A New Discriminative Common Spatial Pattern Method for Motor Imagery Brain–Computer Interfaces

Traditional common spatial pattern (CSP) algorithms for upper limb neural rehabilitation face inherent challenges of overlapping cortical representations and frequency sensitivity, which hinder the decoding performance of motor imagery (MI) electroencephalogram (EEG) signals. To address these issues, this study adopts an improved discriminative filter bank CSP (DFBCSP) framework and applies it to the decoding of upper limb MI-EEG signals, achieving remarkable classification performance. EEG data were acquired from sixteen participants performing two-class (left upper limb flexion-extension vs. relaxing) and three-class (left upper limb flexion vs. right upper limb extension vs. relaxing) MI tasks. The acquired EEG data were then decomposed into nine distinct sub-bands, followed by the adoption of a mutual information-based feature selection strategy to optimize the feature sets. These optimized feature sets were subsequently input into three classification models, namely multilayer perceptron (MLP), support vector machine (SVM), and linear discriminant analysis (LDA), for MI task classification. Experimental results demonstrate that the DFBCSP + MLP method significantly outperforms the traditional CSP approach. Specifically, it achieves an accuracy of 94.83% (Kappa coefficient: 0.890) in two-class MI tasks and 86.20% (Kappa coefficient: 0.775) in three-class MI tasks. The DFBCSP + MLP framework exhibits high robustness and provides a potential technical framework and theoretical basis for future research on the rehabilitation of patients with upper limb motor dysfunction.

Electroencephalogram (EEG) based motor imagery (MI) brain-computer interface (BCI) has emerged as a promising tool for communication and control. Most MI classification methods use fixed-length time windows to intercept signals and perform subsequent analyses. However, the fixed-length time window interception method can not achieve optimal performance due to significant differences in the multiple imagining tasks of the same subject. In this paper, we present a novel interception method using long and short windows (LSWs). This method takes advantage of the subject’s motor imaginary strength at different times of the task to select specific time windows corresponding to the most salient features. The features corresponding to the selected time windows are used for the final MI classification. We compare the proposed LSW interception method with the fixed-length time window method on a public EEG dataset (BCI competition IV dataset 1) and a self-collected dataset. The results show that the classification accuracies are improved with the LSW interception method on both datasets. When using the support vector machine (SVM) classifier, the classification accuracy of common spatial pattern with the LSW method achieves 2.57% and 1.12% improvement on two datasets, respectively, and the classification accuracy of filter bank common spatial pattern (FBCSP) with the LSW method achieves 0.93% and 1.48% improvement, respectively. Among them, the classification accuracy of the LSW method with FBCSP and SVM is the highest, which is 93.43% and 91.12%, respectively. Compared with the traditional methods, this method significantly increases the classification accuracy and provides a new idea for researching the MI classification method in BCI.

Most brain-computer interfaces (BCIs) utilize univariate features (i.e., power spectrum or amplitude) for motor imagery (MI) pattern recognition, while less attention has been paid on multivariate analysis that considers information flow between various brain areas through brain connectivity estimations. Most recently, researches have proved that connectivity features were able to characterize different MI tasks. In this study, we investigated the performance of functional connectivity features measured by phase lag index (PLI), weighted phase lag index(wPLI) and phase-locking value(PLV) on MI classification. The widely-used filter-bank common spatial pattern (FBCSP) approach was employed here for performance assessment. A linear support vector machine was trained to classify different MI tasks using two publicly-available datasets from BCI Competition III and IV. The classification results showed that connectivity features achieved classification accuracy >85% in most cases and PLI outperformed all other methods including FBCSP. Our work suggested that functional connectivity features could be utilized as a powerful tool for recognizing different motor intention.

Brain-computer interface (BCI) systems are proposed as a means of communication for locked-in patients. One common BCI paradigm is motor imagery in which the user controls a BCI by imagining movements of different body parts. It is known that imagining different body parts results in event-related desynchronization (ERD) in various frequency bands. Existing methods such as common spatial patterns (CSP) and its refinement filterbank common spatial patterns (FB-CSP) aim at finding features that are informative for classification of the motor imagery class. Our proposed method is a temporally adaptive common spatial patterns implementation of the commonly used filter-bank common spatial patterns method using convolutional neural networks; hence it is called TA-CSPNN. With this method we aim to: (1) make the feature extraction and classification end-to-end, (2) base it on the way CSP/FBCSP extracts relevant features, and finally, (3) reduce the number of trainable parameters compared to existing deep learning methods to improve generalizability in noisy data such as EEG. More importantly, we show that this reduction in parameters does not affect performance and in fact the trained network generalizes better for data from some participants. We show our results on two datasets, one publicly available from BCI Competition IV, dataset 2a and another in-house motor imagery dataset.

