The effective classification of multi-task motor imagery electroencephalogram (EEG) is helpful to achieve accurate multi-dimensional human-computer interaction, and the high frequency domain specificity between subjects can improve the classification accuracy and robustness. Therefore, this paper proposed a multi-task EEG signal classification method based on adaptive time-frequency common spatial pattern (CSP) combined with convolutional neural network (CNN). The characteristics of subjects' personalized rhythm were extracted by adaptive spectrum awareness, and the spatial characteristics were calculated by using the one-versus-rest CSP, and then the composite time-domain characteristics were characterized to construct the spatial-temporal frequency multi-level fusion features. Finally, the CNN was used to perform high-precision and high-robust four-task classification. The algorithm in this paper was verified by the self-test dataset containing 10 subjects (33 ± 3 years old, inexperienced) and the dataset of the 4th 2018 Brain-Computer Interface Competition (BCI competition Ⅳ-2a). The average accuracy of the proposed algorithm for the four-task classification reached 93.96% and 84.04%, respectively. Compared with other advanced algorithms, the average classification accuracy of the proposed algorithm was significantly improved, and the accuracy range error between subjects was significantly reduced in the public dataset. The results show that the proposed algorithm has good performance in multi-task classification, and can effectively improve the classification accuracy and robustness.
In the research of non-invasive brain-computer interface (BCI), independent component analysis (ICA) has been considered as a promising method of electroencephalogram (EEG) preprocessing and feature enhancement. However, there have been few investigations and implements about online ICA-BCI system up till now. This paper reports the investigation of the ICA-based motor imagery BCI (MIBCI) system, combining the characteristics of unsupervised learning of ICA and event-related desynchronization (ERD) related to motor imagery. We constructed a simple and practical method of ICA spatial filter calculation and discriminate criterion of three-type motor imageries in the study. To validate the online performance of proposed algorithms, an ICA-MIBCI experimental system was fully established based on NeuroScan EEG amplifier and VC++ platform. Four subjects participated in the experiment of MIBCI testing and two of them took part in the online experiment. The average classification accuracies of the three-type motor imageries reached 89.78% and 89.89% in the offline and online testing, respectively. The experimental results showed that the proposed algorithm produced high classification accuracy and required less time consumption, which would have a prospect of cross platform application.
Event-related desynchronization (ERD) is the basic feature of electroencephalogram (EEG), and the brain-computer interface based on motor imagery (MI-BCI) with the foundation of the analysis of ERD is of great significance in motor function recovery. The valid ERD characteristics extracted from EEG are the key to the performance of the BCI, so the study of which kind of stimulation mode can prompt subjects to generate more obvious characteristics of ERD is crucial. Four different stimulation modes are designed in this paper, and the effects of motion imagery tasks under static text stimulation, grip video stimulation, serial motion video stimulation of fingers as well as serial motion video stimulation of fingers with sound on the characteristics of ERD are analyzed. Combining the analysis of time-frequency spectrum, the power spectral density curve, ERD value and brain topographic map, it is shown that the ERD under serial motion video stimulation of fingers and serial motion video stimulation of fingers with sound modes is much stronger and has wider range of activation, and the BCI based on the analysis of ERD will have a better effect on practical application. As a result, the recognition and acceptance of the users of BCI system are improved in some extent.
The brain-computer interface (BCI) based on motor imagery electroencephalography (MI-EEG) enables direct information interaction between the human brain and external devices. In this paper, a multi-scale EEG feature extraction convolutional neural network model based on time series data enhancement is proposed for decoding MI-EEG signals. First, an EEG signals augmentation method was proposed that could increase the information content of training samples without changing the length of the time series, while retaining its original features completely. Then, multiple holistic and detailed features of the EEG data were adaptively extracted by multi-scale convolution module, and the features were fused and filtered by parallel residual module and channel attention. Finally, classification results were output by a fully connected network. The application experimental results on the BCI Competition IV 2a and 2b datasets showed that the proposed model achieved an average classification accuracy of 91.87% and 87.85% for the motor imagery task, respectively, which had high accuracy and strong robustness compared with existing baseline models. The proposed model does not require complex signals pre-processing operations and has the advantage of multi-scale feature extraction, which has high practical application value.
