Empirical Decomposition Research Articles

Fatigue feature extraction and classification algorithm of forehead single-channel electroencephalography signals

Aiming at the problem that the feature extraction ability of forehead single-channel electroencephalography (EEG) signals is insufficient, which leads to decreased fatigue detection accuracy, a fatigue feature extraction and classification algorithm based on supervised contrastive learning is proposed. Firstly, the raw signals are filtered by empirical modal decomposition to improve the signal-to-noise ratio. Secondly, considering the limitation of the one-dimensional signal in information expression, overlapping sampling is used to transform the signal into a two-dimensional structure, and simultaneously express the short-term and long-term changes of the signal. The feature extraction network is constructed by depthwise separable convolution to accelerate model operation. Finally, the model is globally optimized by combining the supervised contrastive loss and the mean square error loss. Experiments show that the average accuracy of the algorithm for classifying three fatigue states can reach 75.80%, which is greatly improved compared with other advanced algorithms, and the accuracy and feasibility of fatigue detection by single-channel EEG signals are significantly improved. The results provide strong support for the application of single-channel EEG signals, and also provide a new idea for fatigue detection research.

Hybrid forecasting model of building cooling load based on EMD-LSTM-Markov algorithm

Precise forecasting of the cooling load (CL) of buildings is crucial for the efficient functioning of central air conditioning systems. The study proposed a new hybrid model based on empirical modal decomposition (EMD) and Markov chain improved LSTM neural network, denoted as EMD-LSTM-Markov. First, Pearson’s correlation coefficient (PCC) and Gradient Boosting Decision Tree (GBDT) are used to extract features with a high degree as the input data. Then, the LSTM is employed to establish a prediction model. Finally, to verify the validity and prediction accuracy of the proposed model, this paper selects the CL data of an office building in Guangzhou as the research sample. The results show that the Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE) of the EMD-LSTM-Markov model are 4.53 and 0.84%. Compared with the other three predicting models, the RMSE and MAPE values of EMD-LSTM-Markov are decreased by 40% − 94% and 70% − 96%, which has better performance in accuracy and stability. It testifies that the proposed strategy is reliable and effective. This work successfully resolves the issue of delayed cold response. The hybrid model proposed demonstrates significant energy-saving potential for accurately predicting building CLs and enhancing the optimal control of cooling systems. Future research should explore the hybrid model’s robustness across different building types and climatic regions.

Temporal assessment of Gross alpha emissions from the petroleum industry in Tenerife, Canary Islands (2001–2022)

A ca. 76% decrease in gross alpha activity levels, measured in surface aerosols collected in the city of Santa Cruz de Tenerife (Spain), has been explained in the present study in connection with the reduction of activities, and eventual closure, of an oil refinery in the city. Gross Alpha in surface aerosols, collected at weekly intervals over a period of 22 years (2001–2022), was used for the analysis. The dynamic behaviour of the gross alpha time series was studied using statistical wavelet, multifractal analysis, empirical decomposition method, multivariate analysis, principal component, and cluster analyses approaches. This was performed to separate the impact of other sources of alpha emitting radionuclides influencing the gross alpha levels at this site. These in-depth analyses revealed a noteworthy shift in the dynamic behaviour of the gross alpha levels following the refinery's closure in 2013. This analysis also attributed fluctuations and trends in the gross alpha levels to factors such as the 2008 global economic crisis and the refinery's gradual reduction of activity leading up to its closure. The mixed-model approach, incorporating multivariate regression and autoregressive integrated moving average methods, explained approximately 84% of the variance of the gross alpha levels. Finally, this work underscored the marked reduction in alpha activity levels following the refinery's closure, alongside the decline of other pollutants (CO, SO2, NO, NO2, Benzene, Toluene and Xylene) linked to the primary industrial activity in the municipality of Santa Cruz de Tenerife.

