Motor Imagery EEG Signals Decoding by Multivariate Empirical Wavelet Transform-Based Framework for Robust Brain–Computer Interfaces

Abstract

The robustness and computational load are the key challenges in motor imagery (MI) based on electroencephalography (EEG) signals to decode for the development of practical brain-computer interface (BCI) systems. In this study, we propose a robust and simple automated multivariate empirical wavelet transform (MEWT) algorithm for the decoding of different MI tasks. The main contributions of this study are four-fold. First, the multiscale principal component analysis method is utilized in the preprocessing module to obtain robustness against noise. Second, a novel automated channel selection strategy is proposed and then is further verified with comprehensive comparisons among three different strategies for decoding channel combination selection. Third, a sub-band alignment method by utilizing MEWT is adopted to obtain joint instantaneous amplitude and frequency components for the first time in MI applications. Four, a robust correlation-based feature selection strategy is applied to largely reduce the system complexity and computational load. Extensive experiments for subject-specific and subject independent cases are conducted with the three-benchmark datasets from BCI competition III to evaluate the performances of the proposed method by employing typical machine-learning classifiers. For subject-specific case, experimental results show that an average sensitivity, specificity and classification accuracy of 98% was achieved by employing multilayer perceptron neural networks, logistic model tree and least-square support vector machine (LS-SVM) classifiers, respectively for three datasets, resulting in an improvement of upto 23.50% in classification accuracy as compared with other existing method. While an average sensitivity, specificity and classification accuracy of 93%, 92.1% and 91.4% was achieved for subject independent case by employing LS-SVM classifier for all datasets with an increase of up to 18.14% relative to other existing methods. Results also show that our proposed algorithm provides a classification accuracy of 100% for subjects with small training size in subject-specific case, and for subject independent case by employing a single source subject. Such satisfactory results demonstrate the great potential of the proposed MEWT algorithm for practical MI EEG signals classification.

Identification of Motor and Mental Imagery EEG in Two and Multiclass Subject-Dependent Tasks Using Successive Decomposition Index

“…In this section, a similar type of comparison is presented for dataset IVa and IVb with 18 channels, three channels and three channels selected with automated channel selection criteria. The 18 and three channels are widely adopted motor cortex channels while three-channel selection with automated channel selection criterion was proposed in our previous study [ 24 ]. The list of automated channels for each subject is given in Table 2 .…”

“…Therefore, wavelet transform is commonly adopted and its significance is widely tested for non-stationary and nonlinear signals. A hybrid signal denoising algorithm called multiscale principal component analysis (MSPCA) is formulated by combining the properties of PCA and wavelet transform [ 24 ]. The workflow of MSPCA is given in Figure 2 .…”

“…In the past, a large number of studies [ 22 , 24 , 35 , 36 ] investigated the effectiveness of wavelet and signal decomposition-based methods for motor and mental imagery EEG signals using different mother wavelets and decomposition levels. The drawbacks of such methods are the selection of suitable mother wavelets and the number of decomposition levels which requires a thorough investigation in terms of classification outcomes and time complexity.…”

“…After preprocessing the data, the subsequent steps are features estimation and classification [ 15 ]. In EEG signal processing, some widely adopted feature extraction methods are categorized as Fourier transform (FT) [ 16 ], power spectral density (PSD) [ 17 ], common spatial patterns (CSP) [ 18 , 19 ], autoregressive (AR) [ 20 , 21 ], sparse representation, and signal decomposition (SD) [ 22 , 23 , 24 ] based methods. All of these methods have their associated demerits and complications, for example, FT-based features only preserve the spectral resolution of the signal and completely loses the temporal information, PSD-based methods are susceptible to electrodes locality, AR-based techniques are sensitive to noise content, etc.…”

“…The maximum accuracy achieved was 95.2% for the proposed mechanism. Our second study [ 24 ] on motor imagery EEG proposed a multivariate empirical wavelet transform (MEWT) for signal decomposition. By selecting features with correlation-based method and classifying them with three benchmark classifiers, we obtained 98% classification outcomes for the least square version of SVM classifier.…”