Motor Imagery-based Brain-computer Interface System Research Articles

Multilayer network-based channel selection for motor imagery brain–computer interface

Objective. The number of electrode channels in a motor imagery-based brain–computer interface (MI-BCI) system influences not only its decoding performance, but also its convenience for use in applications. Although many channel selection methods have been proposed in the literature, they are usually based on the univariate features of a single channel. This leads to a loss of the interaction between channels and the exchange of information between networks operating at different frequency bands. Approach. We integrate brain networks containing four frequency bands into a multilayer network framework and propose a multilayer network-based channel selection (MNCS) method for MI-BCI systems. A graph learning-based method is used to estimate the multilayer network from electroencephalogram (EEG) data that are filtered by multiple frequency bands. The multilayer participation coefficient of the multilayer network is then computed to select EEG channels that do not contain redundant information. Furthermore, the common spatial pattern (CSP) method is used to extract effective features. Finally, a support vector machine classifier with a linear kernel is trained to accurately identify MI tasks. Main results. We used three publicly available datasets from the BCI Competition containing data on 12 healthy subjects and one dataset containing data on 15 stroke patients to validate the effectiveness of our proposed method. The results showed that the proposed MNCS method outperforms all channels (85.8% vs. 93.1%, 84.4% vs. 89.0%, 71.7% vs. 79.4%, and 72.7% vs. 84.0%). Moreover, it achieved significantly higher decoding accuracies on MI-BCI systems than state-of-the-art methods (paired t-tests, p < 0.05). Significance. The experimental results showed that the proposed MNCS method can select appropriate channels to improve the decoding performance as well as the convenience of the application of MI-BCI systems.

A Combined Virtual Electrode-Based ESA and CNN Method for MI-EEG Signal Feature Extraction and Classification.

A Brain-Computer Interface (BCI) is a medium for communication between the human brain and computers, which does not rely on other human neural tissues, but only decodes Electroencephalography (EEG) signals and converts them into commands to control external devices. Motor Imagery (MI) is an important BCI paradigm that generates a spontaneous EEG signal without external stimulation by imagining limb movements to strengthen the brain's compensatory function, and it has a promising future in the field of computer-aided diagnosis and rehabilitation technology for brain diseases. However, there are a series of technical difficulties in the research of motor imagery-based brain-computer interface (MI-BCI) systems, such as: large individual differences in subjects and poor performance of the cross-subject classification model; a low signal-to-noise ratio of EEG signals and poor classification accuracy; and the poor online performance of the MI-BCI system. To address the above problems, this paper proposed a combined virtual electrode-based EEG Source Analysis (ESA) and Convolutional Neural Network (CNN) method for MI-EEG signal feature extraction and classification. The outcomes reveal that the online MI-BCI system developed based on this method can improve the decoding ability of multi-task MI-EEG after training, it can learn generalized features from multiple subjects in cross-subject experiments and has some adaptability to the individual differences of new subjects, and it can decode the EEG intent online and realize the brain control function of the intelligent cart, which provides a new idea for the research of an online MI-BCI system.

Supervised penalty-based aggregation applied to motor-imagery based brain-computer-interface

In this paper we propose a new version of penalty-based aggregation functions, the Multi Cost Aggregation choosing functions (MCAs), in which the function to minimize is constructed using a convex combination of two relaxed versions of restricted equivalence and dissimilarity functions instead of a penalty function. We additionally suggest two different alternatives to train a MCA in a supervised classification task in order to adapt the aggregation to each vector of inputs. We apply the proposed MCA in a Motor Imagery-based Brain–Computer Interface (MI-BCI) system to improve its decision making phase. We also evaluate the classical aggregation with our new aggregation procedure in two publicly available datasets. We obtain an accuracy of 82.31% for a left vs. right hand in the Clinical BCI challenge (CBCIC) dataset, and a performance of 62.43% for the four-class case in the BCI Competition IV 2a dataset compared to a 82.15% and 60.56% using the arithmetic mean. Finally, we have also tested the goodness of our proposal against other MI-BCI systems, obtaining better results than those using other decision making schemes and Deep Learning on the same datasets.

