Mode Decomposition Technique Research Articles

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.

Dynamic mode decomposition of thermocapillary convection in GaAs melt liquid bridge between unequal ends

The effects of the radius ratio on the stability of thermocapillary convection in the GaAs melt (Pr=0.068) liquid bridge, situated between unequal ends, are studied by three-dimensional direct numerical simulation. The simulated results reveal that, for the first time, the GaAs melt flow transforms from a stable axisymmetric flow into a three-dimensional steady flow through the first bifurcation at 0.5≤Γr≤0.9. The bifurcation phenomenon was previously common in the range of small Prandtl numbers(0.001≤Pr≤0.057). Additionally, we observe that the stability of the thermocapillary liquid bridge is initially weakened and then slowly improved as the radius ratio Γr decreases. The second bifurcation occurs with the further increase of Ma, and the flow becomes oscillatory. Remarkably, two different oscillation forms are identified, depending on the difference in the degree of symmetry of the flow field structure during its oscillation process. Once the flow reaches a stable periodic oscillation, the Dynamic Mode Decomposition (DMD) technique is used to study the inherent spatio-temporal evolution of the temperature field. By combining the spectrum obtained from the Fast Fourier Transform (FFT), we provide evidence for the existence of mixed forms with different azimuthal wavenumbers from a dynamic perspective, intuitively displaying the different components of the oscillation and examining the contribution of different modes to the oscillation. The dynamic model analysis demonstrates that oscillation form I is a mixed form with m = 1 and m = 2, while oscillation form II belongs to the form where m = 2 is absolutely dominant.

The Temporal and Spatial Evolution of Magnetohydrodynamic Wave Modes in Sunspots

Through their lifetime, sunspots undergo a change in their area and shape and, as they decay, they fragment into smaller structures. Here, for the first time we analyze the spatial structure of the magnetohydrodynamic (MHD) slow-body and fast-surface modes in the observed umbrae as their cross-sectional shape changes. The proper orthogonal decomposition (POD) and dynamic mode decomposition (DMD) techniques were used to analyze 3 and 6 hr Solar Dynamics Observatory/Helioseismic and Magnetic Imager time series of Doppler velocities at the photospheric level of approximately circular and elliptically shaped sunspots. Each time series was divided into equal time intervals to evidence the change in the shape of the sunspots. To identify the physical wave modes, the POD/DMD modes were cross-correlated with a slow-body mode model using the exact shape of the umbra, whereas the shape obtained by applying a threshold level of the mean intensity for every time interval. Our results show that the spatial structure of MHD modes are affected, even by apparently small changes in the umbral shape, especially in the case of the higher-order modes. For the data sets used in our study, the optimal time intervals to consider the influence of the change in the shape on the observed MHD modes is 37–60 minutes. The choice of these intervals is crucial to properly quantify the energy contribution of each wave mode to the power spectrum.

Conditional space-time POD extensions for stability and prediction analysis

The correlation and extraction of coherent structures from a turbulent flow is a principal objective of data-driven modal decomposition techniques. The Conditional space-time Proper Orthogonal Decomposition (CST-POD) offers insight into transient dynamics, revealing the causes of specific flow phenomena, or events, in a customizable manner. This work targets the temporal evolution of CST-POD modes in a reduced subspace, resulting in new extensions and adaptations that are distinct from capabilities of other decomposition methods. First, the properties of CST-POD and its relation to the ensemble average are instantiated with a simple Lorenz system. Other CST-POD properties are examined with applications to problems displaying intermittent properties that test data-driven methods, including transitional supersonic boundary layers and schlieren video processing of unstarted inlet buzz. These examples also explore the pragmatic concerns of oversampling and offer theoretical connections to the sub-sampling of a larger Hankel space through time-delay embedding. Through these insights, it is demonstrated that the subsequent application of dynamic mode decomposition (DMD) to CST-POD modes, provides a flexible tool to investigate targeted flow instabilities, both absolute (tonal) and convective in nature. It is shown, using a resonating jet as an example, that Spectral POD modes associated with tones can be recovered if the time-horizon of CST-POD is suitably extended. Regarding convective instabilities, a multi-resolution framework (CST-mrDMD) yields a refined “cause and effect” stability analysis, capable of diagnosing the natural forcing mechanisms within the jet, and the resulting unstable shear-layer mode. In the final interpretation, the potential for real-time flow prediction of extreme events is derived from an active sensor correlated to a CST-POD mode using the example of bluff-body wake structures impinging on a channel wall.