Brain-computer interfaces (BCIs) were initially created to help individuals with disabilities control devices and communicate without muscle movement. Today, BCIs are used for prosthetic control, cognitive enhancement, and neurological rehabilitation. The BCI system depends on analyzing electroencephalogram (EEG) signals captured from the brain. Decoding these EEG signals is a complex process that combines multiple algorithms to extract meaningful information from these intricate and noisy signals. One of the most popular techniques is the Common Spatial Patterns (CSP), which helps preserve useful and sensitive information. This paper presents an optimized extension of the CSP model for extracting EEG data features in a multiclass setting using Riemannian geometry-based weighting. The use of weighting based on Riemannian geometry enhances the robustness of covariance matrix computation, thereby decreasing the influence of noise that can significantly distort the mean of covariance matrices in the traditional CSP method. The proposed approach is also extended by the integration of a multi-band filter bank, providing a more detailed examination of EEG signals. Three classifiers, Linear Discriminant Analysis (LDA), Random Forest Classifier (RFC), and Multi-Layer Perceptron (MLP), are employed to differentiate features across four motor imagery tasks. LDA achieves an accuracy of 80.40%, while MLP and RFC reach 80.02% and 80.90%, respectively. The results obtained using a majority vote combining the decisions of the three classifiers are 81.83% for accuracy and Recall, 82.74% for precision, and 81.87% for F1-score. The proposed architecture is evaluated using the BCI Competition IV set 2a dataset, proving its effectiveness in EEG signal classification for BCI applications.

Effective common spatial pattern (CSP) feature extraction for motor-imagery (MI) EEG recordings usually depends on the filter band selection to a large extent. However, the most proper filter band can hardly be determined manually due to its subject-specific property. This study introduces a sparse support vector machine (SSVM) approach to implement simultaneous CSP feature selection and classification for MI-based brain–computer interface (BCI). In SSVM, CSP features are first extracted on multiple signals that are filtered from raw EEG data at a set of overlapping subbands. SVM with l 1-norm regularization is then proposed to classify MI tasks with automatic selection of filter bands giving the significant CSP features. The effectiveness of SSVM for MI classification is demonstrated on the BCI Competition III dataset IVa, in comparison with several other competing methods. Experimental results indicate that the proposed SSVM method is promising for development of an improved MI-based BCI.

Motor Imagery (MI) based Brain Computer Inter-face (BCI) is a promising neurorehabilitation tool for treating motor impaired stroke survivors. It enables the MI electroencephalogram (EEG) signals to be converted/mapped into customized robotic and assisting commands. Even though stroke causes varying effects in the brain, the EEG signals have shown promises towards the MI classification of post-stroke subjects. This paper presents a MI based left and right wrist dorsiflexion classification performed on 6 stoke subjects. The MI EEG data are recorded from 16 electrode locations on the subject’s scalp. Three different feature extraction methods are used to compare and find the best performing one; the first one is based on the Wavelet Packet Decomposition (WPD) combined with Higher Order Statistics (HOS) which is compared with the widely used Common Spatial Pattern (CSP) and Filter Bank Common Spatial Pattern (FBCSP) filter method. The MI classifications are performed using Random Forest (RF) algorithm to achieve a mean accuracy that exceeds 70% for the WPD+HOS method, while outperforming the CSP and FBCSP based methods.

Brain computer interfaces (BCIs) based on motor imagery (MI) play an important role in helping to improve and restore the loss of physical function. However, traditional MI-BCIs are limited to the motion intention of gross limb, which places many restrictions on their applications. This study proposes a hybrid paradigm based on MI and the steady-state somatosensory evoked potential, with the aim of improving the spatial resolution of MI recognition. Twelve subjects participated in this study. They performed MI tasks under MI and hybrid conditions. In the MI condition, subjects only performed MI tasks, whereas, in the hybrid condition, they received an electrical stimulus while performing the same tasks. Under the hybrid condition, subjects were required not to pay extra attention to the electrical stimulation. The MI task included imagining clenching the right hand and lifting the right forearm. The classifier was built using the filter bank common spatial pattern algorithm and a support vector machine, and online experiments were used to verify the recognition of two MI tasks. During the online experiments, all subjects were able to output different commands at a recognition accuracy far higher than the random level. The average classification accuracy of the hybrid condition reached 76.39%, with a maximum value of 88.34%, which was about 11% higher than that of the MI condition. Moreover, based on offline data, the classification performance using the event-related desynchronization (ERD) feature under the hybrid condition did not differ significantly from that under the MI condition, indicating that the introduction of electrical stimulation did not interfere in the separability of ERD. The proposed paradigm improved the efficiency of decoding multiple MI locations within a single limb. Despite the introduction of external stimuli, users could still drive the new system in the same way as MI in traditional MI-BCI.

