Mode Decomposition Approach Research Articles

Blind Source Separation Using Time-Delayed Dynamic Mode Decomposition

Blind Source Separation (BSS) is a significant field of study in signal processing, with many applications in various fields such as audio processing, speech recognition, biomedical signal analysis, image processing and communication systems. Traditional methods, such as Independent Component Analysis (ICA), often rely on statistical independence assumptions, which may limit their performance in systems with significant temporal dynamics. This paper introduces an extension of the dynamic mode decomposition (DMD) approach by using time-delayed coordinates to implement BSS. Time-delay embedding enhances the capability of the method to handle complex, nonstationary signals by incorporating their temporal dependencies. We validate the approach through numerical experiments and applications, including audio signal separation, image separation and EEG artifact removal. The results demonstrate that modification achieves superior performance compared to conventional techniques, particularly in scenarios where sources exhibit dynamic coupling or non-stationary behavior.

Research on Physically Constrained VMD-CNN-BiLSTM Wind Power Prediction

Accurate forecasting of wind power is crucial for addressing energy demands, promoting sustainable energy practices, and mitigating environmental challenges. In order to improve the prediction accuracy of wind power, a VMD-CNN-BiLSTM hybrid model with physical constraints is proposed in this paper. Initially, the isolation forest algorithm identifies samples that deviate from actual power outputs, and the LightGBM algorithm is used to reconstruct the abnormal samples. Then, leveraging the variational mode decomposition (VMD) approach, the reconstructed data are decomposed into 13 sub-signals. Each sub-signal is trained using a CNN-BiLSTM model, yielding individual prediction results. Finally, the XGBoost algorithm is introduced to add the physical penalty term to the loss function. The predicted value of each sub-signal is taken as the input to get the predicted result of wind power. The hybrid model is applied to the 12 h forecast of a wind farm in Zhangjiakou City, Hebei province. Compared with other hybrid forecasting models, this model has the highest score on five performance indicators and can provide reference for wind farm generation planning, safe grid connection, real-time power dispatching, and practical application of sustainable energy.

Fused Multi-Domains and Adaptive Variational Mode Decomposition ECG Feature Extraction for Lightweight Bio-Inspired Key Generation and Encryption.

Security is one of the increasingly significant issues given advancements in technology that harness data from multiple devices such as the internet of medical devices. While protecting data from unauthorized user access, several techniques are used including fingerprints, passwords, and others. One of the techniques that has attracted much attention is the use of human features, which has proven to be most effective because of the difficulties in impersonating human-related features. An example of a human-related attribute includes the electrical signal generated from the heart, mostly referred to as an Electrocardiogram (ECG) signal. The methods to extract features from ECG signals are time domain-based; however, the challenge with relying only on the time-domain or frequency-domain method is the inability to capture the intra-leading relationship of Variational Mode Decomposition signals. In this research, fusing multiple domains ECG feature and adaptive Variational Mode Decomposition approaches are utilized to mitigate the challenge of losing the intra-leading correlations of mode decompositions, which might reduce the robustness of encryption algorithms. The features extracted using the reconstructed signal have a mean (0.0004), standard deviation (0.0391), skewness (0.1562), and kurtosis (1.2205). Among the lightweight encryption methods considered, Chacha20 has a total execution time of 27µs. The study proposes a lightweight encryption technique based on the fused vector representation of extracted features to provide an encryption scheme in addition to a bio-inspired key generation technique for data encryption.

A Hybrid Data Assimilation and Dynamic Mode Decomposition Approach for Xenon Dynamic Prediction of Nuclear Reactor Cores

In this paper, a dynamic prediction scheme that combines the data assimilation method and dynamic mode decomposition (DMD) is brought out for the prediction of the whole-core power distribution under xenon oscillations within the HRP1000 reactor. The DMD is used to predict the power values over the nodes where in-core detectors exist, and predicted power is then extended to the whole core using data assimilation methodologies, e.g. the inverse distance–based data assimilation method. In the data assimilation stage, the selection of the background physical field and the regularization factor under different noise levels is investigated. A series of numerical experiments, based on the HPR1000 proof of feasibility of the coupling scheme, is conducted under low noise levels or low prediction step sizes. Finally, the optimal application conditions and the prediction performance of the coupling scheme in different noise levels are analyzed for practical engineering usage.

