.910. The data processed according to the feature analysis results and then predicted; Zhengzhou, Anyang, Lushi, and Xinyang stations improved by 39.548%, 14.478%, 11.548%, and 19.037% respectively compared with the original prediction model.

Research on Denoising Method for Hydroelectric Unit Vibration Signal Based on ICEEMDAN-PE-SVD.

Vibration monitoring and analysis play a crucial role in the fault diagnosis of hydroelectric units. However, accurate extraction and identification of fault features from vibration signals are challenging because of noise interference. To address this issue, this study proposes a novel denoising method for vibration signals based on improved complementary ensemble empirical mode decomposition with adaptive noise (ICEEMDAN), permutation entropy (PE), and singular value decomposition (SVD). The proposed method is applied for the analysis of hydroelectric unit sway monitoring. Firstly, the ICEEMDAN method is employed to process the signal and obtain several intrinsic mode functions (IMFs), and then the PE values of each IMF are calculated. Subsequently, based on a predefined threshold of PE, appropriate IMFs are selected for reconstruction, achieving the first denoising effect. Then, the SVD is applied to the signal after the first denoising effect, resulting in the SVD spectrum. Finally, according to the principle of the SVD spectrum and the variation in the singular value and its energy value, the signal is reconstructed by choosing the appropriate reconstruction order to achieve the secondary noise reduction effect. In the simulation and case analysis, the method is better than the commonly used wavelet threshold, SVD, CEEMDAN-PE, and ICEEMDAN-PE, with a signal-to-noise ratio (SNR) improvement of 6.9870 dB, 4.6789 dB, 8.9871 dB, and 4.3762 dB, respectively, and where the root-mean-square error (RMSE) is reduced by 0.1426, 0.0824, 0.2093 and 0.0756, respectively, meaning that our method has a better denoising effect and provides a new way for denoising the vibration signal of hydropower units.

Prediction of suspended sediment concentration in the lower Yellow River in China based on the coupled CEEMD-NAR model.

The scientific and accurate prediction of suspended sediment concentrations is of great importance for river management in the lower reaches of the Yellow River and for the scheduling of water conservancy projects in the upper and middle reaches. In order to solve the influence of the non-linear and non-smooth characteristics of the suspended sediment concentration series in the lower Yellow River on the prediction results and improve the prediction accuracy, this paper proposes a coupled model based on Complementary Ensemble Empirical Mode Decomposition (CEEMD) and non-linear autoregressive (NAR) model. Take the predicted suspended sediment concentrations in the lower reaches of the Yellow River at the Huayuankou hydrographic station as an example. The accuracy and stability of the coupled CEEMD-NAR model were verified through the Gaocun and Lijin hydrological stations. The CEEMD-NAR model predicted suspended sediment concentrations with a Nash-Sutcliffe efficiency (NSE) factor of 0.93. The three statistical evaluation indicators of the CEEMD-NAR model, mean absolute error (MAE), mean relative error (MRE), and root mean square error (RMSE) were 2.12 kg/m3, 1.07, and 3.75 kg/m3 respectively. In contrast to the NAR, EMD-NAR, and EEMD-NAR models, the coupled CEEMD-NAR model has good stability and high prediction accuracy and can be used in non-linear, non-smooth suspended sediment concentration long series prediction.

Using Complementary Ensemble Empirical Mode Decomposition and Gated Recurrent Unit to Predict Landslide Displacements in Dam Reservoir.