A prediction model for chlorophyll concentration in seawater based on BorutaShap-MEMD-GRU

To solve the problem of the difficulty in selecting multi-parameter features of the ocean and the lack of power of traditional time-series prediction models in predicting ocean data, an ocean time-series prediction GRU model based on the Borutashap algorithm, and a hybrid multivariate empirical modal decomposition is proposed to predict multivariate in this paper. The feature selection of multi-feature ocean data is carried out by the Borutashap algorithm based on the XG-boost model, then the selected data are decomposed by multi-modal decomposition, and the data are reconstructed to get the high-frequency and low-frequency components, and the trend term components by Permutation Entropy, and finally the high-frequency and low-frequency components and the trend term are respectively brought into the GRU network and the prediction is summed up to get the final result. In this paper, the model’s effectiveness is verified by ablation experiments and compared with other feature selection models and classical time series prediction models, the results show that the model has a better prediction effect.

A forecasting model with hybrid bidirectional long short-term memory for mooring line responses of semi-submersible offshore platforms

Semi-submersible offshore platforms are often produced in the deep sea far away from land, which results in high operating costs and difficult safety maintenance due to the harsh and complex working conditions. Adopting a neural network model for online accurate prediction of mooring tension of semi-submersible offshore platforms can adjust the ballast according to the advance of mooring tension change to keep the platform in a relatively smooth movement amplitude and improve production efficiency. In addition, it can also prevent catastrophic accidents caused by anchor chain breakage due to excessive mooring tension. However, the measured mooring tension of semi-submersible offshore platforms is characterized by complex nonlinear non-stationarity, which leads to insufficient prediction accuracy of a single prediction model. This paper develops a novel online prediction model of mooring tension for semi-submersible offshore platforms based on empirical modal decomposition (EMD), convolutional neural network (CNN), and bidirectional long and short-term memory neural network (BiLSTM). The proposed model is validated using the measured data of the first semi-submersible offshore platform in the South China Sea during operation. The experimental results show that the proposed model outperforms other comparative models currently mainstream for mooring tension prediction. In addition, the proposed method can also be used to predict complex nonlinear data in the field of ship and ocean engineering.

Multi-resolution assessment of heart rate variability signals during yogic and normal breathing using machine learning modules

In recent times, yoga has gained global prominence due to its wide-ranging health benefits. Heart rate variability (HRV) analysis has become a widely embraced tool to assess the impact of yoga and meditation on individuals. The effects of yoga can vary significantly among individuals based on their prior expertise, skills, and the interplay of external and internal dynamics. This variability complicates the task of extracting distinctive characteristics from raw data to categorize yogic and pre-yogic states. This paper introduces a new approach that enhances the screening of yogic states through multi-resolution analysis of HRV data combined with a machine learning module. The empirical Fourier decomposition (EFD) technique is harnessed to decompose input data into distinct multi-resolution modes. Various statistical characteristics are then extracted from these modes, allowing for a comprehensive analysis of the immediate effects of yoga breathing on HRV signals. To discern between yogic and pre-yogic HRV signals, a selection of significant features is ranked using a chi-square score and subsequently inputted into machine-learning modules. Notably, employing normalized features with the decision medium tree classifier yields an area under the curve (AUC) value of 0.99, while using direct features with an ensemble bagged tree classifier results in an AUC value of 0.82. Furthermore, this research underscores the importance of assessing outcomes from various metrics to compute the underlying dynamics of HRV data during breathing practices. This approach facilitates precise monitoring, personalized feedback, and intervention in yoga machine interfacing systems, ultimately enriching the overall experience and well-being of yoga practitioners.

Three-dimensional reconstruction method for layered structures based on a frequency modulated continuous wave terahertz radar.

The feasibility of employing a continuous-wave terahertz detection system for non-contact and non-destructive testing (NDT) in multi-layered bonding structures is assessed in this study. The paper introduces the detection principle of terahertz frequency modulated continuous wave (FMCW) radar and outlines the two-dimensional (2D) scanning platform, which integrates optical lenses, three linear actuators, a control platform, and data acquisition units. Experimental results on two types of insulation with prefabricated defects demonstrate the capability of terahertz waves for transparent inspection imaging. These results confirm the viability of terahertz FMCW detection technology as an advanced NDT tool for multi-layered bonding structures. However, the inherent limitations of terahertz wavelength and hardware systems pose challenges in discriminating reflection peaks on upper and lower surfaces. To address this issue, a local adaptive empirical wavelet coefficient modal decomposition (LAEWCMD) method is proposed to enhance the longitudinal discrimination ability of terahertz detection. The proposed method involves segmenting the 2D terahertz detection image into regions to differentiate between defective and non-defective areas. Continuous wavelet transforms (CWT) are then applied to the range signals of each region to derive continuous wavelet coefficients (CWCs). Subsequently, empirical mode decomposition (EMD) is performed on the CWCs to decompose them into intrinsic mode functions (IMFs) and residual signals. The 1st IMF is utilized for three-dimensional (3D) reconstruction, and the regions are fused to generate the final output. The effectiveness of the proposed method is validated on aircraft thermal protection structures (TPS), achieving high-precision 3D reconstruction. This offers a novel approach for the application of terahertz computed tomography imaging and NDT.