Physics-informed dynamic mode decomposition for reconstruction and prediction of dense particulate pipe flows

Dynamic mode decomposition (DMD) effectively captures the growth and frequency characteristics of individual modes, enabling the construction of reduced-order models for flow evolution, thereby facilitating the prediction of fluid dynamic behavior. However, DMD's predictive accuracy is inherently constrained by its inability to inherently incorporate physical principles. Therefore, for dense particulate pipe flows with complex flow mechanisms, we introduce a physics-informed dynamic mode decomposition (PIDMD) approach, which augments the purely data-driven DMD framework by incorporating the conservation of mass as a constraint. This ensures that the extracted dynamic modes adhere to known physical principles. Initially, we apply the DMD to reconstruct and predict the velocity field, comparing the results against benchmark computational fluid dynamics-discrete element method (CFD-DEM) simulations. Findings indicate that while DMD can reconstruct the flow field simulated by CFD-DEM and provide predictions of future flow states, its predictive accuracy gradually deteriorates over time. Next, we utilize both PIDMD and DMD to reconstruct and predict particle volume fraction, evaluating both models based on CFD-DEM outcomes. The results indicate that both PIDMD and DMD can predict particle aggregation toward the center, but PIDMD provides more accurate predictions regarding the size of particle aggregations and their distribution near the tube wall. Furthermore, the average prediction error for particle volume fraction using PIDMD is 6.54%, which is lower than the error of 13.49% obtained by DMD. Both qualitative and quantitative comparisons highlight the superior predictive capability of PIDMD. The methodology developed in this study provides valuable insights for high-precision predictions of particulate flows.

Accelerometer-assisted computer vision data fusion framework for structural dynamic displacement reconstruction

Accurate displacement measurement provides crucial information for evaluating the structural health condition. It is important to note that both direct and indirect displacement measurement methods have their own limitations, which can be remedied by leveraging each other’s strengths. In this study, a novel accelerometer-assisted computer vision data fusion framework is developed for accurately reconstructing structural dynamic displacement. The framework does not require a specific mathematical model or prior knowledge about the data’s characteristics, allowing it to be applied more broadly across different applications without the constraints of model assumptions. The core of this framework is to integrate successive variational mode decomposition (SVMD) and Bayesian optimization approaches to adaptively determine the weight factors of the fusion components. Importantly, an enhanced optical flow approach is presented for converting pixel movement to structural displacement from natural targets. This approach can effectively reduce the selection of mis-matched points within the ROI (Region of Interest), thereby reducing drift errors. The developed framework is verified via shaking table tests of a reinforced concrete frame structure under seismic excitation. Results indicate that the developed framework excels in accurately estimating structural dynamic displacement. Compared to single-vision displacement identification results, the proposed framework demonstrates lower peak error (< 1.65 mm) and normalized root mean square error (< 0.30). Meanwhile, the reconstructed displacement, by introducing dynamic displacement component from acceleration measurement, presents a wider frequency range than the vision-based displacement.

Advancements in Blind Source Separation for EEG Artifact Removal: A comparative analysis of Variational Mode Decomposition and Discrete Wavelet Transform approaches

Electroencephalography (EEG) is a vital tool for elucidating cerebral processes; however, it is inherently vulnerable to physiological interference, including cardiac rhythm, ocular movement, and muscular activity. To guarantee the reliability of essential neuronal data, it is imperative to implement efficacious denoising methodologies. This study compares the efficacy of two advanced blind source separation (BSS) techniques applied to EEG signals: variational mode decomposition-based BSS (VMD-BSS) and discrete wavelet transform-based BSS (DWT-BSS). The efficacy of these methods is rigorously assessed using performance metrics such as the Euclidean Distance (ED) and the Spearman Correlation Coefficient (SCC), which evaluate the precision of signal reconstruction and the correlation between the original and denoised signals, respectively. The findings indicate that both methods yield robust results, with minimal Euclidean distances of 704.04 for VMD-BSS and 703.64 for DWT-BSS, and a strong correlation coefficient of 0.82. The results demonstrate the effectiveness of the proposed techniques in removing artifacts while preserving essential neural information in EEG recordings. Furthermore, the proposed techniques are benchmarked against previous studies, considering factors such as signal properties, computational complexity, frequency localization, and flexibility. These findings highlight the importance of customized parameter selection tailored to the specific characteristics of EEG datasets and research objectives.