Real-Time Motor Imagery-Based Brain–Computer Interface System by Implementing a Frequency Band Selection

Real-Time Motor Imagery-Based Brain–Computer Interface System by Implementing a Frequency Band Selection

An EEG-based asynchronous MI-BCI system to reduce false positives with a small number of channels for neurorehabilitation: A pilot study

Many studies have used motor imagery-based brain–computer interface (MI-BCI) systems for stroke rehabilitation to induce brain plasticity. However, they mainly focused on detecting motor imagery but did not consider the effect of false positive (FP) detection. The FP could be a threat to patients with stroke as it can induce wrong-directed brain plasticity that would result in adverse effects. In this study, we proposed a rehabilitative MI-BCI system that focuses on rejecting the FP. To this end, we first identified numerous electroencephalogram (EEG) signals as the causes of the FP, and based on the characteristics of the signals, we designed a novel two-phase classifier using a small number of EEG channels, including the source of the FP. Through experiments with eight healthy participants and nine patients with stroke, our proposed MI-BCI system showed 71.76% selectivity and 13.70% FP rate by using only four EEG channels in the patient group with stroke. Moreover, our system can compensate for day-to-day variations for prolonged session intervals by recalibration. The results suggest that our proposed system, a practical approach for the clinical setting, could improve the therapeutic effect of MI-BCI by reducing the adverse effect of the FP.

A Subject-Independent Brain-Computer Interface Framework Based on Supervised Autoencoder.

A calibration procedure is required in motor imagery-based brain-computer interface (MI-BCI) to tune the system for new users. This procedure is time-consuming and prevents naive users from using the system immediately. Developing a subject-independent MI-BCI system to reduce the calibration phase is still challenging due to the subject-dependent characteristics of the MI signals. Many algorithms based on machine learning and deep learning have been developed to extract high-level features from the MI signals to improve the subject-to-subject generalization of a BCI system. However, these methods are based on supervised learning and extract features useful for discriminating various MI signals. Hence, these approaches cannot find the common underlying patterns in the MI signals and their generalization level is limited. This paper proposes a subject-independent MI-BCI based on a supervised autoencoder (SAE) to circumvent the calibration phase. The suggested framework is validated on dataset 2a from BCI competition IV. The simulation results show that our SISAE model outperforms the conventional and widely used BCI algorithms, common spatial and filter bank common spatial patterns, in terms of the mean Kappa value, in eight out of nine subjects.

Low-quality training data detection method of EEG signals for motor imagery BCI system

BackgroundThe design and implementation of high-performance motor imagery-based brain computer interface (MI-BCI) requires high-quality training samples. However, fluctuation in subjects’ physiological and mental states as well as artifacts can produce the low-quality motor imagery electroencephalogram (EEG) signal, which will damage the performance of MI-BCI system. New methodIn order to select high-quality MI-EEG training data, this paper proposes a low-quality training data detection method combining independent component analysis (ICA) and weak classifier cluster. we also design and implement a new online BCI system based on motor imagery to verify the online processing performance of the proposed method. ResultIn order to verify the effectiveness of the proposed method, we conducted offline experiments on the public dataset called BCI Competition IV Data Set 2b. Furthermore, in order to verify the processing performance of the online system, we designed 60 groups of online experiments on 12 subjects. The online experimental results show that the twelve subjects can complete the system task efficiently (the best experiment is 135.6 s with 9 trials of subject S1). ConclusionThis paper demonstrated that the proposed low-quality training data detection method can effectively screen out low-quality training samples, so as to improve the performance of the MI-BCI system.

A framework for motor imagery with LSTM neural network

Background and ObjectiveHow to learn robust representations from brain activities and to improve algorithm performance are the most significant issues for brain-computer interface systems. MethodsThis study introduces a long short-term memory recurrent neural network to decode the multichannel electroencephalogram or electrocorticogram for implementing an effective motor imagery-based brain-computer interface system. The unique information processing mechanism of the long short-term memory network characterizes spatio-temporal dynamics in time sequences. This study evaluates the proposed method using publically available electroencephalogram/electrocorticogram datasets. ResultsThe decoded features coupled with a gradient boosting classifier could obtain high recognition accuracies of 99% for electroencephalogram and 100% for electrocorticogram, respectively. ConclusionsThe results demonstrated that the proposed model can estimate robust spatial-temporal features and obtain significant performance improvement for motor imagery-based brain-computer interface systems. Further, the proposed method is of low computational complexity.

A Tensor-Based Frequency Features Combination Method for Brain-Computer Interfaces.

With the development of the brain-computer interface (BCI) community, motor imagery-based BCI system using electroencephalogram (EEG) has attracted increasing attention because of its portability and low cost. Concerning the multi-channel EEG, the frequency component is one of the most critical features. However, insufficient extraction hinders the development and application of MI-BCIs. To deeply mine the frequency information, we proposed a method called tensor-based frequency feature combination (TFFC). It combined tensor-to-vector projection (TVP), fast fourier transform (FFT), common spatial pattern (CSP) and feature fusion to construct a new feature set. With two datasets, we used different classifiers to compare TFFC with the state-of-the-art feature extraction methods. The experimental results showed that our proposed TFFC could robustly improve the classification accuracy of about 5% ( ). Moreover, visualization analysis implied that the TFFC was a generalization of CSP and Filter Bank CSP (FBCSP). Also, a complementarity between weighted narrowband features (wNBFs) and broadband features (BBFs) was observed from the averaged fusion ratio. This article certificates the importance of frequency information in the MI-BCI system and provides a new direction for designing a feature set of MI-EEG.

