Empirical Mode Decomposition Technique Research Articles

EMD AND WAVELET-BASED ECG SIGNAL DENOISING AND QRS COMPLEX DETECTION

This project presents a novel method for noise removal and QRS complex detection in electrocardiogram (ECG) signals, employing Empirical Mode Decomposition (EMD), windowing, and wavelet thresholding techniques. Noise is added to the ECG signal, and EMD is applied to obtain denoised components. Local minima detection and peak matching identify QRS complex boundaries. Windowing isolates the QRS regions, followed by wavelet thresholding for further denoising. Evaluation metrics like improved Signal-to-Noise Ratio, Mean Square Error, and Percent Root Mean Square Difference are calculated at different input SNR values, demonstrating the method's effectiveness in preserving the QRS complex while removing noise.. Keywords: ECG signal processing, QRS complex detection, Empirical Mode Decomposition (EMD), Windowing, Wavelet thresholding, QRS complex extraction, Signal-to-Noise Ratio (SNR), Mean Square Error (MSE), Percent Root Mean Square Difference (PRD).

Fault Detection and VSC-HVDC Network Dynamics Analysis for the Faults in Its Host AC Networks

High-voltage direct current (HVDC) transmission is preferred over high-voltage alternating current (HVAC) for long power lines for asynchronous power grid interconnection and high-level renewable energy integration. The control and protection functions associated with HVDC systems help with fast and secure clearance of faults. The control and protection challenges in the embedded HVDC network are of great concern for the stable and secure operation of an HVDC network. The DC fault current may reach an extremely high level in a rather short period because of the low impedance in a DC system, which is dangerous for converters, and disturbances in the AC network directly influence the performance of the HVDC system. Sometimes, faults on the AC side may lead to disconnection or failure of the DC link, causing reliability problems as well as huge economic losses. AC and DC protection solutions are being developed for HVDC systems to enhance their sustainability and reliability. As such, AC and DC faults should be detected and cleared at a faster rate. Therefore, in this article, the feasibility of the synchro-squeezed transform (SST) is analyzed for detection purposes. For more accurate and faster detection, the signal is first decomposed using the empirical mode decomposition (EMD) technique, and then the SST is applied. A discrete Teager energy (DTE) spectrum is obtained with the processed signal, which works as the detection index. The algorithm shows low sampling frequency requirements, with higher efficiency and reliability for the purpose. PSCAD/EMTDC version 4.6 software and MATLAB 2022a software is used for the modeling and simulation.

Estimating Rotational Acceleration in Shoulder and Elbow Joints Using a Transformer Algorithm and a Fusion of Biosignals.

In the present study, we used a transformer model and a fusion of biosignals to estimate rotational acceleration in elbow and shoulder joints. To achieve our study objectives, we proposed a mechanomyography (MMG) signal isolation technique based on a variational mode decomposition (VMD) algorithm. Our results show that the VMD algorithm delivered excellent performance in MMG signal extraction compared to the commonly used technique of empirical mode decomposition (EMD). In addition, we found that transformer models delivered estimates of joint acceleration that were more precise than those produced by mainstream time series forecasting models. The average R2 values of transformer are 0.967, 0.968, and 0.935, respectively. Finally, we found that using a fusion of signals resulted in more precise estimation performance compared to using MMG signals alone. The differences between the average R2 values are 0.041, 0.053, and 0.043, respectively. Taken together, the VMD isolation method, the transformer algorithm and the signal fusion technique described in this paper can be seen as supplying a robust framework for estimating rotational acceleration in upper-limb joints. Further study is warranted to examine the effectiveness of this framework in other musculoskeletal contexts.