A 2D VMD video image processing-based transfer learning approach for the detection and estimation of biofouling in tidal stream turbines

Harnessing the power of tidal streams is a sustainable way of exploiting renewable marine energy resources. It involves installing tidal stream turbines underwater to harness the energy. Nevertheless, these turbines are prone to the accumulation of biofouling, which significantly reduces their energy output and operational efficiency. It is therefore crucial to implement a condition-based monitoring system to detect biofouling promptly and ensure the continuous operation of a tidal stream turbine. In this context, this paper presents a data-centric approach that uses model submerged tidal stream turbine video images to detect and quantify biofouling. The relevance of a two-dimensional variational mode decomposition approach is investigated to extract relevant information from the potentially noisy collected images. While generative adversarial networks are used to address the data imbalance problem, a convolutional neural network is adopted to detect and assess the extent of biofouling. The performance of the proposed approach is assessed and validated using two experimental datasets obtained from the tidal stream turbine platforms of the Shanghai Maritime University and the Lehigh University.

Optimized air quality management based on air quality index prediction and air pollutants identification in representative cities in China

With the ongoing challenge of air pollution posing serious health and environmental threats, particularly in rapidly industrializing regions, accurate forecasting and effective pollutant identification are crucial for enhancing public health and ecological stability. This study aimed to optimize air quality management through the prediction of the Air Quality Index (AQI) and identification of air pollutants. Our study spans nine representative cities (Hohhot, Yinchuan, Lanzhou, Beijing, Taiyuan, Xi’an, Shanghai, Nanjing, Wuhan) in China, with data collected from January 1, 2015, to November 30, 2021. We proposed a new model for daily AQI prediction, termed VMD-CSA-CNN-LSTM, which employed advanced machine learning techniques, including convolutional neural networks (CNN) and long short-term memory (LSTM) networks, and leveraged the chameleon swarm algorithm (CSA) for hyperparameter optimization, integrated through a variational mode decomposition approach. The model was developed using data from Lanzhou, with a split ratio of 8:1:1 into training, validation, and test sets, achieving an RMSE of 2.25, MAPE of 0.02, adjusted R-squared of 98.91%, and training efficiency of 5.31%. The model was further externally validated in the other eight cities, yielding comparable results, with an adjusted R-squared above 96%, MAPE below 0.1, and RMSE below 7.5. Additionally, we employed a random forest algorithm to identify the primary pollutants contributing to AQI levels. Our results indicated that PM2.5 was the most significant pollutant in Beijing, Taiyuan, and Xi’an, while PM10 was dominant in Hohhot, Yinchuan, and Lanzhou. In Shanghai, Nanjing, and Wuhan, both PM2.5 and PM10 were critical, with ozone also identified as a major air pollutant. This study not only advances the predictive accuracy of AQI models but also aids policymakers by providing a reliable tool for air quality management and strategic planning aimed at pollution reduction. The integration of these advanced computational techniques into environmental monitoring practices offers a promising avenue for enhancing air quality and mitigating pollution-related risks.

Bridge the gap between simulated and real-world data in optical fiber mode decomposition for accuracy improvement: A deep learning-based co-learning framework with visual similarity-based matching