This paper proposes a motor imagery recognition algorithm based on feature fusion and transfer adaptive boosting (TrAdaboost) to address the issue of low accuracy in motor imagery (MI) recognition across subjects, thereby increasing the reliability of MI-based brain-computer interfaces (BCI) for cross-individual use. Using the autoregressive model, power spectral density and discrete wavelet transform, time-frequency domain features of MI can be obtained, while the filter bank common spatial pattern is used to extract spatial domain features, and multi-scale dispersion entropy is employed to extract nonlinear features. The IV-2a dataset from the 4th International BCI Competition was used for the binary classification task, with the pattern recognition model constructed by combining the improved TrAdaboost integrated learning algorithm with support vector machine (SVM), k nearest neighbor (KNN), and mind evolutionary algorithm-based back propagation (MEA-BP) neural network. The results show that the SVM-based TrAdaboost integrated learning algorithm has the best performance when 30% of the target domain instance data is migrated, with an average classification accuracy of 86.17%, a Kappa value of 0.723 3, and an AUC value of 0.849 8. These results suggest that the algorithm can be used to recognize MI signals across individuals, providing a new way to improve the generalization capability of BCI recognition models.
As the most common active brain-computer interaction paradigm, motor imagery brain-computer interface (MI-BCI) suffers from the bottleneck problems of small instruction set and low accuracy, and its information transmission rate (ITR) and practical application are severely limited. In this study, we designed 6-class imagination actions, collected electroencephalogram (EEG) signals from 19 subjects, and studied the effect of collaborative brain-computer interface (cBCI) collaboration strategy on MI-BCI classification performance, the effects of changes in different group sizes and fusion strategies on group multi-classification performance are compared. The results showed that the most suitable group size was 4 people, and the best fusion strategy was decision fusion. In this condition, the classification accuracy of the group reached 77%, which was higher than that of the feature fusion strategy under the same group size (77.31% vs. 56.34%), and was significantly higher than that of the average single user (77.31% vs. 44.90%). The research in this paper proves that the cBCI collaboration strategy can effectively improve the MI-BCI classification performance, which lays the foundation for MI-cBCI research and its future application.
The traditional paradigm of motor-imagery-based brain-computer interface (BCI) is abstract, which cannot effectively guide users to modulate brain activity, thus limiting the activation degree of the sensorimotor cortex. It was found that the motor imagery task of Chinese characters writing was better accepted by users and helped guide them to modulate their sensorimotor rhythms. However, different Chinese characters have different writing complexity (number of strokes), and the effect of motor imagery tasks of Chinese characters with different writing complexity on the performance of motor-imagery-based BCI is still unclear. In this paper, a total of 12 healthy subjects were recruited for studying the effects of motor imagery tasks of Chinese characters with two different writing complexity (5 and 10 strokes) on the performance of motor-imagery-based BCI. The experimental results showed that, compared with Chinese characters with 5 strokes, motor imagery task of Chinese characters writing with 10 strokes obtained stronger sensorimotor rhythm and better recognition performance (P < 0.05). This study indicated that, appropriately increasing the complexity of the motor imagery task of Chinese characters writing can obtain stronger motor imagery potential and improve the recognition accuracy of motor-imagery-based BCI, which provides a reference for the design of the motor-imagery-based BCI paradigm in the future.
Motor imagery (MI), motion intention of the specific body without actual movements, has attracted wide attention in fields as neuroscience. Classification algorithms for motor imagery electroencephalogram (MI-EEG) signals are able to distinguish different MI tasks based on the physiological information contained by the EEG signals, especially the features extracted from them. In recent years, there have been some new advances in classification algorithms for MI-EEG signals in terms of classifiers versus machine learning strategies. In terms of classifiers, traditional machine learning classifiers have been improved by some researchers, deep learning and Riemannian geometry classifiers have been widely applied as well. In terms of machine learning strategies, ensemble learning, adaptive learning, and transfer learning strategies have been utilized to improve classification accuracies or reach other targets. This paper reviewed the progress of classification algorithms for MI-EEG signals, summarized and evaluated the existing classifiers and machine learning strategies, to provide new ideas for developing classification algorithms with higher performance.
In order to realize brain-computer interface (BCI), optimal features of single trail motor imagery electroencephalogram (EEG) were extracted and classified. Mu rhythm of EEG was obtained by preprocessing, and the features were optimized by spatial filtering, which are estimated from a set of data by method of common spatial pattern. Classification decision can be made by Fisher criterion, and classification performance can be evaluated by cross validation and receiver operating characteristic (ROC) curve. Optimal feature dimension determination projected by spatial filter was discussed deeply in cross-validation way. The experimental results show that the high discriminate accuracy can be guaranteed, meanwhile the program running speed is improved. Motor imagery intention classification based on optimized EEG feature provides difference of states and simplifies the recognition processing, which offers a new method for the research of intention recognition.