Probabilistic analysis of geological and structural Prospects for Oil and gas Potential in Western Yakutia Using three-Dimensional Empirical Mode Decomposition of Potential Fields

Further development of modern formal approaches to extracting geo-structural information from gravimetric and magnetometric data is herein discussed. A practical example of using 3D GEMD (three-dimensional controlled empirical mode decomposition) algorithm to calculate potential fields transforms associated with the impact of deep and medium (of different ranks) geological structures on the adjacent territories of Western Yakutia was considered. Two types of reference groups were determined based on analysis of the known hydrocarbon fields in the Lena-Vilyuy and Lena-Tunguska oil and gas provinces. Statistical efficiency of the observed fields, fields’ area transforms (modified functions of empirical decomposition), and also spatially-linked combinations of the said attributes, aiming to solve the forecasting tasks, was determined. As a result of integration within the testing area, layout diagrams of deep geological and structural prerequisites for oil and gas potential, similar to group standards, were drawn up. A geological interpretation of forecasting and geophysical constructions is presented. It is shown that a number of identified areas predicted with high probabilities correlate with depressions of rift zones. Combined with thick volcanogenic-sedimentary formations, the latter forms most prospective oil and gas content pre-requisites.

A diagnosis method for loss of circulation based on transient-pressure wave analysis and particle swarm optimization

Lost circulation during operations poses a significant threat to production processes. In the search for an effective detection method, an impulse-response detection method of lost circulation is introduced. This method involves generating transient pressure waves at the wellhead and analyzing their time-frequency domain characteristics to pinpoint location for lost circulation within the wellbore annulus system. Utilizing the data processing capabilities of machine learning models, this study proposes an integrated model for signal feature classification and diagnosis model for lost circulation. Drawing from extensive experimental data, this model integrates laboratory experiments, signal analysis, and machine learning algorithms. Data preprocessing, including wavelet variation and denoising, precedes the application of an enhanced adaptive noise complete ensemble empirical modal decomposition with adapted noise (ICEEMDAN) alongside energy and sample entropy analysis for feature extraction. By establishing a mapping relationship between signal features and lost circulation changes, we develop an improved backpropagation neural network (IBP) model using the particle swarm optimization (PSO) algorithm for diagnosis (PSO-IBP). Comparative analysis of five models reveals compelling results: ① PSO-IBP achieves an average accuracy of 97.60%, with a standard deviation of 0.356; ② diagnosis accuracy for every lost circulation scenario exceeds 92%, outperforming other models in precision, recall, and F-Score; ③ even with limited training data, PSO-IBP maintains 84% accuracy, demonstrating superior performance. Further analysis highlights the efficacy of PSO-IBP, especially when leveraging ICEEMDAN for signal feature extraction, in accurately diagnosing lost circulation.

A Study on Fault Localization Method of Three-Terminal Multi-Section Overhead Line–Cable Hybrid Line Using MEEMD Combined with Teager Energy Operator Algorithm

An improved fault localization method combining total aggregate empirical modal decomposition (MEEMD) and Teager energy operator (TEO) is proposed to address the fault localization issue of three-terminal multi-segment overhead line–cable hybrid transmission lines. This method solves the fault localization problem caused by wave impedance discontinuity in hybrid lines. First, the MEEMD algorithm, which improves modal aliasing, and the Teager energy operator, which reflects transient energy changes, are combined for the accurate detection of faulty traveling wave heads. The fault line section determination condition within the fault branch is used to determine the overhead line section or cable section where the fault is located after determining the faulty branch line. This condition is based on the time difference between the initial traveling wave of the fault arriving at each end measurement point and the T-node. Ultimately, the fault distance is determined using the double-ended traveling wave technique. By combining PSCAD and MATLAB for simulation verification, the accuracy of the ranging method is compared and analyzed, and the results show that the method is able to ensure the accuracy of ranging at different fault locations and transition resistances. Additionally, the localization error is basically kept within 30 m, which significantly improves the accuracy of fault localization.

