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.

Recent advances in artificial intelligence demand an automated framework for the development of versatile brain–computer interface (BCI) systems. In this article, we proposed a novel automated framework that reveals the importance of multidomain features with feature selection to increase the performance of a learning algorithm for motor imagery electroencephalogram task classification on the utility of signal decomposition methods. A framework is explored by investigating several combinations of signal decomposition methods with feature selection techniques. Thus, this article also provides a comprehensive comparison among the aforementioned modalities and validates them with several performance measures, robust ranking, and statistical analysis (Wilcoxon and Friedman) on public benchmark databases. Among all the combinations, the variational mode decomposition, multidomain features obtained with linear regression, and the cascade-forward neural network provide better classification accuracy results for both subject-dependent and independent BCI systems in comparison with other state-of-the-art methods. Impact Statement—The brain–computer interface (BCI) is a revolutionary device that utilizes cognitive function explicitly for the interaction of external devices without any motor intervention. BCI systems based on motor imagery have shown efficacy for stroke patient treatment, but poor performance, nonflexible characteristics, and lengthy training sessions have limited their use in clinical practice. The proposed automated framework overcomes these limitations. With the significant improvement of up to 26.1% and 26.4% in comparison with the available literature, the proposed automated framework could offer help to BCI device developers to develop flexible BCI devices and provide interaction for motor-disabled users.

In this article, a novel computer-aided diagnosis framework is proposed for the classification of motor imagery (MI) electroencephalogram (EEG) signals. First, a multivariate variational mode decomposition (MVMD) method was employed to obtain joint modes in frequency scale across all channels. Second, several multi-domain features (time domain, frequency domain, nonlinear and geometrical) were extracted from each EEG signal, and to further enhance the classification performance of different MI EEG signals, a variety of wrapper and filter feature selection methods were utilized with different channel combinations. Finally, to avoid a large number of training sessions for a particular device, extensive subject-independent experiments were performed. The MVMD applied to 18-channel EEG from the motor cortex area in combination with the ReliefF feature selection method achieved an average classification accuracy of 99.8% for a subject-dependent while 98.3% for subject-independent experiments. Besides the aforementioned combination provide above 99% accuracy for subjects with sufficient or small training samples for both subject-dependent or independent cases. These promising findings suggest that the proposed framework is flexible to use for subject-dependent or independent BCI systems.

Nonstationary signal decomposition (SD) is a primary procedure to extract monotonic components or modes from electroencephalogram (EEG) signals for the development of robust brain-computer interface (BCI) systems. This study proposes a novel automated computerized framework for proficient identification of motor and mental imagery (MeI) EEG tasks by employing empirical Fourier decomposition (EFD) and improved EFD (IEFD) methods. Specifically, the multiscale principal component analysis (MSPCA) is rendered to denoise EEG data first, and then, EFD is utilized to decompose nonstationary EEG into subsequent modes, while the IEFD criterion is proposed for a single conspicuous mode selection. Finally, the time- and frequency-domain features are extracted and classified with a feedforward neural network (FFNN) classifier. Extensive experiments are conducted on four multichannel motor and MeI data sets from BCI competitions II and III using a tenfold cross-validation strategy. Results compared with the other existing methods demonstrated that the highest classification accuracies of 99.82% (data set IV-a), 93.33% (data set IV-b), 91.96% (data set III), and 88.08% (data set V) in subject-specific scenarios, while 82.70% (data set IV-a) in the subject-independent framework are achieved for IEFD with FFNN classifiers collectively. The overall exploratory results authenticate that the proposed IEFD-based automated computerized framework not only outperforms the conventional SD methods but is also robust and computationally efficient for the development of subject-dependent and subject-independent BCI systems.

The present study investigated the steady magnetohydrodynamics of the axisymmetric flow of a incompressible, viscous, electricity-conducting nanofluid with convective boundary conditions and thermo-diffusion over a radially stretched surface. The nanoparticles’ volume fraction was passively controlled on the boundary, rather than actively controlled. The governing non-linear partial differential equations were transformed into a system of nonlinear, ordinary differential equations with the aid of similarity transformations which were solved numerically, using the very efficient variational finite element method. The coefficient of skin friction and rate of heat transfer, and an exact solution of fluid flow velocity, were contrasted with the numerical solution gotten by FEM. Excellent agreement between the numerical and exact solutions was observed. The influences of various physical parameters on the velocity, temperature, and solutal and nanoparticle concentration profiles are discussed by the aid of graphs and tables. Additionally, authentication of the convergence of the numerical consequences acquired by the finite element method and the computations was acquired by decreasing the mesh level. This exploration is significant for the higher temperature of nanomaterial privileging technology.

This study introduces a novel matrix determinant feature extraction approach for efficient classification of motor and mental imagery activities from electroencephalography signals. First, the multiscale principal component analysis (MSPCA) was utilized to obtain clean EEG signals. Secondly, denoised data were sequentially arranged to form a square matrix of different orders (e.g.10,13,16,20) and determinant was computed for each order matrix. Finally, the extracted matrix determinant features were provided to several machine learning and neural network classification models for classification. All experiments were carried out using a 10-fold cross-validation approach on three publicly accessible datasets: Dataset IV-a, Dataset IVb, and Dataset V of BCI competition III. Also, this study designs a Computerized Automatic Detection of Motor and Mental Imagery graphical user interface (CADMMI GUI) that can assist physicians/experts to efficiently analyses motor and mental imagery data. Experimental results reveal that the highest average classification accuracy of 99.55% (for dataset IV-a), 99.52% (for dataset IV-b), and 91.80% (for dataset V) were obtained for motor and mental imagery respectively with 20-order matrix determinant using feedforward neural network classifier. The experimental results suggest that the proposed framework provides a robust biomarker with the least computational complexity for the development of automated braincomputer interfaces.