Inter-stimulus phase coherence in steady-state somatosensory evoked potentials and its application in improving the performance of single-channel MI-BCI

Objective. With the development of clinical applications of motor imagery-based brain–computer interfaces (MI-BCIs), a single-channel MI-BCI system that can be easily assembled is an attractive goal. However, due to the low quality of the spectral power features in the traditional MI-BCI paradigm, the recognition performance of current single-channel systems is far lower than that of multi-channel systems, impeding their use in clinical applications. Approach. In this study, the subjects’ right and left hands were stimulated simultaneously at different frequencies to induce steady-state somatosensory evoked potentials (SSSEP). Subjects then performed motor imagery (MI) tasks. A new electroencephalography (EEG) index, inter-stimulus phase coherence (ISPC), was built to measure phase desynchronization of SSSEP caused by MI. Then, ISPC is introduced as a feature into left-hand and right-hand MI recognition. Main results. ISPC analysis found that left-handed MI can cause a significant decrease in phase synchronization in contralateral sensorimotor SSSEP, while right-handed MI has little effect on it, and vice versa. Combining ISPC features with traditional spectral power features, the single-channel left-hand versus right-hand MI recognition accuracy reaches 81.0%, which is much higher than that observed with traditional MI paradigms (about 60%). Significance. This work shows that the hybrid MI-SSSEP paradigm can provide more sensitive EEG features to decode motor intentions, demonstrating its potential for clinical applications.

Cross-correlation based discriminant criterion for channel selection in motor imagery BCI systems

Objective. Many electroencephalogram (EEG)-based brain-computer interface (BCI) systems use a large amount of channels for higher performance, which is time-consuming to set up and inconvenient for practical applications. Finding an optimal subset of channels without compromising the performance is a necessary and challenging task. Approach. In this article, we proposed a cross-correlation based discriminant criterion (XCDC) which assesses the importance of a channel for discriminating the mental states of different motor imagery (MI) tasks. Channels are ranked and selected according to the proposed criterion. The efficacy of XCDC is evaluated on two MI EEG datasets. Main results. On the two datasets, the proposed method reduces the channel number from 71 and 15 to under 18 and 11 respectively without compromising the classification accuracy on unseen data. Under the same constraint of accuracy, the proposed method requires fewer channels than existing channel selection methods based on Pearson’s correlation coefficient and common spatial pattern. Visualization of XCDC shows consistent results with neurophysiological principles. Significance. This work proposes a quantitative criterion for assessing and ranking the importance of EEG channels in MI tasks and provides a practical method for selecting the ranked channels in the calibration phase of MI BCI systems, which alleviates the computational complexity and configuration difficulty in the subsequent steps, leading to real-time and more convenient BCI systems.

Spatio-time-frequency joint sparse optimization with transfer learning in motor imagery-based brain-computer interface system

Motor imagery-based brain-computer interface (MI-BCI) is widely considered as the most promising BCI. Non-stationary of EEG data and long BCIs’ calibration time are main problems that affect the practicability of MI-BCI. In this paper, we propose a new algorithm, i.e. spatio-time-frequency joint sparse optimization algorithm with transfer learning (STFSTL) to achieve satisfactory classification accuracy with small training set. By introducing artificial bee colony (ABC) algorithm and least absolute shrinkage and selection operator (LASSO), the algorithm optimized parameters in spatial domain, time domain and frequency domain simultaneously. The similarity between data was measured by Euclidean distance. Through instanced-based transfer learning, the source data which was most similar to the target data was selected as the auxiliary data to train the target classifier. We evaluated the performance of the proposed algorithm on three data sets, including a private data set and two public data sets. The classification accuracy of the proposed algorithm with one fifth of the training data was higher than that of five other algorithms. Paired t-test analysis revealed that the accuracy of STFSTL and that of five other algorithms were significantly different. The experimental results suggested that the proposed algorithm with less target data can effectively achieve higher classification accuracy than traditional algorithms. It’s likely to have a broad application prospect in MI-BCI.

