A Multivariate Empirical Mode DecompositionBased Approach to Pansharpening

A novel scheme to perform the fusion of multiple images using the multivariate empirical mode decomposition (MEMD) algorithm is proposed. Standard multi-scale fusion techniques make a priori assumptions regarding input data, whereas standard univariate empirical mode decomposition (EMD)-based fusion techniques suffer from inherent mode mixing and mode misalignment issues, characterized respectively by either a single intrinsic mode function (IMF) containing multiple scales or the same indexed IMFs corresponding to multiple input images carrying different frequency information. We show that MEMD overcomes these problems by being fully data adaptive and by aligning common frequency scales from multiple channels, thus enabling their comparison at a pixel level and subsequent fusion at multiple data scales. We then demonstrate the potential of the proposed scheme on a large dataset of real-world multi-exposure and multi-focus images and compare the results against those obtained from standard fusion algorithms, including the principal component analysis (PCA), discrete wavelet transform (DWT) and non-subsampled contourlet transform (NCT). A variety of image fusion quality measures are employed for the objective evaluation of the proposed method. We also report the results of a hypothesis testing approach on our large image dataset to identify statistically-significant performance differences.

Time-frequency analysis is of necessity for wrist pulse signal due to its complexity, among which, empirical mode decomposition (EMD) algorithm and its improved noise-assisted versions (such as ensemble EMD, noise-assisted multivariate EMD (NA-MEMD) and very recently median EMD) are deemed to be the most representative ones. In this study, we provide an in-depth evaluation of these well-established noise-assisted EMD algorithms in computational pulse analysis for the first time. In particular, we compare the performance of the different algorithms systematically and quantitatively based on objective quantitative criteria: number and central frequency of intrinsic mode function (IMF) components, total orthogonality index and mode mixing. Rather than using synthetic signals with visual inspection in most existing literature, the wrist pulse signals used in the evaluation are real recorded samples acquired from both healthy and patient subjects. Through extensive experiments, we found that: 1) Advanced EMD algorithm that has the best performance in other areas may not be the most suitable method for pulse signal analysis, which indicates its high dependence on the type of signal to be analyzed; 2) Adding noise can significantly improve algorithm performance, but tends to produce physiologically not relevant components, which however are usually neglected throughout the intelligent pulse diagnosis literature. Therefore, excluding redundant components and then extracting features is expected to improve performance further. Together, currently NA-MEMD achieves a better performance consistently, potential to become a powerful tool for computational pulse analysis, which in itself have not been applied in wrist pulse analysis before. We believe our works can bring up a new perspective to application of EMD-like algorithms in computational pulse analysis/diagnosis with effective information and guidance. Additionally, considering the similarity between physiological signals, especially such as photoplethysmogram/electrocardiogram, our research can be extended to wearable health monitoring technologies, including smart watches and fitness trackers, and their potential future applications, such as in heart rate estimation and evaluate various cardiovascular-related diseases. The present study underscored the necessity of evaluation noise-assisted EMDs or other adaptive decomposition algorithms based on real recorded signals with more objective measures. Especially, caution the possible redundant components that are introduced.

The high accuracy of electroencephalogram (EEG) signal classification is the premise for the wide application of brain computer interface (BCI). In this paper, a hybrid method consisting of multivariate empirical mode decomposition (MEMD) and common space pattern (CSP) is proposed to recognize left-hand and right-hand hypothetical motion from EEG signals. Experiments were carried out using the BCI competition II imagery database. EEG signals were decomposed into multiple intrinsic mode functions (IMFs) by MEMD. The IMF functions with high correlation were processed by CSP, and AR coefficients and entropy values were extracted as features. After genetic algorithm optimization, classification is carried out. Our research results show that the K nearest neighbor (KNN) as an optimal classification model produces 85.36% accuracy. We also compare the proposed algorithm with the existing algorithms. The experimental results show that the performance of the proposed algorithm is comparable to or better than that of many existing algorithms.

A braking intention identification method based on empirical mode decomposition (EMD) algorithm and entropy theory for electric vehicles is proposed. EMD algorithm is given to decompose nonstationary brake pedal signal to stationary intrinsic mode function (IMF), which is the base of data mining. After that, entropy theory is used to extract brake pedal signal features. A braking intention identification model is built based on fuzzy c-means clustering algorithm. The hardware and software for braking intention identification system based on this method is set up to do offline and real-time experiments. The results show that the identification method proposed in this paper has good real-time quality and can distinguish moderate braking intention and gentle braking intention better.