In the area of optical fiber mode decomposition (MD), data-driven deep-learning (DL) algorithms have achieved remarkable strides with unlimited theoretically synthetic data, but the differences between theoretical and real-world data in the DL context are rarely investigated. The two differences, namely the information bottleneck and the domain discrepancy, between the simulation and realistic domain remain significant obstacles that limit the practical deployment of DL-based MD approaches in real-world optical systems. The paper aims to mitigate their influence on the accuracy limitation and the accuracy degradation of DL-based MD. First, we present a DL-based co-learning framework for MD for the first time. With the co-learning process, the knowledge of the teacher model learned from rich input information sources (near-field, far-field, and phase-distribution optical images) is transferred to the student model with the only near-field input source, which breaks the information bottleneck by allowing the student model to learn more knowledge in a simulation context. Furthermore, to settle the domain discrepancy between ideal data and practical observation, we propose a visual similarity-based matching to assign real values of modal coefficients to the practical optical images whose ground truth values cannot be easily acquired, which enables the transfer learning from the synthetic data to the real-world data for accuracy enhancement. Simulated and experimental results show that the proposed co-learning framework with visual similarity-based matching has realized high precision and robustness in MD simulated and practical tasks. By bridging the gap between theoretical and practical data, our study offers novel perspectives on DL-based MD practice.

Multiresolution dynamic mode decomposition approach for wind pressure analysis and reconstruction around buildings

AbstractAccurate wind pressure analysis on high‐rise buildings is critical for wind load prediction. However, traditional methods struggle with the inherent complexity and multiscale nature of these data. Furthermore, the high cost and practical limitations of deploying extensive sensor networks restrict the data collection capabilities. This study addresses these limitations by introducing a novel framework for optimal sensor placement on high‐rise buildings. The framework leverages the strengths of multiresolution dynamic mode decomposition (mrDMD) for feature extraction and incorporates a novel regularization term within an existing sensor placement algorithm under constraints. This innovative term enables the algorithm to consider real‐world system constraints during sensor selection, leading to a more practical and efficient solution for wind pressure analysis. mrDMD effectively analyzes the multiscale features of wind pressure data. The extracted mrDMD modes, combined with the enhanced constrained QR decomposition technique, guide the selection of informative sensor locations. This approach minimizes the required number of sensors while ensuring accurate pressure field reconstruction and adhering to real‐world placement constraints. The effectiveness of this method is validated using data from a scaled building model tested in a wind tunnel. This approach has the potential to revolutionize wind pressure analysis for high‐rise buildings, paving the way for advancements in digital twins, real‐time monitoring, and risk assessment of wind loads.

Assessing the effect of turbine size on the coherent structures in the wake using DMD

The aim of this study is to evaluate and quantify the effect of the incoming flow on the coherent structures characterizing the wake of two NREL reference wind turbines with different dimensions: the NREL 5-MW and the NREL 15-MW. The Dynamic Mode Decomposition (DMD) approach has been used to detect dynamically-relevant flow structures. We employ the Sparsity-Promoting version of the DMD (SPDMD) algorithm for ranking the most relevant modes, in order to extract a limited subset of relevant flow features that optimally approximate the original data sequence. The dataset on which the SPDMD is based consists of ordered snapshots obtained by Large Eddy Simulations (LES), where the Actuator Line Method (ALM) simulates the rotor and the Immersed Boundary Method (IBM) models the tower and nacelle. To ensure a realistic comparison, the two turbines are subjected to two turbulent inflows with the same mean Atmospheric Boundary Layer (ABL) obtained through a precursor simulation. The results reveal significant differences in the dependence of the absolute value of the DMD amplitudes on the angular frequency for the two turbines. However, the coherent structures appear to have the same shape for the main modes, although the tip vortex structures have a higher dynamic relevance for the NREL 15-MW turbine. This is due to the larger length scales imposed by the rotor and the lower turbulence intensity at the taller rotor height.

ELINA: Emotion low-resources INference algorithm based on 1D ConvNets

In this study, a thorough analysis of the proposed approach in the context of emotion classification using both single-modal (A-13sbj) and multi-modal (B-12sbj) sets from the YAAD dataset was conducted. This dataset encompassed 25 subjects exposed to audiovisual stimuli designed to induce seven distinct emotional states. Electrocardiogram (ECG) and galvanic skin response (GSR) biosignals were collected and classified using two deep learning models, BEC-1D and ELINA, along with two different preprocessing techniques, a classical fourier-based filtering and an Empirical Mode Decomposition (EMD) approach. For the single-modal set, this proposal achieved an accuracy of 84.43±30.03, precision of 85.16±28.91, and F1-score of 84.06±29.97. Moreover, in the extended configuration the model maintained strong performance, yielding scores of 80.95±22.55, 82.44±24.34, and 79.91±24.55, respectively. Notably, for the multi-modal set (B-12sbj), the best results were obtained with EMD preprocessing and the ELINA model. This proposal achieved an improved accuracy, precision, and F1-score scores of 98.02±3.78, 98.31±3.31, and 97.98±3.83, respectively, demonstrating the effectiveness of this approach in discerning emotional states from biosignals.