Optimization of preprocessing stage in EEG based BCI systems in terms of accuracy and timing cost

Performance of the motor imagery-based brain computer interface (MI-BCI) systems has been tried to improve by the researchers with novel approaches and methods used on preprocessing stages. In this study, the preprocessing stages are optimized to improve the performance of MI-BCI systems in terms of the accuracy and the timing cost. Taguchi method is adopted for the optimization study. Time window-step size, time interval, theta frequency band, and mu and beta frequency bands are considered as controllable factors in the preprocessing stage. The preprocessing stages are performed according to an experimental plan created by the Taguchi method. The study is applied on BCI Competition IV-2b dataset. The features are extracted from the data with the Hjorth algorithm and classified by using the SVM classifier. The statistical significance and relatively contribution effects of factors on the performance parameters are tested with ANOVA. As a result, optimum combinations of the preprocessing stage factors providing the highest accuracy and the lowest timing cost are both individually and simultaneously revealed. In addition, it is concluded that the most effective factor on the preprocessing stage is determined as time window-step size. Consequently, the results of various combinations of the preprocessing stages on the MI-BCI performance are revealed in terms of both the accuracy and the timing cost.

Zero-Shot Learning for EEG Classification in Motor Imagery-Based BCI System.

A brain-computer interface (BCI) based on motor imagery (MI) translates human intentions into computer commands by recognizing the electroencephalogram (EEG) patterns of different imagination tasks. However, due to the scarcity of MI commands and the long calibration time, using the MI-based BCI system in practice is still challenging. Zero-shot learning (ZSL), which can recognize objects whose instances may not have been seen during training, has the potential to substantially reduce the calibration time. Thus, in this context, we first try to use a new type of motor imagery task, which is a combination of traditional tasks and propose a novel zero-shot learning model that can recognize both known and unknown categories of EEG signals. This is achieved by first learning a non-linear projection from EEG features to the target space and then applying a novelty detection method to differentiate unknown classes from known classes. Applications to a dataset collected from nine subjects confirm the possibility of identifying a new type of motor imagery only using already obtained motor imagery data. Results indicate that the classification accuracy of our zero-shot based method accounts for 91.81% of the traditional method which uses all categories of data.

Optimization of parameters for improving the performance of EEG-based BCI system

Brain–computer interface (BCI) is an active domain which has attracted attention of the research community in recent years. It offers huge potential as a technology which can estimate the intention of a user by analysis of brain signals and establish a communication channel directly between a human brain and an external device. Electroencephalography (EEG) is the most popular signal acquisition technique due to its ease of use and simplicity. In EEG-based BCI systems, electrodes are placed on specific positions on the scalp of the subject to record electrical activity. The BCI system consists of sequential stages of signal acquisition, its preprocessing, feature extraction and feature classification. It is an active research area which has a focus on improving classification accuracy in motor imagery-based BCI systems. The first stage in a BCI system is to acquire EEG signals from different positions of the scalp of the human subject. The acquired brain signals are preprocessed to remove artifacts before these are fed to feature the extraction stage. In this paper, independent component analysis (ICA) technique is used to remove artifacts from acquired signals. Filter bank common spatial pattern (FBCSP) technique is then used for feature extraction and feature selection. A feature classification approach based on support vector machine (SVM) is proposed in this work and its performance is enhanced by optimizing its polynomial kernel parameters. Selection of kernel parameters is done by grid search method using the fivefold cross-validation procedure. The proposed approach is then executed on publicly available data set 2a of BCI Competition IV. Results show that the proposed approach offers higher classification accuracy and lower misclassification rate as compared to other methods executed on the same dataset, as reported in literature.

On the Better Performance of Pianists with Motor Imagery-Based Brain-Computer Interface Systems.

Motor imagery (MI)-based brain-computer interface (BCI) systems detect electrical brain activity patterns through electroencephalogram (EEG) signals to forecast user intention while performing movement imagination tasks. As the microscopic details of individuals’ brains are directly shaped by their rich experiences, musicians can develop certain neurological characteristics, such as improved brain plasticity, following extensive musical training. Specifically, the advanced bimanual motor coordination that pianists exhibit means that they may interact more effectively with BCI systems than their non-musically trained counterparts; this could lead to personalized BCI strategies according to the users’ previously detected skills. This work assessed the performance of pianists as they interacted with an MI-based BCI system and compared it with that of a control group. The Common Spatial Patterns (CSP) and Linear Discriminant Analysis (LDA) machine learning algorithms were applied to the EEG signals for feature extraction and classification, respectively. The results revealed that the pianists achieved a higher level of BCI control by means of MI during the final trial (74.69%) compared to the control group (63.13%). The outcome indicates that musical training could enhance the performance of individuals using BCI systems.