In motor imagery (MI) based brain-computer interface (BCI), common spatial pattern (CSP) is most popularly used for discriminant feature extraction. However, the performance of CSP depends on the operational frequency bands, which are selected manually or set to a broad frequency range in most of the previously developed applications. Due to subject to subject or even trial to trial variability of frequency band affected by MI task, these methods suffer from poor performance. We have proposed a novel approach, using combination of multivariate iterative filtering (MIF) and CSP (MIFCSP), to automatically select optimal frequency bands based on MIF which can be further used for discriminant feature extraction. MIF decomposes the signal into several multivariate intrinsic mode functions, from which features are extracted using CSP. We select the minimum number of most significant features for which highest classification accuracy is achieved. Subsequently, linear discriminant analysis (LDA) classifier is used to classify different MI tasks. Experimental results for BCI competition IV dataset 2a and BCI competition III-IIIa are presented. For left hand versus right hand MI classification, proposed MIFCSP method provides 83.18% and 84.44% average accuracy, respectively. Superior classification performance confirms that MIFCSP is a promising candidate for MI BCI application.

Existing research methods for recognizing EEG (Electroencephalogram) signals in motor imagery (MI) often overlook the dynamic changes of brain networks over time, resulting in insufficient classification accuracy for MI tasks. This article addresses the recognition problem of dynamic changes in brain networks during MI tasks and applies an EEG signal classification method based on multi-layer time-varying functional brain networks. This article uses the BCI (Brain-Computer Interface) Competition IV 2a dataset to preprocess the raw EEG signals through bandpass filtering and CSP (Common Spatial Pattern) algorithm. The EEG signals of the MI task are divided into 7 1-second time windows with a step size of 0.5 seconds. Within each time window, Pearson correlation coefficients between EEG channels can be calculated to generate corresponding brain networks, and multiple time-varying functional brain networks can be constructed by stacking the brain networks from multiple time windows. The network topology features, node degree, clustering coefficient, network efficiency, and multi-layer network features of each window can be extracted, including Multiplex Clustering Coefficient (MCC), Multiplex Participation Coefficient (MPC), and inter layer correlation coefficient. By dividing the dataset through 10 fold cross validation, the random forest algorithm can be used to classify and recognize four types of motion imagination tasks. The experimental results show that the average recognition rate of the article’s method in four types of MI tasks reached 89.19%. This method can improve the classification accuracy of MI tasks and enhance a comprehensive understanding of the dynamic changes in brain networks during the process of MI.

Motor imagery (MI)-based brain-computer interface (BCI) systems are being increasingly employed to provide alternative means of communication and control for people suffering from neuro-motor impairments, with a special effort to bring these systems out of the controlled lab environments. Hence, accurately classifying MI from brain signals, e.g., from electroencephalography (EEG), is essential to obtain reliable BCI systems. However, MI classification is still a challenging task, because the signals are characterized by poor SNR, high intra-subject and cross-subject variability. Deep learning approaches have started to emerge as valid alternatives to standard machine learning techniques, e.g., filter bank common spatial pattern (FBCSP), to extract subject-independent features and to increase the cross-subject classification performance of MI BCI systems. In this paper, we first present a review of the most recent studies using deep learning for MI classification, with particular attention to their cross-subject performance. Second, we propose DynamicNet, a Python-based tool for quick and flexible implementations of deep learning models based on convolutional neural networks. We show-case the potentiality of DynamicNet by implementing EEGNet, a well-established architecture for effective EEG classification. Finally, we compare its performance with FBCSP in a 4-class MI classification over public datasets. To explore its cross-subject classification ability, we applied three different cross-validation schemes. From our results, we demonstrate that DynamicNet-implemented EEGNet outperforms FBCSP by about 25%, with a statistically significant difference when cross-subject validation schemes are applied.