It is crucial to predict landslide displacement accurately for establishing a reliable early warning system. Such a requirement is more urgent for landslides in the reservoir area. The main reason is that an inaccurate prediction can lead to riverine disasters and secondary surge disasters. Machine learning (ML) methods have been developed and commonly applied in landslide displacement prediction because of their powerful nonlinear processing ability. Recently, deep ML methods have become popular, as they can deal with more complicated problems than conventional ML methods. However, it is usually not easy to obtain a well-trained deep ML model, as many hyperparameters need to be trained. In this paper, a deep ML method-the gated recurrent unit (GRU)-with the advantages of a powerful prediction ability and fewer hyperparameters, was applied to forecast landslide displacement in the dam reservoir. The accumulated displacement was firstly decomposed into a trend term, a periodic term, and a stochastic term by complementary ensemble empirical mode decomposition (CEEMD). A univariate GRU model and a multivariable GRU model were employed to forecast trend and stochastic displacements, respectively. A multivariable GRU model was applied to predict periodic displacement, and another two popular ML methods-long short-term memory neural networks (LSTM) and random forest (RF)-were used for comparison. Precipitation, reservoir level, and previous displacement were considered to be candidate-triggering factors for inputs of the models. The Baijiabao landslide, located in the Three Gorges Reservoir Area (TGRA), was taken as a case study to test the prediction ability of the model. The results demonstrated that the GRU algorithm provided the most encouraging results. Such a satisfactory prediction accuracy of the GRU algorithm depends on its ability to fully use the historical information while having fewer hyperparameters to train. It is concluded that the proposed model can be a valuable tool for predicting the displacements of landslides in the TGRA and other dam reservoirs.

Detecting Epileptic Seizures in EEG Signals with Complementary Ensemble Empirical Mode Decomposition and Extreme Gradient Boosting.

Epilepsy is a common nervous system disease that is characterized by recurrent seizures. An electroencephalogram (EEG) records neural activity, and it is commonly used for the diagnosis of epilepsy. To achieve accurate detection of epileptic seizures, an automatic detection approach of epileptic seizures, integrating complementary ensemble empirical mode decomposition (CEEMD) and extreme gradient boosting (XGBoost), named CEEMD-XGBoost, is proposed. Firstly, the decomposition method, CEEMD, which is capable of effectively reducing the influence of mode mixing and end effects, was utilized to divide raw EEG signals into a set of intrinsic mode functions (IMFs) and residues. Secondly, the multi-domain features were extracted from raw signals and the decomposed components, and they were further selected according to the importance scores of the extracted features. Finally, XGBoost was applied to develop the epileptic seizure detection model. Experiments were conducted on two benchmark epilepsy EEG datasets, named the Bonn dataset and the CHB-MIT (Children's Hospital Boston and Massachusetts Institute of Technology) dataset, to evaluate the performance of our proposed CEEMD-XGBoost. The extensive experimental results indicated that, compared with some previous EEG classification models, CEEMD-XGBoost can significantly enhance the detection performance of epileptic seizures in terms of sensitivity, specificity, and accuracy.

Multiscale Entropy Feature Extraction Method of Running Power Equipment Sound.

The equipment condition monitoring based on computer hearing is a new pattern recognition approach, and the system formed by it has the advantages of noncontact and strong early warning abilities. Extracting effective features from the sound data of the running power equipment help to improve the equipment monitoring accuracy. However, the sound of running equipment often has the characteristics of serious noise, non-linearity and instationary, which makes it difficult to extract features. To solve this problem, a feature extraction method based on the improved complementary ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) and multiscale improved permutation entropy (MIPE) is proposed. Firstly, the ICEEMDAN is utilized to obtain a group of intrinsic mode functions (IMFs) from the sound of running power equipment. The noise IMFs are then identified and eliminated through mutual information (MI) and mean mutual information (meanMI) of IMFs. Next, the normalized mutual information (norMI) and MIPE are calculated respectively, and norMI is utilized to weigh the corresponding MIPE result. Finally, based on the separability criterion, the weighted MIPE results are feature-dimensionally reduced to obtain the multiscale entropy feature of the sound. The experimental results show that the classification accuracies of the method under the conditions of no noise and 5 dB reach 96.7% and 89.9%, respectively. In practice, the proposed method has higher reliability and stability for the sound feature extraction of the running power equipment.

Muscle Fatigue Analysis With Optimized Complementary Ensemble Empirical Mode Decomposition and Multi-Scale Envelope Spectral Entropy.