Multivariate short-term wind speed prediction based on PSO-VMD-SE-ICEEMDAN two-stage decomposition and Att-S2S

To counter the challenges posed by the unpredictability of wind velocities on wind energy production, a wind speed prediction model combining chaotic mapping-based particle swarm optimization with variational modal decomposition (CPSO-VMD), sample entropy (SE), improved completely integrated empirical modal decomposition with adaptive noise (ICEEMDAN) two-layer decomposition, and attention mechanism-based sequence to sequence (Att-S2S) method is proposed. Firstly, the Lasso method is employed to filter the features that significantly contribute to the wind speed data, fully considering hidden relevant information and eliminating redundant data to improve the prediction accuracy; Secondly, CPSO optimized by introducing chaotic mapping determines the parameter pairs for VMD. This facilitates an adaptive VMD breakdown of the wind speed sequence, aiding in noise removal and selection of the intrinsic mode function (IMF) with the highest sample entropy for further decomposition using ICEEMDAN. In light of this, a sequence-to-sequence method based on the attention mechanism is suggested, which may highlight the influence features' effects on IMF; Finally, the proposed model is implemented at both the Paso Robles wind farm and the Oasis wind farm for practical assessment and benchmarked against other models. Overall, the proposed model outperforms the other models in these trials.

Improved bridge modal identification from vibration measurements using a hybrid empirical Fourier decomposition

Bridge health monitoring has been a prominent focus within the global engineering community. Bridge owners, stakeholders, and engineers face the formidable tasks of ensuring efficient monitoring, conducting reliable data analysis, interpreting data logically, and making timely decisions. With the increasing global infrastructure deficit, there is an ever-increasing need to develop reliable and economical bridge monitoring solutions. In this paper, a bridge condition assessment technique is proposed that can utilize the vibration data collected from the instrumented sensors and provide reliable system identification results. The proposed method develops a hybrid approach by integrating the Natural Excitation Technique (NExT) and Empirical Fourier Decomposition (EFD) to analyze ambient bridge vibration data and determine the modal parameters of the bridge. First, NExT is formulated to determine the cross-correlation functions of the bridge measurements, and then EFD is explored to decompose the signals into their monocomponents to identify the bridge modal parameters. The proposed methodology can overcome mode mixing and perform modal identification of a system with closely spaced frequencies and low energy modes. The estimated modal parameters such as bridge frequencies, mode shapes, and damping ratio are used for condition assessment of numerical, experimental and full-scale structures, including a short-span steel bridge located in Ontario, Canada. The results demonstrate that the proposed methodology can provide accurate and robust estimates of bridge modal parameters. Future research is reserved for real-time implementation of the proposed methodology for a wide range of civil structures.

A short-term electricity load forecasting method integrating empirical modal decomposition with SAM-LSTM

Short-term power load forecasting is the basis for ensuring the safe and stable operation of the power system. However, because power load forecasting is affected by weather, economy, geography, and other factors, it has strong instability and nonlinearity, making it difficult to improve the accuracy of short-term power load forecasting. To solve the above problems, a load forecasting method combining empirical modal decomposition (EMD) and long short-term memory neural network (LSTM) has been proposed. The original signal is first decomposed into a series of eigenmode functions and a residual quantity using the EMD algorithm. Subsequently, all the components are fed into the LSTM network. To further improve the load prediction accuracy, a self-attention mechanism is introduced for large component signals to further explore the internal correlation of the data, and the Sparrow Optimisation Algorithm (SSA) is used to optimize the LSTM hyperparameters. Combining EMD, LSTM, self-attention mechanism (SAM), and SSA, the EMD-SSA- SAM -LSTM method for short-term power load forecasting is further proposed. The results show that the coefficient of determination (R2) of the method is 0.98, the mean absolute error (MAE) is 0.013, the root mean square error (RMSE) is 0.018, and the mean absolute percentage error (MAPE) is 2.57%, which verifies that the proposed model can improve the accuracy of load forecasting, and has a certain application prospect.