Channel and Feature Selection for a Motor Imagery-Based BCI System Using Multilevel Particle Swarm Optimization.

Brain-computer interface (BCI) is a communication and control system linking the human brain and computers or other electronic devices. However, irrelevant channels and misleading features unrelated to tasks limit classification performance. To address these problems, we propose an efficient signal processing framework based on particle swarm optimization (PSO) for channel and feature selection, channel selection, and feature selection. Modified Stockwell transforms were used for a feature extraction, and multilevel hybrid PSO-Bayesian linear discriminant analysis was applied to optimization and classification. The BCI Competition III dataset I was used here to confirm the superiority of the proposed scheme. Compared to a method without optimization (89% accuracy), the best classification accuracy of the PSO-based scheme was 99% when less than 10.5% of the original features were used, the test time was reduced by more than 90%, and it achieved Kappa values and F-score of 0.98 and 98.99%, respectively, and better signal-to-noise ratio, thereby outperforming existing algorithms. The results show that the channel and feature selection scheme can accelerate the speed of convergence to the global optimum and reduce the training time. As the proposed framework can significantly improve classification performance, effectively reduce the number of features, and greatly shorten the test time, it can serve as a reference for related real-time BCI application system research.

An adaptive multi-domain feature joint optimization framework based on composite kernels and ant colony optimization for motor imagery EEG classification

Brain computer interface (BCI) is a novel technology that translates human intention into command to control external device. Common spatial pattern (CSP) algorithm is most frequently applied for feature engineering in motor imagery (MI) based BCI system. How to select the most suitable spatial channels, temporal & frequency parameters for different people before CSP is still a challenging issue which greatly affects the performance of MI based BCI system. In this paper, we introduce an adaptive multi-domain feature joint optimization framework. Specifically, random forest (RF) and composite kernel support vector machine (CKSVM) algorithms are used to measure the significances of different spatial channels and local temporal-frequency segments. An ant colony optimization (ACO) based scheme is proposed to search the most suitable spatial channels and temporal-frequency segments. We evaluated the effectiveness of the proposed algorithm on public BCI competition III data set IVa and two self-collected MI EEG datasets. For BCI competition III data set IVa, our method outperforms some other close related algorithms in the literature. For the two self-collected datasets, compared to the traditional manual parameter setting, the classification performance is proven to significantly improve (more than 15%) adopting our adaptive multi-domain parameters. Since our proposed method can simultaneously and automatically optimize subject-specific features in the entire spatial-temporal-frequency domains, the most discriminative CSP features can be selected and the performance of MI EEG classification is significantly improved. Thus, our research is a useful complement to the BCI field.

MLP With Riemannian Covariance for Motor Imagery Based EEG Analysis

Stroke is one of the leading causes of disability and incidence. For the treatment of prognosis of stroke patients, Motor imagery (MI) as a novel experimental paradigm, clinically it is effective because MI based Brain-Computer interface system can promote rehabilitation of stroke patients. There is being a hot and challenging topic to recognize multi-class motor imagery action classification accurately based on electroencephalograph (EEG) signals. In this work, we propose a novel framework named MRC-MLP. Multiple Riemannian covariance is used for EEG feature extraction. We make a multi-scale spectral division to filter EEG signals. They consist of different frequency bandwidths name sub-band. We concatenate and vectorize features extracted by Riemannian covariance on each sub-band. We design a fully connected MLP model with an improved loss function for motor imagery EEG classification. Furthermore, our proposed method MRC-MLP outperforms state-of-the-art methods and achieves approximately mean accuracy with 76%.

Cortical Activations and BCI Performances at Different Speeds of Visual and Proprioceptive Stimulation.

Motor imagery based brain-computer interface (MI-BCI) is one of the most common paradigms utilized in neurofeedback training (NFT) for rehabilitation engineering. Specifically, finding an appropriate feedback protocol is significantly important to improve the effectiveness of the motor training system. To this end, we investigated the electroencephalography(EEG) oscillatory patterns measured by event-related desynchronization (ERD) when sixteen participants accepted the visual and proprioceptive stimulation achieving the kinematic hand grasping movements at three different speeds (i.e. 1/3 Hz, 2/3 Hz and 1 Hz). The EEG results indicated that the ERD patterns showed no significant difference in sensorimotor cortex (i.e. C3 and FC3 channels) by comparing the three conditions. Nevertheless, the 2/3 Hz stimulation speed could achieve a significantly better classification performance than the other two conditions across all participants. Therefore, the visual and proprioceptive electrical stimulation achieving the kinematic hand grasping at 2/3 Hz speed might provide an available approach for the online MI-BCI system based NFT system in the future.