Sinusoidal Signal Assisted Multivariate Empirical Mode Decomposition for Brain–Computer Interfaces

Abstract

A brain-computer interface (BCI) is a communication approach that permits cerebral activity to control computers or external devices. Brain electrical activity recorded with electroencephalography (EEG) is most commonly used for BCI. Noise-assisted multivariate empirical mode decomposition (NA-MEMD) is a data-driven time-frequency analysis method that can be applied to nonlinear and nonstationary EEG signals for BCI data processing. However, because white Gaussian noise occupies a broad range of frequencies, some redundant components are introduced. To solve this leakage problem, in this study, we propose using a sinusoidal assisted signal that occupies the same frequency ranges as the original signals to improve MEMD performance. To verify the effectiveness of the proposed sinusoidal signal assisted MEMD (SA-MEMD) method, we compared the decomposition performances of MEMD, NA-MEMD, and the proposed SA-MEMD using synthetic signals and a real-world BCI dataset. The spectral decomposition results indicate that the proposed SA-MEMD can avoid the generation of redundant components and over decomposition, thus, substantially reduce the mode mixing and misalignment that occurs in MEMD and NA-MEMD. Moreover, using SA-MEMD as a signal preprocessing method instead of MEMD or NA-MEMD can significantly improve BCI classification accuracy and reduce calculation time, which indicates that SA-MEMD is a powerful spectral decomposition method for BCI.

Motor Imagery EEG Recognition using Deep Generative Adversarial Network with EMD for BCI Applications

“…Ge et al [21] introduced sine wave signal, that spans the identical frequency range as the unique signals to enhance the MEMD presentation. To test the MEMD (SA-MEMD) method performance of the specific sinusoidal signal, the decomposition characteristics of MEMD, NA-MEMD and specific SA-MEMD were compared using synthetic signals and an actual BCI dataset.…”

Intrinsic synchrosqueezing analysis on micro‐Doppler features for small unmanned aerial vehicles identification with dual‐channel radar

“…With the assistance of noise, multivariate input data, consisting of the original signal and added independent WGN [16], enable NA-MEMD to align IMFs in accordance with the quasidyadic filter bank structure, which could reduce the mode-mixing problem within the extracted IMFs [16]. The details of NA-MEMD are outlined in Algorithm 1 [18]. 2) Process the resulting signal X (n+m)�d using the MEMD algorithm to calculate multivariate IMFs I (n+m)�d�y , where y represents the number of IMFs for each channel data.…”

Noise-Assisted Multivariate Empirical Mode Decomposition Based Emotion Recognition

“…Recently, different methods have also been proposed in which the assistant signal for the input signal (a fractional gaussian noise and sinusoidal signal apart from WGN are utilized [39][40][41]. The details of the NA-MEMD are as Figure 2 and Figure 3.…”