Ultrasonic Pulse-Echo Signals for Quantitative Assessment of Reinforced Concrete Anomalies

This paper presents a study to accurately evaluate defects in concrete decks using ultrasonic pulse-echo signals. A reinforced concrete deck with void defects was designed and evaluated for validation, and a commercial ultrasonic pulse-echo (UPE) device was used to obtain the 2D images of the void defect inside the deck. The UPE image is based on the ultrasonic shear-wave test method and an extended synthetic aperture focusing technique (SAFT). To enhance the accuracy of the defect location in the SAFT imaging, the recorded A-scan data from UPE was analyzed using an advanced denoising approach and defect echo peak extraction, which are based on empirical modal decomposition, Hurst exponent characterization, and Hilbert envelope estimation. The results demonstrated that the location and depth of the void defect in the deck can be accurately assessed by using the developed approach. The new method provides quantitative information of the anomalies inside the deck, which can be used to calibrate the qualitative images of UPC devices with the SAFT.

Composite fault feature extraction for gears based on MCKD-EWT adaptive wavelet threshold noise reduction

For the strong noise gear fault vibration signal is relatively weak, and the transmission path is complex and variable, in the case of composite faults, the modulation of different fault characteristics of the frequency, coupling, resulting in the actual acquisition of the fault characteristics are difficult to extract and separate. Aiming at fault feature extraction and separation, an adaptive threshold denoising fault detection method based on Maximum correlated kurtosis deconvolution (MCKD) and Empirical wavelet transform (EWT) is proposed. Firstly, envelope entropy and information entropy are used as fitness functions, and the parameters of the MCKD algorithm are optimized by the improved particle swarm algorithm, then the empirical wavelet decomposition is carried out on the signals, and finally adaptive wavelet threshold denoising is carried out on the decomposed Intrinsic mode functions (IMFs) components. The results of experimental data analysis show that compared with the feature extraction methods such as spatial scale threshold EWT-MCKD and Complete Ensemble Empirical Mode Decomposition (CEEMDAN)-MCKD, the proposed method is more suitable for the diagnosis of gear composite faults in a strong background noise environment, the noise interference is effectively suppressed, and the extraction effect of gear composite fault features is more obvious.

Exploring the potential of pretrained CNNs and time-frequency methods for accurate epileptic EEG classification: a comparative study

Prompt diagnosis of epilepsy relies on accurate classification of automated electroencephalogram (EEG) signals. Several approaches have been developed to characterize epileptic EEG data; however, none of them have exploited time-frequency data to evaluate the effect of tweaking parameters in pretrained frameworks for EEG data classification. This study compares the performance of several pretrained convolutional neural networks (CNNs) namely, AlexNet, GoogLeNet, MobileNetV2, ResNet-18 and SqueezeNet for the localization of epilepsy EEG data using various time-frequency data representation algorithms. Continuous wavelet transform (CWT), empirical Fourier decomposition (EFD), empirical mode decomposition (EMD), empirical wavelet transform (EWT), and variational mode decomposition (VMD) were exploited for the acquisition of 2D scalograms from 1D data. The research evaluates the effect of multiple factors, including noisy versus denoised scalograms, different optimizers, learning rates, single versus dual channels, model size, and computational time consumption. The benchmark Bern-Barcelona EEG dataset is used for testing purpose. Results obtained show that the combination of MobileNetV2, Continuous Wavelet Transform (CWT) and Adam optimizer at a learning rate of 10−4, coupled with dual-data channels, provides the best performance metrics. Specifically, these parameters result in optimal sensitivity, specificity, f1-score, and classification accuracy, with respective values of 96.06%, 96.15%, 96.08%, and 96.10%. To further corroborate the efficacy of opted pretrained models on exploited Signal Decomposition (SD) algorithms, the classifiers are also being simulated on Temple University database at pinnacle modeling composition. A similar pattern in the outcome readily validate the findings of our study and robustness of deep learning models on epilepsy EEG scalograms.The conclusions drawn emphasize the potential of pretrained CNN-based models to create a robust, automated system for diagnosing epileptiform. Furthermore, the study offers insights into the effectiveness of varying time-frequency techniques and classifier parameters for classifying epileptic EEG data.