Ambient oscillatory mode assessment in power system using an advanced signal processing method

Estimation of electromechanical mode properties is crucial in modern power systems for providing the operators with an adequate indication of the stress in the system. Measurement-based approaches use signal processing algorithms for mode identification and parameter estimation. This paper presents a novel framework for the assessment of low-frequency oscillation modes using real-world synchrophasor data with minimum computational effort. A nonstationary approach known as Time-Varying Filter based Empirical Mode Decomposition (TVF-EMD) technique is used to identify the dominant low-frequency modes present in the ambient PMU data. The combination of TVF-EMD with Teager Kaiser Energy Operator (TKEO) precisely estimates the instantaneous mode parameters, such as frequency, amplitude, and damping ratio. The efficacy of the proposed approach is demonstrated by applying it in a synthetic signal, simulated data of a standard IEEE test system, and in real-world PMU data of the Indian power grid. The proposed method is compared with the existing methodologies and the observations reveal that the proposed method has robust performance in estimating the instantaneous mode features in the power system with less computational complexities.

Verification of the Mode Decomposition Technique for Closely Distributed Modal Systems in the State Space Domain.

This study aims to propose and validate the state space mode decomposition technique for precise mode separation of non-classical damping systems and closely distributed modal systems. To assess the reliability and applicability of this technique, a 40-story building with a tuned mass damper is investigated, and acceleration responses measured by the building's health monitoring system are used for the verification of the technique. The mode separation results reveal that the separated modal power spectrum becomes distorted at neighboring natural frequency ranges when the performance index only considers the concentration of power spectral energy at the target natural frequency. However, by introducing an augmented performance index that includes a constraint condition to account for distortion, more accurate mode decomposition can be achieved.

Stochastic Real-Time Second-Order Green's Function Theory for Neutral Excitations in Molecules and Nanostructures.

We present a real-time second-order Green's function (GF) method for computing excited states in molecules and nanostructures, with a computational scaling of O(Ne3), where Ne is the number of electrons. The cubic scaling is achieved by adopting the stochastic resolution of the identity to decouple the 4-index electron repulsion integrals. To improve the time propagation and the spectral resolution, we adopt the dynamic mode decomposition technique and assess the accuracy and efficiency of the combined approach for a chain of hydrogen dimer molecules of different lengths. We find that the stochastic implementation accurately reproduces the deterministic results for the electronic dynamics and excitation energies. Furthermore, we provide a detailed analysis of the statistical errors, bias, and long-time extrapolation. Overall, the approach offers an efficient route to investigate excited states in extended systems with open or closed boundary conditions.

Speech Enhancement Using Sliding Window Empirical Mode Decomposition and Hurst-based Technique

The most challenging in speech enhancement technique is tracking non-stationary noises for long speech segments and low Signal-to-Noise Ratio (SNR). Different speech enhancement techniques have been proposed but, those techniques were inaccurate in tracking highly non-stationary noises. As a result, Empirical Mode Decomposition and Hurst-based (EMDH) approach is proposed to enhance the signals corrupted by non-stationary acoustic noises. Hurst exponent statistics was adopted for identifying and selecting the set of Intrinsic Mode Functions (IMF) that are most affected by the noise components. Moreover, the speech signal was reconstructed by considering the least corrupted IMF. Though it increases SNR, the time and resource consumption were high. Also, it requires a significant improvement under nonstationary noise scenario. Hence, in this article, EMDH approach is enhanced by using Sliding Window (SW) technique. In this SWEMDH approach, the computation of EMD is performed based on the small and sliding window along with the time axis. The sliding window depends on the signal frequency band. The possible discontinuities in IMF between windows are prevented by the total number of modes and the number of sifting iterations that should be set a priori. For each module, the number of sifting iterations is determined by decomposition of many signal windows by standard algorithm and calculating the average number of sifting steps for each module. Based on this approach, the time complexity is reduced significantly with suitable quality of decomposition. Finally, the experimental results show the considerable improvements in speech enhancement under non-stationary noise environments.