The preprocessing of surface electromyography (sEMG) signals with complementary ensemble empirical mode decomposition (CEEMD) improves frequency identification precision and temporal resolution, and lays a good foundation for feature extraction. However, a mode-mixing problem often occurs when the CEEMD decomposes an sEMG signal that exhibits intermittency and contains components with a near-by spectrum into intrinsic mode functions (IMFs). This paper presents a method called optimized CEEMD (OCEEMD) to solve this problem. The method integrates the least-squares mutual information (LSMI) and the chaotic quantum particle swarm optimization (CQPSO) algorithm in signal decomposition. It uses the LSMI to calculate the correlation between IMFs so as to reduce mode mixing and uses the CQPSO to optimize the standard deviation of Gaussian white noise so as to improve iteration efficiency. Then, useful IMFs are selected and added to reconstruct a de-noised signal. Finally, considering that the IMFs contain abundant frequency and envelope information, this paper extracts the multi-scale envelope spectral entropy (MSESEn) from the reconstructed sEMG signal. Some original sEMG signals, which were collected from experiments, were used to validate the methods. Compared with the CEEMD and complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), the OCEEMD effectively suppresses mode mixing between IMFs with rapid iteration. Compared with approximate entropy (ApEn) and sample entropy (SampEn), the MSESEn clearly shows a declining tendency with time and is sensitive to muscle fatigue. This suggests a potential use of this approach for sEMG signal preprocessing and the analysis of muscle fatigue.

A New Method Based on CEEMD Combined With Iterative Feature Reduction for Aided Diagnosis of Epileptic EEG.

In the clinical diagnosis of epileptic diseases, the intelligent diagnosis of epileptic electroencephalogram (EEG) signals has become a research focus in the field of brain diseases. In order to solve the problem of time-consuming and easily influenced by human subjective factors, artificial intelligence pattern recognition algorithm has been applied to EEG signals recognition. However, at present, the common empirical mode decomposition (EMD) signal decomposition algorithm does not consider the problem of mode aliasing. The EEG features obtained by feature extraction may be mixed with some unimportant features that affect the classification accuracy. In this paper, we proposed a new method based on complementary ensemble empirical mode decomposition (CEEMD) combined with iterative feature reduction for aided diagnosis of epileptic EEG. First of all, the evaluation indexes of decomposing and reconstructing signals by several methods were compared. The CEEMD was selected as the decomposition method of the signals. Then, the support vector machine recursive elimination (SVM-RFE) was used to reduce 9 features extracted from EEG data. The support vector classification of the gray wolf optimizer (GWO-SVC) recognition model was established for different feature subsets. By comparing the classification accuracy of training set and test set of different feature subsets, and considering the complexity of the model reflected by the number of features selected by SVM-RFE, the analysis showed that the 6 feature subsets with fewer features and higher classification accuracy could reflect the key information of epileptic EEG. The accuracy of the training set classification was 99.38% and the test set was as high as 100%. The recognition time was only 1.6551 s. Finally, in order to verify the reliability of the algorithm proposed in this paper, the proposed algorithm compared with the classification model established by the raw EEG signals and the optimization model established by other intelligent optimization algorithms. It is found that the algorithm used in this paper has higher classification accuracy and faster recognition time than other processing methods. The experimental results show that CEEMD combined with SVM-RFE is feasible for rapid and accurate recognition of EEG signals, which provides a theoretical basis for the aided diagnosis of epilepsy.

Estimation of Heart Rate and Respiratory Rate from PPG Signal Using Complementary Ensemble Empirical Mode Decomposition with both Independent Component Analysis and Non-Negative Matrix Factorization.

This paper proposes a framework combining the complementary ensemble empirical mode decomposition with both the independent component analysis and the non-negative matrix factorization for estimating both the heart rate and the respiratory rate from the photoplethysmography (PPG) signal. After performing the complementary ensemble empirical mode decomposition on the PPG signal, a finite number of intrinsic mode functions are obtained. Then, these intrinsic mode functions are divided into two groups to perform the further analysis via both the independent component analysis and the non-negative matrix factorization. The surrogate cardiac signal related to the heart activity and another surrogate respiratory signal related to the respiratory activity are reconstructed to estimate the heart rate and the respiratory rate, respectively. Finally, different records of signals acquired from the Medical Information Mart for Intensive Care database downloaded from the Physionet Automated Teller Machine (ATM) data bank are employed for demonstrating the outperformance of our proposed method. The results show that our proposed method outperforms both the digital filtering approach and the conventional empirical mode decomposition based methods in terms of reconstructing both the surrogate cardiac signal and the respiratory signal from the PPG signal as well as both achieving the higher accuracy and the higher reliability for estimating both the heart rate and the respiratory rate.