Motor imagery electroencephalography (EEG) has been successfully used in the brain-computer interface (BCI) systems. Broad learning (BL) is an effective and efficient incremental learning algorithm with simple neural network structure. In this work, a novel EEG multi-classification method is proposed by combining with BL and common spatial pattern (CSP). Firstly, the CSP algorithm with the one-versus-the-test scheme is exploited to extract the discriminative multiclass brain patterns from raw EEG data, and then the BL algorithm is applied to the extracted features to discriminate the classes of EEG signals during different motor imagery tasks. Finally, the effectiveness of the proposed method has been verified on four-class motor imagery EEG data from BCI Competition IV Dataset 2a. Compare with other methods including ELM, HELM, DBN and SAE, the proposed method has yielded higher average classification test accuracy with less training time-consuming. The proposed method is meaningful and may have potential to apply into BCI field.

Motor imagery (MI) is a cognitive process wherein an individual mentally rehearses a specific movement without physically executing it. Recently, MI-based brain-computer interface (BCI) has attracted widespread attention. However, accurate decoding of MI and understanding of neural mechanisms still face huge challenges. These seriously hinder the clinical application and development of BCI systems based on MI. Thus, it is very necessary to develop new methods to decode MI tasks. In this work, we propose a multi-branch convolutional neural network (MBCNN) with a temporal convolutional network (TCN), an end-to-end deep learning framework to decode multi-class MI tasks. We first used MBCNN to capture the MI electroencephalography signals information on temporal and spectral domains through different convolutional kernels. Then, we introduce TCN to extract more discriminative features. The within-subject cross-session strategy is used to validate the classification performance on the dataset of BCI Competition IV-2a. The results showed that we achieved 75.08% average accuracy for 4-class MI task classification, outperforming several state-of-the-art approaches. The proposed MBCNN-TCN-Net framework successfully captures discriminative features and decodes MI tasks effectively, improving the performance of MI-BCIs. Our findings could provide significant potential for improving the clinical application and development of MI-based BCI systems.

In recent years, Brain Computer Interface (BCI) based on motor imagery has been widely used in the fields of medicine, active safe systems for automobiles, entertainment, and so on. Motor imagery relevant electroencephalogram (EEG) signals are weak, nonlinear, and susceptible to interference. As a feature extraction method for motor imagery, Common Spatial Pattern (CSP) has been proven to be very effective. However, its effectiveness depends heavily on the choice of frequency bands, and Euclidean space cannot effectively describe the inner relationship. To solve these problems, a classification approach for motor imagery using the Geodesic Filtering Common Spatial Pattern (GFCSP) and filter-bank Feature Weighted Support Vector Machine (FWSVM) is presented. First, GFCSP based on the Riemannian manifold is proposed, in which the extracted covariance features are spatially filtered in Riemannian tangent space, and the average covariance matrix is replaced by Riemannian mean in CSP. Second, filter-bank FWSVM with a feature weighted matrix is proposed. EEG signals are filtered into 8-12 Hz, 12-16 Hz, 18-22 Hz, 22-26 Hz, and a wide band of 8-24 Hz, and GFCSP features of these filtered signals are extracted. A feature weighted matrix is calculated using mutual information and the Pearson correlation coefficient from these features and class information. Then, the Support Vector Machine (SVM) is used for classification with the feature weighted matrix. Finally, the proposed method is validated on the dataset IVa in BCI competition III. Classification accuracies of the five subjects are 92.31%, 99.03%, 80.36%, 96.30%, and 97.67%, which demonstrate the effectiveness of our proposed method.

Objective. Deep transfer learning has been widely used to address the nonstationarity of electroencephalogram (EEG) data during motor imagery (MI) classification. However, previous deep learning approaches suffer from limited classification accuracy because the temporal and spatial features cannot be effectively extracted. Approach. Here, we propose a novel end-to-end deep subject adaptation convolutional neural network (SACNN) to handle the problem of EEG-based MI classification. Our proposed model jointly optimizes three modules, i.e. a feature extractor, a classifier, and a subject adapter. Specifically, the feature extractor simultaneously extracts the temporal and spatial features from the raw EEG data using a parallel multiscale convolution network. In addition, we design a subject adapter to reduce the feature distribution shift between the source and target subjects by using the maximum mean discrepancy. By minimizing the classification loss and the distribution discrepancy, the model is able to extract the temporal-spatial features to the prediction of a new subject. Main results. Extensive experiments are carried out on three EEG-based MI datasets, i.e. brain–computer interface (BCI) competition IV dataset IIb, BCI competition III dataset IVa, and BCI competition IV dataset I, and the average accuracy reaches to 86.42%, 81.71% and 79.35% on the three datasets respectively. Furthermore, the statistical analysis also indicates the significant performance improvement of SACNN. Significance. This paper reveals the importance of the temporal-spatial features on EEG-based MI classification task. Our proposed SACNN model can make fully use of the temporal-spatial information to achieve the purpose.