Unbalance Bearing Fault Identification Using Highly Accurate Hilbert–Huang Transform Approach

Abstract The dynamic characteristics of rolling element bearings are strongly related to their geometric and operating parameters, most importantly the bearing unbalance. Modern condition monitoring necessitates the use of intrinsic mode functions (IMFs) to diagnose unbalance bearing failure. This paper presents a Hilbert–Huang transform (HHT) method to diagnose the unbalanced rolling bearing faults of rotating machinery. To initially reduce the noise levels with slight signal distortion, the noises of the sample in normal and unbalanced fault states are measured and denoised using the wavelet threshold approach. The complex vibration signatures are decomposed into finite IMFs with ensemble empirical mode decomposition technique. Fast Fourier techniques are employed to extract the vibration responses of bearings that are artificially damaged using electrochemical machining on a newly established test setup for rotor disc bearings. The similarities between the information-contained marginal Hilbert spectra can be used to diagnose rotating machinery bearing faults. The data marginal Hilbert spectra of Mahalanobis and cosine index are compared to determine the fault indicator index’s similarity score. The HHT model’s simplicity enhanced the precision of diagnosis correlated to the results of the experiments with weak fault characteristic signals. The effectiveness of the proposed approach is evaluated with several theoretical models from the literature. The HHT approach is experimentally proven with unbalance diagnosis and capable of classifying marginal Hilbert spectra distribution. Because of its superior time-frequency characteristics and pattern identification of marginal Hilbert spectra and fault indicator indices, the newly stated HHT can process nonlinear, non-stationary, and even transient signals. The findings demonstrate that the suggested method is superior in terms of unbalance fault identification accuracy for monitoring the dynamic stability of industrial rotating machinery.

Acoustic characteristics of supersonic planar impinging jets

The present work aims to study the tonal and broadband noise associated with a supersonic planar jet, of Mach number 1.28 and Reynolds number 50000, impinging on a flat plate. Five different cases are considered corresponding to different plate distances and angles of impingement. The near-field noise is analyzed using Large Eddy Simulation (LES). For this, we employ a low dispersive and dissipative Finite Volume solver using AUSM for inviscid fluxes and third-order Runge–Kutta method for temporal discretization. The far-field noise is calculated using a hybrid approach in which the acoustic sources and mean flow are provided by the fluid solver while the far-field acoustic pressure is calculated by an acoustic solver. It solves Acoustic Perturbation Equations using a spectral/hp element method with a Discontinuous Galerkin projection. The present work highlights many important acoustics studies of impinging jets. Firstly, the far-field sound with the effect of non-uniform base fields is obtained which is important as the far-field acoustic pressure in most of the literature is reported either without any base fields or by the application of uniform base fields. Secondly, a correlation between the different modes of oscillations of the impinging jet and the production of impinging tones is studied using Modal Decomposition techniques. This analysis also sheds some light on the number of concurrent cycles for the different nozzle-to-plate distances. Lastly, the relation between the phase lag term and the distance between the plate and the nozzle exit is highlighted using a vortex tracking method. These observations can serve to provide a better understanding of the sound generation process.

HISET: Hybrid interpretable strategies with ensemble techniques for respiratory sound classification

The human respiratory systems can be affected by several diseases and it is associated with distinctive sounds. For advanced biomedical signal processing, one of the most complex issues is automated respiratory sound classification. In this research, five Hybrid Interpretable Strategies with Ensemble Techniques (HISET) which are quite interesting and robust are proposed for the purpose of respiratory sounds classification. The first approach is termed as an Ensemble GSSR technique which utilizes L2 Granger Analysis and the proposed Supportive Ensemble Empirical Mode Decomposition (SEEMD) technique and then Support Vector Machine based Recursive Feature Elimination (SVM-RFE) is used for feature selection and followed by classification with Machine Learning (ML) classifiers. The second approach proposed is the implementation of a novel Realm Revamping Sparse Representation Classification (RR-SRC) technique and third approach proposed is a Distance Metric dependent Variational Mode Decomposition (DM-VMD) with Extreme Learning Machine (ELM) classification process. The fourth approach proposed is with the usage of Harris Hawks Optimization (HHO) with a Scaling Factor based Pliable Differential Evolution (SFPDE) algorithm termed as HHO-SFPDE and it is classified with ML classifiers. The fifth or the final approach proposed analyzes the application of dimensionality reduction techniques with the proposed Gray Wolf Optimization based Support Vector Classification (GWO-SVC) and another parallel approach utilizes a similar kind of analysis with the Grasshopper Optimization Algorithm (GOA) based Sparse Autoencoder. The results are examined for ICBHI dataset and the best results are shown for the 2-class classification when the analysis is carried out with Manhattan distance-based VMD-ELM reporting an accuracy of 95.39%, and for 3-class classification Euclidean distance-based VMD-ELM reported an accuracy of 90.61% and for 4-class classification, Manhattan distance-based VMD-ELM reported an accuracy of 89.27%.

