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.
In the study of the scalp electroencephalogram (EEG)-based brain-computer interface (BCI), individual differences and complex background noise are two main factors which affect the stability of BCI system. For different subjects, therefore, optimization of BCI system parameters is necessary, including the optimal designing of temporal and spatial filters parameters as well as the classifier parameters. In order to improve the accuracy of BCI system, this paper proposes a new BCI information processing method, which combines the optimization design of independent component analysis spatial filter (ICA-SF) with the multiple sub-band features of EEG signals. The four subjects' three-class motor imagery EEG (MI-EEG) data collected in different periods were analyzed with the proposed method. Experimental results revealed that, during the inner and outer cross-validation of single subject as well as the subject-to-subject validation, the proposed multiple sub-band method always had higher average classification accuracy compared to those with single-band method, and the maximum difference could achieve 6.08% and 5.15%, respectively.
To improve the performance of brain-controlled intelligent car based on motor imagery (MI), a method based on neurofeedback (NF) with electroencephalogram (EEG) for controlling intelligent car is proposed. A mental strategy of MI in which the energy column diagram of EEG features related to the mental activity is presented to subjects with visual feedback in real time to train them to quickly master the skills of MI and regulate their EEG activity, and combination of multi-features fusion of MI and multi-classifiers decision were used to control the intelligent car online. The average, maximum and minimum accuracy of identifying instructions achieved by the trained group (trained by the designed feedback system before the experiment) were 85.71%, 90.47% and 76.19%, respectively and the corresponding accuracy achieved by the control group (untrained) were 73.32%, 80.95% and 66.67%, respectively. For the trained group, the average, longest and shortest time consuming were 92 s, 101 s, and 85 s, respectively, while for the control group the corresponding time were 115.7 s, 120 s, and 110 s, respectively. According to the results described above, it is expected that this study may provide a new idea for the follow-up development of brain-controlled intelligent robot by the neurofeedback with EEG related to MI.
The research on brain functional mechanism and cognitive status based on brain network has the vital significance. According to a time–frequency method, partial directed coherence (PDC), for measuring directional interactions over time and frequency from scalp-recorded electroencephalogram (EEG) signals, this paper proposed dynamic PDC (dPDC) method to model the brain network for motor imagery. The parameters attributes (out-degree, in-degree, clustering coefficient and eccentricity) of effective network for 9 subjects were calculated based on dataset from BCI competitions IV in 2008, and then the interaction between different locations for the network character and significance of motor imagery was analyzed. The clustering coefficients for both groups were higher than those of the random network and the path length was close to that of random network. These experimental results show that the effective network has a small world property. The analysis of the network parameter attributes for the left and right hands verified that there was a significant difference on ROI2 (P = 0.007) and ROI3 (P = 0.002) regions for out-degree. The information flows of effective network based dPDC algorithm among different brain regions illustrated the active regions for motor imagery mainly located in fronto-central regions (ROI2 and ROI3) and parieto-occipital regions (ROI5 and ROI6). Therefore, the effective network based dPDC algorithm can be effective to reflect the change of imagery motor, and can be used as a practical index to research neural mechanisms.
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.
High-density channels are often used to acquire electroencephalogram (EEG) spatial information in different cortical regions of the brain in brain-computer interface (BCI) systems. However, applying excessive channels is inconvenient for signal acquisition, and it may bring artifacts. To avoid these defects, the common spatial pattern (CSP) algorithm was used for channel selection and a selection criteria based on norm-2 is proposed in this paper. The channels with the highest M scores were selected for the purpose of using fewer channels to acquire similar rate with high density channels. The DatasetⅢa from BCI competition 2005 were used for comparing the classification accuracies of three motor imagery between whole channels and the selected channels with the present proposed method. The experimental results showed that the classification accuracies of three subjects using the 20 channels selected with the present method were all higher than the classification accuracies using all 60 channels, which convinced that our method could be more effective and useful.