Model-based impending lithium battery terminal voltage collapse detection via data-driven and machine learning approaches

Lithium battery is an important power source of an electrical vehicle (EV). Practically, when a battery is about to fail, it needs to be removed from the load because keeping it connected can lead to permanent damage. Hence, it is important to detect battery failure to sustain the lifespan of the battery and avoid safety issues which will contribute to the sustainability of the EV. However, determining the effective disconnecting or discharging moment of the battery remains a challenging issue in EV applications. In order to solve the abovementioned problem, a control framework and maximum likelihood estimation are proposed to estimate the parameters of a battery model. In addition, both the sparse representation and dynamic mode decomposition (DMD) approaches are applied to protect the physical battery unit from a failure scenario. For comparison purposes, the proposed framework is compared to a Lyapunov-based detection approach along with neural network (NN) and linear discriminant analysis (LDA). Moreover, several state estimation algorithms are applied to estimate battery state of charge (SOC) at each time step: extended Kalman filter, extended Kalman smooth variable structure filter, and cubature Kalman filter. Finally, the experimental results showed that the proposed DMD approach outperforms the sparse representation, NN, LDA, and Lyapunov-based approaches in terms of detection accuracy. Moreover, the proposed DMD strategy is more robust towards the inaccuracy of the estimated SOC. Besides that, the proposed battery model parameter estimation approach exhibited fast processing time; therefore, it is a reliable choice for recomputing the model parameters from time to time to compensate aging effect. An autonomous unmanned aerial vehicle (UAV) was simulated as a proof-of-concept in a MATLAB environment to verify the detection performance of the proposed methods. Both actual and UAV results showed that the DMD demonstrated more robust detection performance than other methods in terms of processing time and detection accuracy.

Microphone array analysis of the first non-axisymmetric mode for the detection of pipe conditions.

This paper reports on the use of a circular microphone array to analyze the reflections from a pipe defect with enhanced resolution. A Bayesian maximum a posteriori algorithm is combined with the mode decomposition approach to localize pipe defects with six or fewer microphones. Unlike all previous acoustic reflectometry techniques, which only estimate the location of a pipe defect along the pipe, the proposed method uses the phase information about the wave propagated in the form of the first non-axisymmetric mode to estimate its circumferential position as well as axial location. The method is validated against data obtained from a laboratory measurement in a 150 mm diameter polyvinyl chloride pipe with a 20% in-pipe blockage and 100 mm lateral connection. The accuracy of localization of the lateral connection and blockage attained in this measurement was better than 2% of the axial sensing distance and 9° error in terms of the circumferential position. The practical significance of this approach is that it can be implemented remotely on an autonomous inspection robot so that accurate axial location and circumferential position of lateral connections and small blockages can be estimated with a computationally efficient algorithm.

Data Mining Applied to the Electrochemical Noise Technique in the Time/Frequency Domain for Stress Corrosion Cracking Recognition

In this paper, time/frequency domain data processing was proposed to analyse the EN signal recorded during stress corrosion cracking on precipitation-hardening martensitic stainless steel in a chloride environment. Continuous Wavelet Transform, albeit with some limitations, showed a suitable support in the discriminatory capacity among transient signals related to the different stress corrosion cracking mechanisms. In particular, the aim is to propose the analysis of electrochemical noise signals under stress corrosion cracking conditions in the time–frequency domain by using the Hilbert–Huang approach. The Hilbert–Huang Transform (performed by the Empirical Mode Decomposition approach) was finally proposed to carry out an identification of the corrosion mechanisms in comparison to conventional data processing methods. By using this approach, a detailed simultaneous decomposition of the original electrochemical noise data in the time and frequency domain was carried out. The method gave useful information about transitions among different corrosion mechanisms, allowing us to (i) identify a specific characteristic response for each corrosion damaging phenomenon induced by stress corrosion cracking, (ii) time each corrosion of the damaging phenomenon, and (iii) provide a topological description of the advancing SCC damaging stages. This characteristic evidences that the Hilbert–Huang Transform is a very powerful technique to potentially recognize and distinguish the different corrosion mechanisms occurring during stress corrosion cracking.