Prediction of Protein-DNA Interface Hot Spots Based on Empirical Mode Decomposition and Machine Learning.

Protein-DNA complex interactivity plays a crucial role in biological activities such as gene expression, modification, replication and transcription. Understanding the physiological significance of protein-DNA binding interfacial hot spots, as well as the development of computational biology, depends on the precise identification of these regions. In this paper, a hot spot prediction method called EC-PDH is proposed. First, we extracted features of these hot spots' solid solvent-accessible surface area (ASA) and secondary structure, and then the mean, variance, energy and autocorrelation function values of the first three intrinsic modal components (IMFs) of these conventional features were extracted as new features via the empirical modal decomposition algorithm (EMD). A total of 218 dimensional features were obtained. For feature selection, we used the maximum correlation minimum redundancy sequence forward selection method (mRMR-SFS) to obtain an optimal 11-dimensional-feature subset. To address the issue of data imbalance, we used the SMOTE-Tomek algorithm to balance positive and negative samples and finally used cat gradient boosting (CatBoost) to construct our hot spot prediction model for protein-DNA binding interfaces. Our method performs well on the test set, with AUC, MCC and F1 score values of 0.847, 0.543 and 0.772, respectively. After a comparative evaluation, EC-PDH outperforms the existing state-of-the-art methods in identifying hot spots.

Fault feature extraction method based on maximum envelope spectrum PFGI2 and empirical wavelet transform

Fast kurtogram (FK) is an efficient method for processing non-stationary signals, widely recognized by scholars as a rapid and effective approach for fault diagnosis. However, it has limitations in distinguishing between periodic pulse and random interference pulses due to the drawbacks in its frequency band segmentation methods and the inherent shortcomings of the kurtosis index itself. To address this, this paper proposes a fault feature extraction method based on the maximum envelope spectrum power function-based Gini indices (PFGI2) and empirical wavelet transform. This method, inspired by the concept of FK, constructs a series of band-pass filters following the principles of empirical wavelet decomposition. It applies envelope spectrum analysis to a series of sub-bands and calculates the PFGI2 value for each, to identify the optimal sub-band. The effectiveness of the proposed method is validated through simulations of vibration signals and experimental data.

Study on motion states of sphere based on empirical Fourier decomposition

This study uses Empirical Fourier Decomposition (EFD) to decompose the signal of motion of a sphere on a rough planar surface, which is a mixture of three main states: sliding, rolling, and collision. The simulation results show that the decomposed sub- signals are consistent with the original signals. Furthermore, we conducted a laboratory experiment to study the movement of a sphere on a rough inclined chute. The movement of the sphere is divided into two main stages: low-speed rolling and bouncing forward. In the first stage, the sphere motion consists mainly of rolling and collision. In the second stage, the sphere motion consists of sliding, rolling, and collision. We propose for the first time that the duration and peak acceleration of collisions from two stages follow a normal distribution.

A Fault Diagnosis Method for Rectifier-Filter Circuit Integrating EEMD Algorithm and Transformer Network

Rectifier-filter circuit, as a critical component of the drive circuit in instrumentation and control systems of nuclear power plants, can convert the 50 Hz AC into the smooth DC. Thus, it plays a vital role in the power control of reactors. However, the weak waveform anomalies of soft faults in the rectifier-filter circuit make fault feature extraction difficult. Therefore, in this article, an ensemble empirical modal decomposition (EEMD) algorithm is employed to decompose the signal mode components in the monitor data of the rectifier-filter circuit. The weak waveform anomalies are indirectly enhanced by the IMF and residual components. Subsequently, the Transformer network is utilized to construct the feature extractor. With the advantage of multi-head attention (MHA) mechanism in the Transformer network, the multi-directional, multi-scale, and highly sensitive long-range time-dependent features in the EEMD feature data are extracted. Then, a deep Softmax classifier is adopted to reduce the dimensionality and diagnose the soft faults of the rectifier-filter circuit. Finally, a fault simulation model of the rectifier-filter circuit is constructed and the condition monitor data are collected. The effectiveness and diagnosis accuracy of the proposed method are verified by a real case experiment and some comparative methods.