Aiming at feature selection problem of motor imagery task in brain computer interface (BCI), an algorithm based on mutual information and principal component analysis (PCA) for electroencephalogram (EEG) feature selection is presented. This algorithm introduces the category information, and uses the sum of mutual information matrices between features under different motor imagery category to replace the covariance matrix. The eigenvectors of the sum matrix represent the direction of the principal components and the eigenvalues of the sum matrix are used to determine the dimensionality of principal components. 2005 International BCI competition data set was used in our experiments, and four feature extraction methods were adopted, i. e. power spectrum estimation, continuous wavelet transform, wavelet packet decomposition and Hjorth parameters. The proposed feature selection algorithm was adopted to select and combine the most useful features for classification. The results showed that relative to the PCA algorithm, our algorithm had better performance in dimensionality reduction and in classification accuracy with the assistance of support vector machine classifier under the same dimensionality of principal components.
Motor imaging therapy is of great significance to the rehabilitation of patients with stroke or motor dysfunction, but there are few studies on lower limb motor imagination. When electrical stimulation is applied to the posterior tibial nerve of the ankle, the steady-state somatosensory evoked potentials (SSSEP) can be induced at the electrical stimulation frequency. In order to better realize the classification of lower extremity motor imagination, improve the classification effect, and enrich the instruction set of lower extremity motor imagination, this paper designs two experimental paradigms: Motor imaging (MI) paradigm and Hybrid paradigm. The Hybrid paradigm contains electrical stimulation assistance. Ten healthy college students were recruited to complete the unilateral movement imagination task of left and right foot in two paradigms. Through time-frequency analysis and classification accuracy analysis, it is found that compared with MI paradigm, Hybrid paradigm could get obvious SSSEP and ERD features. The average classification accuracy of subjects in the Hybrid paradigm was 78.61%, which was obviously higher than the MI paradigm. It proves that electrical stimulation has a positive role in promoting the classification training of lower limb motor imagination.
Motor imagery (MI) is an important paradigm of driving brain computer interface (BCI). However, MI is not easy to control or acquire, and the performance of MI-BCI depends heavily on the performance of the subjects’ MI. Therefore, the correct execution of MI mental activities, ability evaluation and improvement methods play important and even critical roles in the improvement and application of MI-BCI system’s performance. However, in the research and development of MI-BCI, the existing researches mainly focus on the decoding algorithm of MI, but do not pay enough attention to the above three aspects of MI mental activities. In this paper, these problems of MI-BCI are discussed in detail, and it is pointed out that the subjects tend to use visual motor imagery as kinesthetic motor imagery. In the future, we need to develop some objective, quantitatively visualized MI ability evaluation methods, and develop some effective and less time-consumption training methods to improve MI ability. It is also necessary to solve the differences and commonness of MI problems between and within individuals and MI-BCI illiteracy to a certain extent.
Brain-computer interface (BCI) based on functional near-infrared spectroscopy (fNIRS) is a new-type human-computer interaction technique. To explore the separability of fNIRS signals in different motor imageries on the single limb, the study measured the fNIRS signals of 15 subjects (amateur football fans) during three different motor imageries of the right foot (passing, stopping and shooting). And the correlation coefficient of the HbO signal during different motor imageries was extracted as features for the input of a three-classification model based on support vector machines. The results found that the classification accuracy of the three motor imageries of the right foot was 78.89%±6.161%. The classification accuracy of the two-classification of motor imageries of the right foot, that is, passing and stopping, passing and shooting, and stopping and shooting was 85.17%±4.768%, 82.33%±6.011%, and 89.33%±6.713%, respectively. The results demonstrate that the fNIRS of different motor imageries of the single limb is separable, which is expected to add new control commands to fNIRS-BCI and also provide a new option for rehabilitation training and control peripherals for unilateral stroke patients. Besides, the study also confirms that the correlation coefficient can be used as an effective feature to classify different motor imageries.