NOx formation model for utility boilers using robust two-step steady-state detection and multimodal residual convolutional auto-encoder

BackgroundTo achieve carbon neutrality, thermal power plants will take on greater peak-shaving responsibilities, resulting in utility boilers running at more frequently-changing states. This variation inevitably contributes to dirtier measurement data, and the data will follow new distributions that represent asynchronous operational characteristics. MethodTo predict the NOx formation concentration in this new context, a novel modelling framework is proposed. First, a two-step steady-state detection algorithm, including a basic and a precise identification procedure, is proposed to select steady-state samples from operational data. This algorithm also combines with a bayesian optimization–variational mode decomposition (BO–VMD) approach to enhance its robustness by eliminating high-frequency noise, and with an empirical cumulative distribution based outlier detection (ECOD) to remove outliers. Therefore, a high-quality steady-state dataset is acquired. Based on these data, a multimodal residual convolutional auto-encoder is developed to extract the latent variables that vary with the operation modes. These variables are then used to construct the multimodal NOx prediction model. Significant findingsThe findings on a 660 MW utility boiler reveal that, the proposed modelling framework has a lower misdiagnosis rate in steady-state identification compared to the one-step detection technique, and achieves higher fitting and generalization accuracy than the global modelling method.

Empirical Mode Decomposition with Imf Using Ant Colony Optimization

The serial remote sensing images allow us to view how a certain area has changed and grown across period. Even though these raw images have fewer opportunities to generate information and additional insight, serial remote sensing images (SRSI) offer a significant opportunity to generate clusters and patterns. The implementation of SRSI aggregation is supported by the developments of patterns in a variety of circumstances, which include urbanization, the spread of native vegetation, and farming. We propose a novel outlook to mining sequence patterns that makes use of Ant Colony Optimization and Empirical Mode Decomposition. The newly created Empirical Mode Decomposition (EMD) and Ant Colony Optimization (ACO) approach is integrated to extract the most important characteristics features of significantly accurate performance from serial remote sensing images based on distinct criteria. The outcomes demonstrate that the accuracy of projected sequence patterns can be greatly improved by combining a new hybrid method with EMD and ACO feature selection. Because of this, the method is appealing for employing a farmland dataset based on serial remote sensing images to create ground-based stream-flow for strategically extracting spatially sequential patterns despite requesting less computational mining time and cost.

Investigating the Dynamic Relationship Between Greenhouse Gas Emissions and Gross Domestic Product in Türkiye

This study aims to investigate the causal relationship between Gross Domestic Product and greenhouse gas emissions in Türkiye from 1951 to 2018, using the Causal Decomposition Method that integrates Ensemble Empirical Mode Decomposition, Hilbert-Huang Transform, and Phase Coherence Methods. The primary focus is on identifying the key sectors contributing significantly to greenhouse gas emissions, particularly those connected to industrial production. The analysis reveals a one-way, short-term causal relationship from Gross Domestic Product to greenhouse gas emissions, spanning approximately 3 years. This finding suggests that changes in Gross Domestic Product have short-term effects on emissions, but not vice versa. Special emphasis is placed on the gases Cardon Dioxide, Methane and Nitrous Oxide, as they demonstrate a strong, consistent causal connection with Gross Domestic Product. The significance of this study lies in its utilization of the Ensemble Empirical Mode Decomposition approach to investigate this dynamic causality and address a notable gap in the existing literature. Empirical results indicate a complex yet observable association between Gross Domestic Product growth and greenhouse gas emissions in Türkiye, and that this relationship becomes more important, especially in the short and long term, with periodic fluctuations.

Sleep stage classification via dynamic mode decomposition approach

Sleep stage classification via dynamic mode decomposition approach