Remaining Useful Life Prediction of Lithium‐Ion Batteries Based on a Combination of Ensemble Empirical Mode Decomposition and Deep Belief Network–Long Short‐Term Memory

The prediction of remaining useful life (RUL) for lithium‐ion batteries is a critical component of electric vehicle battery management systems. However, during the aging process, batteries exhibit an overall declining trend in capacity curves, coupled with capacity regeneration and localized fluctuations. Directly modeling this degradation trend based on the original capacity curve proves challenging, leading to reduced accuracy in RUL prediction. This article introduces a hybrid method to enhance the precision of battery RUL prediction. Utilizing the ensemble empirical mode decomposition technique, the battery's capacity degradation sequence is decomposed into intrinsic mode functions (IMFs) with varying degrees of fluctuations, along with a residue that characterizes the battery's overall declining trend. Subsequently, deep belief networks and long short‐term memory networks are established to predict the residue and IMFs separately. The combined results from these models yield the final battery RUL prediction. Finally, the effectiveness of this approach is validated on the NASA battery dataset, with diverse training periods and prediction time steps. Experimental results demonstrate that the root mean square error of predictions for all four batteries remains below 2%.

Hybrid energy storage configuration method for wind power microgrid based on EMD decomposition and two-stage robust approach

Data centers are usually characterized by high energy loads, which raises increasing sustainability concerns in both academic and daily usage. To mitigate the uncertainty and high volatility of distributed wind energy generation, this paper proposes a hybrid energy storage allocation strategy by means of the Empirical Mode Decomposition (EMD) technique and the two-stage robust method. First, this paper conducts the evolution analyses for the over- and under-evaluated uncertainty of wind power fluctuation under different time scales. Second, we employ the EMD technique to configure a high-frequency flywheel energy storage device, realizing the wind power transformation from large fluctuations to small fluctuations and the convergence of the wind power fluctuation curves in minute- and hour levels. Finally, based on the hour-level wind energy stable power curves, we carry out two-stage robust planning for the equipment capacity of low-frequency cold storage tanks and lithium bromide chillers. The case study on a data center microgrid in northeastern China confirms the effectiveness of our proposed strategy.

Using 3D-VGG-16 and 3D-Resnet-18 deep learning models and FABEMD techniques in the detection of malware

Currently, the detection of malware to prevent cybersecurity breaches is a raising a concern for millions of people around the globe. Even with the most recent updates, antivirus software can leave computer users vulnerable to malware threats and attacks due to the rapid release of new malware. As a result, conventional antivirus software is frequently incapable of identifying novel forms of malware until their unique signatures have been added to the software's database. To protect systems, there is necessity in the current technology field to develop innovative techniques for detecting unidentified malware, particularly during the initial phases of malware deployment. The objective is to address the issue of imbalanced and inadequate malware dataset through the utilization of the fast and adaptive bidirectional empirical mode decomposition (FABEMD) technique. While exploring the Malimg and MaleVis datasets, promising results were reached in reference to accuracy, precision, recall, and F1-score. The experiment demonstrated the accuracy of two distinct 3D architectures, namely 3D VGG-16 and 3D Resnet-18, on two separate datasets: Malimg dataset and MaleVis dataset. The accuracy achieved for VGG-16 was 96.14% and 98.60% for the Malimg and the MaleVis dataset, respectively. In regards to the Resnet-18 architecture, it demonstrated high accuracy rates of 99.64% and 99.46% for the Malimg and MaleVis datasets, respectively.

Synergizing Smart Agriculture with Hybrid Deep Learning: Predicting Crop Yields Using IoT

