Comparison Analysis: Single and Multichannel EMD-Based Filtering with Application to BCI

Abstract

A brain-computer interface (BCI) aims to facilitate a new communication path that translates the motion intentions of a human into control commands using brain signals such as magnetoencephalography (MEG) and electroencephalogram (EEG). In this work, a comparison of features obtained using single channel and multichannel empirical mode decomposition (EMD) based filtering is done to classify the multi-direction wrist movements based MEG signals for enhancing a brain-computer interface (BCI). These MEG signals are presented as a dataset 3 as part of the BCI competition IV. These single channel and multichannel EMD methods decompose MEG signals into a group of intrinsic mode functions (IMFs). The mean frequency measure of these IMFs has been used to combine these IMFs to obtain enhanced MEG signals which have major contributions from the low-frequency band (<15 Hz). The shrinkage covariance matrix has been computed as a feature set. These features have been used for the classification of MEG signals into multidirection wrist movements using the Riemannian geometry classification method. Significant improvement of > 8 % in the test stage using the multichannel EMD based filtering and >4 % when compared with single channel EMD method and BCI competition winner respectively. This analysis offers evidence that the multichannel EMD based filtering has the potential to be used in online BCI systems which facilitate a broad use of noninvasive BCIs.

Dual stream neural networks for brain signal classification

“…In table 1 we report some more recent classifier results for the BCI competition IV dataset 3. First, in [GKP+19] signal features are extracted via a multi-channel empirical mode decomposition based filtering approach, which then leverages a Riemannian geometry classification scheme [BBCJ11]. As seen in table 1, this approach shows significant improvements in subject S 2 (i.e.…”

Recognizing Tonal and Nontonal Mandarin Sentences for EEG-Based Brain–Computer Interface

“…Many studies have combined the IoT and intelligent medical or rehabilitation systems with brain-computer interfaces (BCIs) [2]- [6]. In recent decades, BCI technologies have made many advances [7]- [14]. BCI is considered to be a new communication platform that utilizes the dynamics of the user's brain.…”

A novel method for the classification of Alzheimer's disease from normal controls using magnetic resonance imaging

“…Mazaheri et al (2018) used EEG recordings of word comprehension by subjects to classify MCI converter (MCIc) from MCI non‐converter (MCInc), and NC. Some recent EEG decomposition techniques such as empirical mode decomposition (EMD) based filtering in Gaur, Pachori, Wang, and Prasad (2015), multivariate EMD based filtering in Gaur et al (Gaur, Pachori, Wang, & Prasad, 2016b; Gaur, Pachori, Wang, & Prasad, 2018), single and multi‐channel EMD‐based filtering in Gaur et al (Gaur, Kaushik, Pachori, Wang, & Prasad, 2019; Gaur, Pachori, Wang, & Prasad, 2016a), and intrinsic mode function selection in Gaur, Pachori, Wang, and Prasad (2019), which enhances the classification of two class EEG signals, motivated us to develop algorithms for better classification of AD.…”