GAM-Based Mooring Alignment for SINS Based on An Improved CEEMD Denoising Method.

To solve the self-alignment problem of the Strapdown Inertial Navigation System (SINS), a novel adaptive filter based on Complementary Ensemble Empirical Mode Decomposition (CEEMD) is proposed. The Gravitational Apparent Motion (GAM) is used in the coarse alignment, and the problem of obtaining the attitude matrix between the body frame and the navigation frame is attributed to obtaining the matrix between the initial body frame and the current navigation frame using two gravitational apparent motion vectors at different moments. However, the accuracy and time of this alignment method always suffer from the measurement noise of sensors. Thus, a novel adaptive filter based on CEEMD using an l 2 -norm to calculate the similarity measure between the Probability Density Function (PDF) of each Intrinsic Mode Function (IMF) and the original signal is proposed to denoise the measurements of the accelerometer. Furthermore, the advantage of this filter is verified by comparing with other conventional denoising methods, such as PDF-based EMD (EMD-PDF) and the Finite Impulse Response (FIR) digital low-pass filter method. The results of the simulation and experiments indicate that the proposed method performs better than the conventional methods in both alignment time and alignment accuracy.

Design and implementation of a hybrid model based on two-layer decomposition method coupled with extreme learning machines to support real-time environmental monitoring of water quality parameters.

Accurate prediction of water quality parameters plays a crucial and decisive role in environmental monitoring, ecological systems sustainability, human health, aquaculture and improved agricultural practices. In this study a new hybrid two-layer decomposition model based on the complete ensemble empirical mode decomposition algorithm with adaptive noise (CEEMDAN) and the variational mode decomposition (VMD) algorithm coupled with extreme learning machines (ELM) and also least square support vector machine (LSSVM) was designed to support real-time environmental monitoring of water quality parameters, i.e. chlorophyll-a (Chl-a) and dissolved oxygen (DO) in a Lake reservoir. Daily measurements of Chl-a and DO for June 2012-May 2013 were employed where the partial autocorrelation function was applied to screen the relevant inputs for the model construction. The variables were then split into training, validation and testing subsets where the first stage of the model testing captured the superiority of the ELM over the LSSVM algorithm. To improve these standalone predictive models, a second stage implemented a two-layer decomposition with the model inputs decomposed in the form of high and low frequency oscillations, represented by the intrinsic mode function (IMF) through the CEEMDAN algorithm. The highest frequency component, IMF1 was further decomposed with the VMD algorithm to segregate key model input features, leading to a two-layer hybrid VMD-CEEMDAN model. The VMD-CEEMDAN-ELM model was able to reduce the root mean square and the mean absolute error by about 14.04% and 7.12% for the Chl-a estimation and about 5.33% and 4.30% for the DO estimation, respectively, compared with the standalone counterparts. Overall, the developed methodology demonstrates the robustness of the two-phase VMD-CEEMDAN-ELM model in identifying and analyzing critical water quality parameters with a limited set of model construction data over daily horizons, and thus, to actively support environmental monitoring tasks, especially in case of high-frequency, and relatively complex, real-time datasets.

Towards estimation of respiratory muscle effort with respiratory inductance plethysmography signals and complementary ensemble empirical mode decomposition.