Agriculture can be defined as the systematic and intentional practice of cultivating and managing plants and animals to produce food, fiber, and other agricultural products. Agricultural practices in India hold the second position globally and encompass approximately 61.1% of the total land area in the country. The Indian economy primarily relies on agriculture and agro-industrial products. Various factors, such as soil composition (including elements like Nitrogen, phosphorus, and Potassium), crop rotation practices, soil moisture content, ambient temperatures, precipitation patterns, and other relevant variables, can significantly influence crop productivity. Smart Agriculture (SA) implementation has recently yielded significant practical benefits, establishing it as a highly significant and valuable system. Using environmental information, including wind velocity, temperature, and moisture, in outdoor plantations facilitates farming operations’ strategic management and regulation, enhancing crop yield and quality. Accurately predicting crop yield trends poses a challenge due to the intricate nature of sensing data, characterized by complexity, nonlinearity, and multiple variables. This study proposes a Hybrid Deep Learning model for Predicting Crop Yields (HDL-PCY) using the Internet of Things (IoT). The HDL-PCY system utilizes the Empirical Mode Decomposition (EMD) technique to break down the crop yield information into distinct element groups with varying frequency attributes. Subsequently, a Long Short-Term Memory (LSTM) network is trained for each group to serve as a sub-predictor. Finally, the predictions generated by the LSTM networks are combined to produce the overall prediction result. The obtained results demonstrate that the proposed HDL-PCY can achieve higher levels of accuracy of 97.32%, 98.03%, 98.74%, and 95.92% for precipitation, temperature, pH, and moisture content, respectively, thereby catering to the requirements of SA.

A multi-step electricity prediction model for residential buildings based on ensemble Empirical Mode Decomposition technique

Residential electricity demand is increasing rapidly, constituting about a quarter of total energy consumption. Electricity demand prediction is one of the sustainable solutions to improve energy efficiency in real-world scenarios. The non-linear and non-stationary consumption patterns in residential buildings make electricity prediction more challenging. This paper proposes a multi-step prediction approach that first conducts cluster analysis to identify seasonal consumption patterns. Secondly, an improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) method and autoencoder model has been deployed to remove irregular patterns, noise, and redundancy from electricity load time series. Finally, the Long Short-Term Memory (LSTM) model has been trained to predict electricity consumption by considering historical, seasonal, and temporal data dependencies. Further, experimental analysis has been conducted on real-time electricity consumption datasets of residential buildings. The comparative results reveal that the proposed multi-step model outperformed the existing state-of-the-art RF-LSTM-based prediction model and attained higher accuracy.

Reducing wave impacts on high-speed catamarans through deployment of ride control: Analysis of full-scale measurements

Full-scale trials on a 98 m wave piercer catamaran were conducted in the North Sea and North Atlantic region. In order to examine, amongst other things, the effectiveness of the ride control system, the ship was deliberately operated in sea conditions likely to induce a large number of wave impact events. Primary ship motion and structural response parameters, such as angles, rates and accelerations, and strains at various locations were recorded. Slam and minor wave impact events were identified in the data records and analysed to determine the influence of wave headings, vessel speeds, sea states and ride control system activation on their occurrence rates and severity. The Empirical Mode Decomposition technique was used to remove both noise and the rigid body response from the acceleration signals. This was based on prior work by the authors and found to provide more reliable slam identification than traditional methods. A prediction of extreme slam occurrences was modelled using logistic regression. A key outcome of the study was the finding that the activation of ride control significantly reduces the probability of extreme slams occurring.

Development of an enhanced bidirectional recurrent neural network combined with time-varying filter-based empirical mode decomposition to forecast weekly reference evapotranspiration