In the present study, an adaptive Fourier Decomposition Method (FDM) is applied to identify damage at connections. For that purpose, an experimental single-story plane frame model is considered. The beam and columns of the frame are connected by angles and bolts, and the damage is introduced by loosening bolts at different locations. The frame is excited at the right top corner using a hammer, and strain time histories are collected from different points. The FDM and Empirical Mode Decomposition (EMD) algorithm are applied to characterize the damage sensitive features. The results obtained from the FDM are compared with the EMD algorithm, which shows that the performance of FDM is better, which motivates to extend its application further to estimate the amount of bolt loosening in terms of extracted damage sensitive features.

We present a method for the analysis of electroencephalogram (EEG) signals which has the potential to distinguish between ictal and seizure-free intracranial EEG recordings. This is achieved by analyzing common frequency components in multichannel EEG recordings, using the multivariate empirical mode decomposition (MEMD) algorithm. The mean frequency of the signal is calculated by applying the Hilbert-Huang transform on the resulting intrinsic mode functions (IMFs). It has been shown that the mean frequency estimates for the ictal and seizure-free EEG recordings are statistically different, and hence, can serve as a test statistic to distinguish between the two classes of signals. Simulation results on real world EEG signals support the analysis and demonstrate the potential of the proposed scheme.

Currently, empirical mode decomposition (EMD) has become a popular data-driven time-frequency analysis method for nonstationary and nonlinear data. However, it is still limited to univariate data due to the number and/or scale misalignment for multivariate data. A newly developed multivariate EMD (MEMD) scheme decomposes multivariate data simultaneously and thus leads to mode alignment and minimizes mode mixing. In addition, an improved amplitude and frequency modulation (AM-FM) decomposition algorithm presented here provides an estimation of a more meaningful instantaneous amplitude and frequency than the widely used Hilbert transform (HT). Both of these facilitate development of a time-frequency analysis framework for multivariate nonstationary and nonlinear data analysis. In this paper, MEMD-based scalogram and coscalogram, and instantaneous frequency spectra and cospectra are proposed to characterize a multivariate nonstationary process. The scalogram and instantaneous frequency spectra capture spectral evolution of each component while the coscalogram and instantaneous frequency cospectra reveal embedded intermittent correlation between two components. Compared with scale-based scalogram and coscalogram, frequency-based instantaneous frequency spectra and cospectra provide a more detailed portrait of multivariate data. The effectiveness of the proposed MEMD-based time-frequency analysis framework is demonstrated by numerical examples of a thunderstorm downburst and an earthquake ground motion. Also, the results from the MEMD-based approach are compared with those based on a continuous wavelet transform, which further reinforces the effectiveness of the proposed framework.

The P300 oddball task is the most popular paradigm in the existing BCI systems. Recently using auditory stimuli in P300 oddball task arises since it gives much freedom to the BCI user. In this paper, we present a novel BCI paradigm using P300 and P100 responses. Since P300 and P100 responses occur in the frontal lobe and the temporal lobe respectively, so that we can use these responses stimulated by an audio in a single task. The main advantage of our designed paradigm is that we can obtain two different kinds of responses in a single trial EEG task. In the EEG data analysis, we first apply the averaging approach to validate our proposed P300 with P100 paradigm. Next, we employ the multivariate empirical mode decomposition (MEMD) algorithm to extract P300 and P100 components. Finally, we employ a support vector machine (SVM) technique for the feature classification.

Short-term solar radiation forecasting using hybrid deep residual learning and gated LSTM recurrent network with differential covariance matrix adaptation evolution strategy

A novel quadrature clutter rejection approach based on the multivariate empirical mode decomposition for bidirectional Doppler ultrasound signals

Multivariate empirical mode decomposition and application to multichannel filtering