A New Insight for Daily Solar Radiation Prediction by Meteorological Data Using an Advanced Artificial Intelligence Algorithm: Deep Extreme Learning Machine Integrated with Variational Mode Decomposition Technique

Reliable and precise estimation of solar energy as one of the green, clean, renewable and inexhaustible types of energies can play a vital role in energy management, especially in developing countries. Also, solar energy has less impact on the earth’s atmosphere and environment and can help to lessen the negative effects of climate change by lowering the level of emissions of greenhouse gas. This study developed thirteen different artificial intelligence models, including multivariate adaptive regression splines (MARS), extreme learning machine (ELM), Kernel extreme learning machine (KELM), online sequential extreme learning machine (OSELM), optimally pruned extreme learning machine (OPELM), outlier robust extreme learning machine (ORELM), deep extreme learning machine (DELM), and their versions combined with variational mode decomposition (VMD) as integrated models (VMD-DELM, VMD-ORELM, VMD-OPELM, VMD-OSELM, VMD-KELM, and VMD-ELM), for solar radiation estimation in Kurdistan region, Iraq. The daily meteorological data from 2017 to 2018 were used to implement suggested artificial models at Darbandikhan and Dukan stations, Iraq. The input parameters included daily data for maximum temperature (MAXTEMP), minimum temperature (MINTEMP), maximum relative humidity (MAXRH), minimum relative humidity (MINRH), sunshine duration (SUNDUR), wind speed (WINSPD), evaporation (EVAP), and cloud cover (CLOUDCOV). The results show that the proposed VMD-DELM algorithm considerably enhanced the simulation accuracy of standalone models’ daily solar radiation prediction, with average improvement in terms of RMSE of 13.3%, 20.36%, 25.1%, 27.1%, 34.17%, 38.64%, and 48.25% for Darbandikhan station and 5.22%, 10.01%, 10.26%, 21.01%, 29.7%, 35.8%, and 40.33% for Dukan station, respectively. The outcomes of this study reveal that the VMD-DELM two-stage model performed superiorly to the other approaches in predicting daily solar radiation by considering climatic predictors at both stations.

Three-Phase Modal Noise Analysis and Optimal Three-Phase Power Line Filter Design

Conducted emissions (CE) for three-phase systems are becoming an increasing concern due to the recent exponential growth of three-phase applications, especially linked to the automotive sector. The problem arises because electromagnetic compatibility (EMC) standards only define the methodology to measure the CE generated by the equipment under test (EUT), and they do not provide sufficient information to design a power line filter (PLF) in case of non-compliance. Hence, the design of an optimal PLF is a very difficult task for engineers. The unclear methodology to be followed, unknown load impedances, inadequate equipment, and lack of knowledge of the modal noise are all different reasons that contribute to increasing the PLF design complexity. Common mode (CM) and differential mode (DM) decomposition and PLF design techniques for single-phase EUTs are well discussed and studied in the literature, but the same cannot be stated when it comes to three-phase PLF design. The objective of this paper is to clarify how modal noises behave in a three-phase system and to propose a clear methodology which can be followed to design an optimal three-phase PLF. Additionally, this paper analyses and discusses the modal noises’ intrinsic behavior and provides an understanding of how the PLF components behave when subjected to either a CM or DM noise. Finally, a methodology to design a three-phase PLF, based on accurate insertion loss (IL) estimations and S-parameter measurements, is used to determine the optimal PLF. This approach is tested and validated.