Evapotranspiration is one of agricultural water management's most significant and impactful hydrologic processes. A new multi-decomposition deep learning-based technique is proposed in this study to forecast weekly reference evapotranspiration (ETo) in western coastal regions of Australia (Redcliffe and Gold Coast). The time-varying filter-based empirical mode decomposition (TVF-EMD) technique was used to first break down the original meteorological variables/signals into intrinsic mode decomposition functions (IMFs), which included maximum and minimum temperature, relative humidity, wind speed, and solar radiation. Using a partial autocorrelation function (PACF), the significant lagged values were then calculated from the decomposed sub-sequences (i.e., IMFs). A novel Extra Tree- Boruta feature selection algorithm was used to extract important features from the decomposed IMFs. Four machine learning approaches, including bidirectional recurrent neural network (Bi-RNN), multi-layer perceptron neural network (MLP), random forest (RF), and extreme gradient boosting (XGBoost), were used to forecast weekly evapotranspiration using the TVF-EMD-based decomposed meteorological data. Different statistical metrics were applied to evaluate the model performances. The results showed that the decomposition of the input data by TVF-EMD significantly improved the accuracy compared with the non-decomposed inputs (single models without decomposition). The findings indicate that the TVF-BiRNN model, as presented, achieved the highest level of accuracy in simulating weekly ET0 at both the Redcliffe and Gold Coast stations (Redcliffe: R=0.9281, RMSE=3.8793 mm/week, MAPE = 9.2010%; Gold Coast: R=0.8717, RMSE=4.1169 mm/week, MAPE = 11.5408%). The novel hybrid modeling technique can potentially improve agricultural water management through its ability to generate more accurate ETo estimates weekly. The proposed methodology exhibits potential applicability to various other environmental and hydrological modeling issues.

A novel hybrid model to forecast seasonal and chaotic time series

Accurate time series forecasting is crucial, particularly in real-world application areas such as demand forecasting. The Prophet model successfully predicts time series containing well-known seasonal patterns but performs less effectively on time series exhibiting chaotic patterns. To overcome this, we propose a novel methodology that combines the empirical mode decomposition (EMD) technique and its noise-assisted variations with the Prophet model. One key property of this methodology is its ability to analyze the seasonality and chaos present in each time series and recommend a suitable forecasting method accordingly. The proposed methodology decomposes chaotic time series into multiple sub-series at various frequencies using EMD and its two noise-assisted extensions: Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and Improved CEEMDAN. Subsequently, models are fitted for each sub-series using the Prophet model, and the resulting forecasts are aggregated to generate a final prediction. We conducted an empirical study using seven time series datasets. Experimental results indicate that the proposed methodology generates accurate models that outperform benchmark methods when applied to time series with chaotic characteristics. Furthermore, the models obtained using our proposed methodology exhibit higher accuracy compared to the best models selected from the existing literature.

Fatigue crack localisation based on empirical mode decomposition and pre-selected entropy

ABSTRACT Fatigue cracks, especially at their initial stage, can lead to a repetitive crack open-close breathing-like phenomenon in the vibration response of structural elements. As such, regularities, bi-linearity, or perturbations in the vibration response can arise. Entropy can be used to quantify the irregularity or bi-linearity in these responses since there is an apparent variation of entropy values on the two sides of a breathing crack. Here, we present a new breathing crack localisation method based on a spatially distributed entropy approach coupled with the empirical mode decomposition technique. To enhance the robustness, a pre-selection mechanism is proposed to select the most suitable entropy method. The proposed method is then employed to localise the breathing crack in a beam in a laboratory setup. It is concluded that the proposed approach can be effectively used for breathing crack localisation in a structural element.

Automatic selection of IMFs to denoise the sEMG signals using EMD

Surface Electromyography (sEMG) signals are muscle activation signals, which has applications in muscle diagnosis, rehabilitation, prosthetics, and speech etc. However, they are known to be affected by noises such as Power Line Interference (PLI), motion artifacts etc. Currently, Empirical Mode Decomposition (EMD) and its modifications such as Ensemble EMD (EEMD), and Complementary EEMD (CEEMD) are used to decompose EMG into a series of Intrinsic Mode Functions (IMFs). The denoised EMG can be obtained from the selected IMFs. Statistical methods are used to select the signal dominant IMFs to reconstruct the denoised signal. In this work, a novel procedure is proposed to automatically separate noisy IMFs from the original sEMG signal. For this purpose, Permutation Entropy (PE) is employed in EEMD sifting process called Partly EEMD (PEEMD), to separate the noisy IMFs from the original sEMG signal according to the preset PE threshold. PEEMD decomposes the original signal into various modes according to a preset PE threshold and the denoised signal is reconstructed from resultant IMFs. The PEEMD denoising procedure is applied on the experimental sEMG data collected from eight subjects, that include six various upper limb movement classes. The proposed denoising procedure achieved an improved denoising performance in comparison with EMD, EEMD, and CEEMD. An alternate measure called Sample Entropy (SE) is also used in place of PE, for the automated sifting process as a comparison. Signal to Noise Ratio (SNR), Root Mean Square Error (RMSE), and Reconstruction Error (RE) parameters are used to evaluate the denoising performance. The results, averaged across eight subjects, demonstrate that the proposed denoising procedure outperforms the state-of-the-art EMD techniques in terms of these performance measures on the experimentally collected sEMG data samples.