Respiratory inductance plethysmography (RIP) sensor is an inexpensive, non-invasive, easy-to-use transducer for collecting respiratory movement data. Studies have reported that the RIP signal's amplitude and frequency can be used to discriminate respiratory diseases. However, with the conventional approach of RIP data analysis, respiratory muscle effort cannot be estimated. In this paper, the estimation of the respiratory muscle effort through RIP signal was proposed. A complementary ensemble empirical mode decomposition method was used, to extract hidden signals from the RIP signals based on the frequency bands of the activities of different respiratory muscles. To validate the proposed method, an experiment to collect subjects' RIP signal under thoracic breathing (TB) and abdominal breathing (AB) was conducted. The experimental results for both the TB and AB indicate that the proposed method can be used to loosely estimate the activities of thoracic muscles, abdominal muscles, and diaphragm. Graphical abstract ᅟ.

Intrinsic frequency specific brain networks for identification of MCI individuals using resting-state fMRI.

Numerous brain oscillations are well organized into several brain rhythms to support complex brain activities within distinct frequency bands. These rhythms temporally coexist in the same or different brain areas and may interact with each other with specific properties and physiological functions. However, the identification and evaluation of these various brain rhythms derived from BOLD-fMRI signals are obscure. To address this issue, we introduced a data-driven method named Complementary Ensemble Empirical Mode Decomposition (CEEMD) to automatically decompose the BOLD oscillations into several brain rhythms within distinct frequency bands. Thereafter, in order to evaluate the performance of CEEMD in the detection of subtle BOLD signals, a novel CEEMD-based high-dimensional pattern classification framework was proposed to accurately identify mild cognitive impairment individuals from the healthy controls. Our results showed CEEMD is a stable frequency decomposition method. Furthermore, CEEMD-based frequency specific topological profiles provided a classification accuracy of 93.33%, which was saliently higher than that of the conventional frequency separation based scheme. Importantly, our findings demonstrated that CEEMD could provide an effective means for brain oscillation separation, by which a more meaningful frequency bins could be used to detect the subtle changes embedded in the BOLD signals.

A new air quality monitoring and early warning system: Air quality assessment and air pollutant concentration prediction.

Air pollution in many countries is worsening with industrialization and urbanization, resulting in climate change and affecting people's health, thus, making the work of policymakers more difficult. It is therefore both urgent and necessary to establish amore scientific air quality monitoring and early warning system to evaluate the degree of air pollution objectively, and predict pollutant concentrations accurately. However, the integration of air quality assessment and air pollutant concentration prediction to establish an air quality system is not common. In this paper, we propose a new air quality monitoring and early warning system, including an assessment module and forecasting module. In the air quality assessment module, fuzzy comprehensive evaluation is used to determine the main pollutants and evaluate the degree of air pollution more scientifically. In the air pollutant concentration prediction module, a novel hybridization model combining complementary ensemble empirical mode decomposition, a modified cuckoo search and differential evolution algorithm, and an Elman neural network, is proposed to improve the forecasting accuracy of six main air pollutant concentrations. To verify the effectiveness of this system, pollutant data for two cities in China are used. The result of the fuzzy comprehensive evaluation shows that the major air pollutants in Xi'an and Jinan are PM10 and PM2.5 respectively, and that the air quality of Xi'an is better than that of Jinan. The forecasting results indicate that the proposed hybrid model is remarkably superior to all benchmark models on account of its higher prediction accuracy and stability.

Frequency specific brain networks in Parkinson's disease and comorbid depression.

The topological organization underlying the human brain was extensively investigated using resting-state functional magnetic resonance imaging, focusing on a low frequency of signal oscillation from 0.01 to 0.1 Hz. However, the frequency specificities with regard to the topological properties of the brain networks have not been fully revealed. In this study, a novel complementary ensemble empirical mode decomposition (CEEMD) method was used to separate the fMRI time series into five characteristic oscillations with distinct frequencies. Then, the small world properties of brain networks were analyzed for each of these five oscillations in patients (n = 67) with depressed Parkinson's disease (DPD, n = 20) , non-depressed Parkinson's disease (NDPD, n = 47) and healthy controls (HC, n = 46). Compared with HC, the results showed decreased network efficiency in characteristic oscillations from 0.05 to 0.12 Hz and from 0.02 to 0.05 Hz for the DPD and NDPD patients, respectively. Furthermore, compared with HC, the most significant inter-group difference across five brain oscillations was found in the basal ganglia (0.01 to 0.05 Hz) and paralimbic-limbic network (0.02 to 0.22 Hz) for the DPD patients, and in the visual cortex (0.02 to 0.05 Hz) for the NDPD patients. Compared with NDPD, the DPD patients showed reduced efficiency of nodes in the basal ganglia network (0.01 to 0.05 Hz). Our results demonstrated that DPD is characterized by a disrupted topological organization in large-scale brain functional networks. Moreover, the CEEMD analysis suggested a prominent dissociation in the topological organization of brain networks between DPD and NDPD in both space and frequency domains. Our findings indicated that these characteristic oscillatory activities in different functional circuits may contribute to distinct motor and non-motor components of clinical impairments in Parkinson's disease.