Combined effect of helical force and rotation on the double convection of a binary viscoelastic fluid in a porous medium: Linear and weakly nonlinear analysis

AbstractWe used linear stability theory based on the normal mode decomposition technique and nonlinear stability theory based on the minimum representation of double Fourier series to study the criterion of appearance of the stationary convection and the oscillatory convection; and the rate of heat and mass transfer in a binary viscoelastic fluid mixture in a rotating porous medium under the effect of helical force. We have determined the analytical expression of the Rayleigh number of the system as a function of the dimensionless parameters. Expressions for heat and mass transfer rates are determined as a function of Nusselt and Sherwood number, respectively. The transient behaviors of the Nusselt number and the Sherwood number are studied by solving the finite amplitude equations using the Runge‐Kutta method. Then, the effect of each dimensionless parameter on the system is studied pointed out interesting results. According to the analysis of the different results obtained, it appears that in a porous medium saturated by a binary mixture of viscoelastic fluid in rotation, the Taylor‐Darcy number , the delay time parameter λ2 and the mass Rayleigh‐Darcy number delay the onset of stationary and oscillatory convection. On the other hand, the helical force , the relaxation time parameter λ1, the ratio of diffusivities τ and the number of Vadasz accelerate the onset of stationary and oscillatory convection. In the case of the nonlinear stability study, at steady state, the helical force accelerates the rate of heat and mass transfer. On the other hand, the Taylor‐Darcy number , the diffusivity ratio τ and the mass Rayleigh‐Darcy number retard the rate of heat and mass transfer. In the unsteady state, the helical force , the relaxation time parameter λ1 and the mass Rayleigh‐Darcy number accelerate the rate of heat and mass transfer. This is not the case for the Taylor‐Darcy number and the delay time parameter λ2.

Beamforming-based algorithms for recovering information from fetal electrocardiographic sensors

We deal with the extraction of the fetal electrocardiography (ECG) signal from the raw ECG signals of the mother by the beamforming- based algorithms. The foetal ECG sensors bring out signals containing information from the pregnant mother and the infant. Detailed and separate signals are already provided by the foetal ECG instruments; but for some specific studies related to the infant conditions, it is necessary to improve the quality of the signal with a dedicated processing. In this paper, four techniques, with some enhancements, are proposed to perform the processing; we have applied the following techniques: Least Mean Square (LMS) with adaptive noise cancellation technique, Discrete Wavelet Transform (DWT)-based technique, Empirical Wavelet Transform (EWT) technique, and Multiple Signal Classification (MUSIC). The LMS and the MUSIC pertain to beamforming approach. The techniques were used to decompose and identify the different elements constituting the source signal (mother's signal) and noise cancellation by Multivariate Empirical Mode Decomposition (MEMD) technique. The signal was adaptively decomposed by LMS, DWT and MUSIC according to optimised parameters to extract some hidden components of the source signal, such as the foetal features, QRS, heartbeat etc. The results have showed that LMS, with enhancements, is more effective in identifying and removing useless noise. The techniques were applied to the ECG signal of a 30-year-old healthy pregnant woman, which allowed to verify their applicability. The present research leads to the below main contributions among others: separation of the ECG signal of the foetus from the mother, highlighting the functional state of the foetal heart rhythm (heart rate and heartbeat,) and this can show us if the foetal ECG has malfunctions.

Application of dynamic mode decomposition and compatible window-wise dynamic mode decomposition in deciphering COVID-19 dynamics of India

Abstract The COVID-19 pandemic recently caused a huge impact on India, not only in terms of health but also in terms of economy. Understanding the spatio-temporal patterns of the disease spread is crucial for controlling the outbreak. In this study, we apply the compatible window-wise dynamic mode decomposition (CwDMD) and dynamic mode decomposition (DMD) techniques to the COVID-19 data of India to model the spatial-temporal patterns of the epidemic. We preprocess the COVID-19 data into weekly time-series at the state-level and apply both the CwDMD and DMD methods to decompose the data into a set of spatial-temporal modes. We identify the key modes that capture the dominant features of the COVID-19 spread in India and analyze their phase, magnitude, and frequency relationships to extract the temporal and spatial patterns. By incorporating rank truncation in each window, we have achieved greater control over the system’s output, leading to better results. Our results reveal that the COVID-19 outbreak in India is driven by a complex interplay of regional, demographic, and environmental factors. We identify several key modes that capture the patterns of disease spread in different regions and over time, including seasonal fluctuations, demographic trends, and localized outbreaks. Overall, our study provides valuable insights into the patterns of the COVID-19 outbreak in India using both CwDMD and DMD methods. These findings can help public health organizations to develop more effective strategies for controlling the spread of the pandemic. The CwDMD and DMD methods can be applied to other countries to identify the unique drivers of the outbreak and develop effective control strategies.