Analysis of Breathing Rate Estimation Using Adaptive Techniques

Breathing rate (BR) is an important physiological factor that is commonly measured in many treatment settings. Though it is still routinely measured by hand. In this study, a novel approach for determining the BR from an ECG, photoplethysmogram, or blood pressure signal is proposed. To extract respiratory signals from time and frequency domain data, the framework employs Discrete Wavelet Transform and Empirical Mode Decomposition techniques. Because we used a Robust Kalman Filter with a Signal Quality Index, our technique worked effectively even when the signals were severely damaged. The output signals have been integrated by state vector fusion, and the BR has been established. Two openly available clinical databases, the MIT-BIH Polysomnographic and the BIDMC datasets are used. The mean absolute percentage error was used to assess performance. The results were very accurate; PPG signals had MAPEs of 7% and BP signals of 5.4%, whereas ECG signals on the two databases had MAPEs of 4% and 4%, respectively.Additionally,the results revealed an astounding robustness to noise at 0 db. In light,this technique may be beneficial for BR monitoring in noisy areas.

Application of the Empirical Mode Decomposition Method to Noise Reduction Using Seismic Event Data Recorded at Kirkuk Seismological Station.

This study aims to use the Empirical Mode Decomposition for reducing the noise of passive seismic signals recorded across seismic event recorded at Kirkuk station which is one of the Iraqi Meteorological Organization and Seismology data, where human activities in Iraq's populous cities significantly impact the seismic recordings at Iraqi Meteorological Organization and Seismology stations sites. In this paper, we present an algorithm based on the Empirical Mode Decomposition. It is a data driven method used as a propelling tool for analyzing and decomposing non-stationary and non-linear data without any previous assumptions. Empirical Mode Decomposition generates a finite and often small number of Intrinsic Mode Functions. The decomposition is based on the direct extraction of the energy related to various intrinsic time scales, an important parameter of the system. Empirical Mode Decomposition technique is applied to the available seismic records to reduce the noise level in the records, which helps in the interpretation of the records.

Capacity optimal allocation of hybrid energy storage in DC distribution network based on Ensemble Empirical Mode Decomposition

In response to fluctuations in the power levels within the link connecting the direct current transmission system to the upper-level power grid, we propose an optimization approach for determining the ability of a Hybrid Energy Storage System (HESS). Our first step involves calculating the power agreement for the link and the total power requirements for the HESS, taking into account the system’s net load power and the dynamic pricing of electricity based on time-of-use. Subsequently, we utilize the Ensemble Empirical Mode Decomposition (EEMD) technique to break down the total energy generated by the HESS into its constituent components. Incorporating instructions for both powering up and losing power of the HESS across varying filter orders, we solve the capacity allocation model for the HESS using a particle swarm algorithm, with rated power and rated capacity as decision variables. Finally, we identify the filter order that yields the best objective function value and the corresponding energy storage configuration scheme. An illustrative analysis, conducted on an enhanced IEEE-14 node DC distribution network, demonstrates that the proposed HESS configuration effectively mitigates tie-line fluctuations and enhances system stability.