A novel hybrid model for air quality index forecasting based on two-phase decomposition technique and modified extreme learning machine.

The randomness, non-stationarity and irregularity of air quality index (AQI) series bring the difficulty of AQI forecasting. To enhance forecast accuracy, a novel hybrid forecasting model combining two-phase decomposition technique and extreme learning machine (ELM) optimized by differential evolution (DE) algorithm is developed for AQI forecasting in this paper. In phase I, the complementary ensemble empirical mode decomposition (CEEMD) is utilized to decompose the AQI series into a set of intrinsic mode functions (IMFs) with different frequencies; in phase II, in order to further handle the high frequency IMFs which will increase the forecast difficulty, variational mode decomposition (VMD) is employed to decompose the high frequency IMFs into a number of variational modes (VMs). Then, the ELM model optimized by DE algorithm is applied to forecast all the IMFs and VMs. Finally, the forecast value of each high frequency IMF is obtained through adding up the forecast results of all corresponding VMs, and the forecast series of AQI is obtained by aggregating the forecast results of all IMFs. To verify and validate the proposed model, two daily AQI series from July 1, 2014 to June 30, 2016 collected from Beijing and Shanghai located in China are taken as the test cases to conduct the empirical study. The experimental results show that the proposed hybrid model based on two-phase decomposition technique is remarkably superior to all other considered models for its higher forecast accuracy.

Instantaneous phase difference analysis between thoracic and abdominal movement signals based on complementary ensemble empirical mode decomposition.

BACKGROUND: Thoracoabdominal asynchrony is often adopted to discriminate respiratory diseases in clinics. Conventionally, Lissajous figure analysis is the most frequently used estimation of the phase difference in thoracoabdominal asynchrony. However, the temporal resolution of the produced results is low and the estimation error increases when the signals are not sinusoidal. Other previous studies have reported time-domain procedures with the use of band-pass filters for phase-angle estimation. Nevertheless, the band-pass filters need calibration for phase delay elimination. METHODS: To improve the estimation, we propose a novel method (named as instantaneous phase difference) that is based on complementary ensemble empirical mode decomposition for estimating the instantaneous phase relation between measured thoracic wall movement and abdominal wall movement. To validate the proposed method, experiments on simulated time series and human-subject respiratory data with two breathing types (i.e., thoracic breathing and abdominal breathing) were conducted. Latest version of Lissajous figure analysis and automatic phase estimation procedure were compared. RESULTS: The simulation results show that the standard deviations of the proposed method were lower than those of two other conventional methods. The proposed method performed more accurately than the two conventional methods. For the human-subject respiratory data, the results of the proposed method are in line with those in the literature, and the correlation analysis result reveals that they were positively correlated with the results generated by the two conventional methods. Furthermore, the standard deviation of the proposed method was also the smallest. CONCLUSIONS: To summarize, this study proposes a novel method for estimating instantaneous phase differences. According to the findings from both the simulation and human-subject data, our approach was demonstrated to be effective. The method offers the following advantages: (1) improves the temporal resolution, (2) does not introduce a phase delay, (3) works with non-sinusoidal signals, (4) provides quantitative phase estimation without estimating the embedded frequency of breathing signals, and (5) works without calibrated measurements. The results demonstrate a higher temporal resolution of the phase difference estimation for the evaluation of thoracoabdominal asynchrony.