The vibration measured from wind turbine drivetrain components is a mixture of multiple frequency modes. In practice, in wind turbine drivetrain condition monitoring systems, multiple accelerometer sensors are used to measure the vibration. Inter-channel common modes are not processed in the standard single-channel empirical mode decomposition (EMD) and it suffers from mode mixing and mode misalignment. Inter-channel correlation implies the causation of vibration mode shapes. Multivariate EMD (MEMD) possesses an enhanced spatial and spectral coherence. The mode alignment property of MEMD is used to process the inter-channel common modes, thus MEMD overcomes the limitation of mode misalignment in single-channel EMD. Still, MEMD exhibits a degree of mode mixing. White noise powers are added in separate channels to lessen the mode mixing. In this research, a novel multivariate signal processing technique, noise-assisted multivariate empirical mode signal decomposition (NA-MEMD) with a competent nonlinear Teager-Kaiser energy operator (NLTKEO), is proposed and tested for truthful extraction of instantaneous frequency and instantaneous amplitude features, and thereby ensures superior fault diagnosis performance. The dyadic filter bank structure of the proposed NA-MEMD decomposes the nonstationary vibrations effectively. The proposed method is used to predict the surface damage pattern embedded in multi-source vibrations at a low-speed planetary gear stage. The effectiveness of the proposed algorithm is tested with NREL GRC wind turbine condition monitoring benchmark datasets.

Reservoir characterization is one of the most challenging tasks that help in modeling different lithological properties like porosity, permeability and fluid saturation using seismic readings like velocity profile, impedance, etc. Such a model is required for field development, placing new wells and prediction management. Seismic attributes are being progressively utilized for the tasks of model building, exploration and properties estimation from the data. However, these tasks become very complex due to the nonlinear and heterogeneous nature of subsurface properties. In this context, present work proposes a recurrent neural network-based learning framework to classify porosity using seismic attributes as predictor variables. The approach begins by calculating different seismic attributes from the data. From the initially calculated attribute set, features that are to be used for classification are selected by using two different strategies. Firstly, the seismic attributes having good correlation strength with reservoir porosity are extracted. Subsequently, generative topographic map is utilized to select the significant features. The final reduced features set obtained by the integrated result of above two strategies is then fed as an input to the empirical mode decomposition (EMD) algorithm. The denoised features resulting from the EMD algorithm are used to train the classification models. Further, a comparison is carried out between the proposed classification framework $$(EMD+RNN)$$ and other supervised classifiers to show the performance of the proposed framework.

Large-eddy simulations of an SD7003 airfoil are conducted for an imposed plunging motion in order to induce a deep dynamic stall regime. Free stream flow parameters are set to Reynolds number Re = 60.000 and Mach number M = 0.1. Coherent structures are identified under the light of modal analysis via the multivariate empirical mode decomposition (EMD) and the multi resolution dynamic mode decomposition (mrDMD). The present study shows that the wavelet approach in the mrDMD does not fully compensate the errors in the frequency analysis related to rotational and translational invariances associated with vortex transport. Meanwhile the Hilbert-Huang transform applied to the intrinsic mode functions from EMD provides a more convenient way to identify the frequencies related to the coherent structures with negligible reconstruction error.

In recent years, the problem of heavy metal pollution in agriculture caused by industrial development has been particularly prominent, directly affecting food and ecological environmental safety. Hyperspectral remote sensing technology has the advantages of high spectral resolution and nondestructive monitoring. The physiological and biochemical parameters of crops undergo similar changes under different heavy metal stresses. Therefore, it is a great challenge to explore the use of hyperspectral technology to distinguish the types of the heavy metal copper (Cu) and lead (Pb) elements. This is also a hot topic in the current research. In this study, several models are proposed to distinguish copper and lead elements by combining multivariate empirical mode decomposition (MEMD) transformation and machine learning. First, MEMD is introduced to decompose the original spectrum, which effectively removes the noise and highlights and magnifies the weak information of the spectrum. The successive projections algorithm (SPA), competitive adaptive reweighted sampling (CARS), and iteratively retaining informative variables (IRIV) were used to screen the characteristic bands and were combined with extreme learning machine (ELM), support vector machine (SVM), and general regression neural network (GRNN) algorithms to build models to distinguish the types of Cu and Pb elements. The quality of the model was evaluated using accuracy (A), precision (P), recall (R), and F-score. The results showed that the MEMD-SPA-SVM, MEMD-CARS-SVM, MEMD-SPA-ELM, MEMD-CARS-ELM, and MEMD-IRIV-ELM models intuitively and effectively distinguished the types of Cu and Pb elements. Their accuracy and F-scores were all greater than 0.8. To verify the superiority of these models, the same model was constructed based on first derivative (FD) and second derivative (SD) transformations, and the obtained classification and recognition accuracy (A) and F-score were both lower than 0.8, which further confirmed the superiority of the model established after MEMD transformation. The model proposed in this study has great potential for applying hyperspectral technology to distinguish the types of elements contaminated by Cu and Pb in crops.