ELM-based stroke classification using wavelet and empirical mode decomposition techniques

ABSTRACT Biomedical signal processing is crucial in many sectors that save lives. Artificial intelligence improvement in signal collection and conditioning boosted this application’s adaptability to varied bodily circumstances. In this study, a novel method is put forth for predicting the type of stroke in the human brain based on the observation of the Electroencephalography (EEG) signal. The signal is the first condition for removing undesirable frequencies by passing through a lowpass filter. To accurately extract the signal features, the signal is first transformed into a 1-second frame format and then normalised. Certain statistical and frequency domain aspects are highlighted to increase taxonomic accuracy. Under the wavelet packet transform, the empirical mode decomposition approach is utilised to recover the most information feasible from the signal. After training on extracted characteristics, the extreme learning machine is regarded to conduct classification. These work achieves 94.95 of Sensitivity, 84.95 of Specificity, 93.74 of Precision, 96.96 of Accuracy, 96.12 of F1 Score. Compared to the standard procedures, the proposed techniques have a greater accuracy rate of about 98%.

Differential absorption LIDAR signal denoising using empirical mode decomposition technique

Differential absorption LIDAR signal denoising using empirical mode decomposition technique

Improving speech communication in the age of face masks: A study on EMD denoising method by subjective speech comparison

The widespread use of face masks during the COVID-19 pandemic has posed challenges to effective communication. This study investigates the application of the Empirical Mode Decomposition (EMD) denoising method to enhance the quality of acoustic signals affected by face masks. The EMD technique utilizes a Fast Fourier transform (FFT) of the intrinsic mode function to distinguish noise from the signal and improve the acoustic signal. The EMD-enhanced speech signal is compared to the acquired speech signal using Comparison Mean Opinion Scores (CMOS), and the spectral subtraction speech enhancement signal is also evaluated using CMOS. The results from various experimental conditions consistently demonstrate the superior performance of EMD denoising in producing enhanced signals. Specifically, the EMD method outperforms the spectral subtraction method in improving speech signal quality affected by face masks. These findings underscore the effectiveness of the EMD denoising method in improving the quality of speech signals impacted by face masks, highlighting its potential for enhancing communication in challenging acoustic environments.

EEG-based clinical decision support system for Alzheimer's disorders diagnosis using EMD and deep learning techniques.

Despite the existence of numerous clinical techniques for identifying neurological brain disorders in their early stages, Electroencephalogram (EEG) data shows great promise as a means of detecting Alzheimer's disease (AD) at an early stage. The main goal of this research is to create a reliable and accurate clinical decision support system leveraging EEG signal processing to detect AD in its initial phases. The research utilized a dataset consisting of 35 neurotypical individuals, 31 patients with mild AD, and 22 patients with moderate AD. Data were collected while participants were at rest. To extract features from the EEG signals, a band-pass filter was applied to the dataset and the Empirical Mode Decomposition (EMD) technique was employed to decompose the filtered signals. The EMD technique was then leveraged to generate feature vectors by combining multiple signal features, thereby enhancing diagnostic performance. Various artificial intelligence approaches were also explored and compared to identify features of the extracted EEG signals distinguishing mild AD, moderate AD, and neurotypical cases. The performance of the classifiers was evaluated using k-fold cross-validation and leave-one-subject-out (LOSO) cross-validation methods. The results of this study provided valuable insights into potential avenues for the early diagnosis of AD. The performance of the various offered methodologies has been compared and evaluated by computing the overall diagnosis precision, recall, and accuracy. The proposed methodologies achieved a maximum classification accuracy of 99.9 and 94.8% for k-fold and LOSO cross-validation techniques, respectively. The study aims to assess and compare different proposed methodologies and determine the most effective combination approach for the early detection of AD. Our research findings strongly suggest that the proposed diagnostic support technique is a highly promising supplementary tool for discovering prospective diagnostic biomarkers that can greatly aid in the early clinical diagnosis of AD.