Novel feature extraction of underwater targets by encoding hydro-acoustic signatures as image

Underwater vessel-radiated acoustical noise (UVRAN) is a major factor for classification in the sea by the SONAR. Due to unsteady and complex maritime ambient, analyzing underwater sound signals is a challenging issue that has lately received attention in the marine field. In the conventional feature extraction methods, to reduce the effect of ocean noise, the de-noising procedure is performed before complexity measurement by mode decomposition techniques. Based on this, we propose a novel insight for the first time to distinguish the objects which made the underwater noises as the hydro-acoustic signature, using a signals-to-image conversion without noise removal. After pre-processing, the spectral amplitude mean difference function is encoded into an image using Gramian angular field (GAF) technique. Subsequently, image texture analysis is performed in which GAF images are subjected to the gray-level co-occurrence matrix (GLCM). Finally, the second-order image statistic (i.e., 2-D permutation entropy) is calculated. Compared with other methods, results demonstrate that the proposed method has a high degree of separation and stability between the various kinds of underwater targets, suggesting that the methodology is superior to the existing methods. Moreover, our model is robust to noise. The approach perhaps opens an alternative path for UVRAN discrimination.

Improved variational mode decomposition for combined imbalance-and-misalignment fault recognition and severity quantification

Rotating machines are among the most used equipment in industrial environments. Monitoring the machine’s parameters as well as predicting its failures are crucial tasks, as they mitigate production losses and avoid severe damage to the equipment. The combined fault scenario, where more than one fault occur simultaneously with different severity levels in the rotating machines, appears frequently in industry and it has been little investigated in the literature. In order to tackle the decomposition of mixed imbalance and misalignment faults, which are the most frequent in industry, it was proposed in this paper the Improved Variable Mode Decomposition (IVMD) technique, since VMD has shown to be not effective in adequately separating combined types of faults. The proposed automatic fault detection system joins a classifier capable of distinguishing imbalance and misalignment isolated faults from combined faults, independently from the rotating speed or severity fault level, with IVMD. It was developed using Support Vector Machine (SVM) applied to the features obtained from the vibration signature. First, the SVM classifier discriminates between healthy or fault signal, which can originate from individual or combined faults, and when the fault decomposition is required, the IVMD is applied. Subsequently, a continuous range severity level is estimated, based on the vibration signal velocity, allowing the contribution of each fault individually to the overall vibration level to be observed. The obtained results reveal that the devised SVM-based algorithm presents an accuracy of 95.43% in identifying from healthy, single and mixed imbalance and misalignment faults, and the IVMD approach accurately separates the faults.

Detection of ADHD from EEG signals using new hybrid decomposition and deep learning techniques

Objective. Attention deficit hyperactivity disorder (ADHD) is considered one of the most common psychiatric disorders in childhood. The incidence of this disease in the community draws an increasing graph from the past to the present. While the ADHD diagnosis is basically made with the psychiatric tests, there is no active clinically used objective diagnostic tool. However, some studies in the literature has reported development of an objective diagnostic tool that facilitates the diagnosis of ADHD. Approach. In this study, it was aimed to develop an objective diagnostic tool for ADHD using electroencephalography (EEG) signals. In the proposed method, EEG signals were decomposed into subbands by robust local mode decomposition and variational mode decomposition techniques. These subbands and the EEG signals were fed as input data to the deep learning algorithm designed in the study. Main results. As a result, an algorithm has been put forward that distinguishes over 95% of ADHD and healthy individuals through using a 19-channel EEG signal. In addition, a classification accuracy of over 87% was obtained by the proposed approach of EEG signal decomposition followed by data processing in the designed deep learning algorithm. Significance. The findings of the current research enrich the literature based on originality and proposed method can be used as a clinical diagnostic tool in the near future.

Analysis of the dispersive Fourier transform dataset using dynamic mode decomposition: evidence of multiple vibrational modes and their interplay in a three-soliton molecule.

We demonstrate that the dynamic mode decomposition technique can effectively reduce the amount of noise in the dispersive Fourier transform dataset and allow for finer quantitative analysis of the experimental data. We therefore show that the oscillation pattern of a soliton molecule actually results from the interplay of several elementary vibration modes.