Search

Accurate predictions of hourly PM2.5 concentrations are crucial for preventing the harmful effects of air pollution. In this study, a new decomposition-ensemble framework incorporating the variational mode decomposition method (VMD), econometric forecasting method (autoregressive integrated moving average model, ARIMA), and deep learning techniques (convolutional neural networks (CNN) and temporal convolutional network (TCN)) was developed to model the data characteristics of hourly PM2.5 concentrations. Taking the PM2.5 concentration of Lanzhou, Gansu Province, China as the sample, the empirical results demonstrated that the developed decomposition-ensemble framework is significantly superior to the benchmarks with the econometric model, machine learning models, basic deep learning models, and traditional decomposition-ensemble models, within one-, two-, or three-step-ahead. This study verified the effectiveness of the new prediction framework to capture the data patterns of PM2.5 concentration and can be employed as a meaningful PM2.5 concentrations prediction tool.

In this Letter, the authors propose a variational mode decomposition method for quantifying diagnostic information of myocardial infarction (MI) from the electrocardiogram (ECG) signal. The multiscale mode energy and principal component (PC) of multiscale covariance matrices are used as features. The mode energies determine the strength of the mode, and the PCs provide the representation of the ECG signal with less redundancy. K-nearest neighbour and support vector machine classifier are utilised to assess the performance of the extracted features for the detection and classification of MI and normal (healthy control). The proposed method achieved a specificity of 99.88%, sensitivity of 99.90%, and accuracy of 99.88%. Experimental results demonstrate that the proposed method with the multiscale mode energy and PC features achieved better output compared to the previously published work.

In this paper, a novel method is presented to analyze the amplitude modulated and frequency modulated (AM–FM) multicomponent signals using a combination of the variational mode decomposition (VMD) and the discrete energy separation algorithm (DESA). In the presented method, firstly, a multicomponent signal is decomposed using VMD method applied in an iterative way. In order to separate the monocomponent signals from multicomponent signal, a suitable convergence criterion is developed based on the values of estimated center frequencies ( CF ¯ ) and standard deviations ( σ CF ) of the decomposed components. Further, the estimation of amplitude envelope and the instantaneous frequency functions of monocomponent AM–FM signals has been carried out by employing DESA. Moreover, the proposed method is also applied on the synthetic AM–FM signal and speech signals to evaluate its performance. Furthermore, its performance is also compared with the Fourier–Bessel series expansion-based DESA, empirical wavelet transform-based DESA, and iterative eigenvalue decomposition-based DESA methods. The performance of the proposed method is compared with the other methods in terms of mean square error between actual and estimated amplitude envelopes ( MSE AE ), mean square error between actual and estimated instantaneous frequencies ( MSE IF ) for synthetic signal. The COSH distance measure is used as a performance measure for speech signals. It is found that the proposed method gives better results in terms of performance measures in several cases. [ABSTRACT FROM AUTHOR]

To improve the accuracy of multi‐step wind power forecast, a variational mode decomposition‐long short‐term memory (VMD‐LSTM) forecast method is proposed. Firstly, the variational mode decomposition method is adopted to decompose the wind power data into three constituent modes, named as the long‐term component, the fluctuation component and the random component. Secondly, long short‐term memory network is utilised to deeply learn the characteristics of the three constituent modes. Profit from its unique forget gate and memory gate structure, the association with long‐term time series is learned to build a multi‐step forecast model. Finally, the wind power data from ELIA and NERL are used to test. The error analysis shows that the proposed method has superior performance in the multi‐step forecast and real‐time forecast. [ABSTRACT FROM AUTHOR]

An improved variational mode decomposition (VMD) method is introduced into the mode recognition of low‐frequency oscillation of power system in this study. First, fast Fourier transform is used to determine the number of VMD components, and the approximate fitting formula of the best balancing parameter α is obtained by a large number of tests. The original signal is decomposed into several modes via improved VMD (IMVD) method. Then, Teager–Kaiser energy operator is applied on the fitting of each component to get the amplitude, frequency, and damping factor of it. By the constructed test signals, the proposed method is compared with the methods of non‐parametric VMD, empirical mode decomposition, total least‐squares estimation of signal parameters via rotational invariance techniques, and Prony on the performance of mode parameter identification. Results show that the IVMD method effectively overcomes the shortcomings of those methods mentioned above in dealing with mode mixing, noise sequence, and non‐stationary signals. Finally, the feasibility of the proposed method in extracting the low‐frequency oscillation mode parameters of power system is verified by the simulation signals of the IEEE two‐area four‐generator power system and the New England 39‐bus system. [ABSTRACT FROM AUTHOR]