Subject-independent Brain Computer Interface Research Articles

Subject-independent EEG classification based on a hybrid neural network.

A brain-computer interface (BCI) based on the electroencephalograph (EEG) signal is a novel technology that provides a direct pathway between human brain and outside world. For a traditional subject-dependent BCI system, a calibration procedure is required to collect sufficient data to build a subject-specific adaptation model, which can be a huge challenge for stroke patients. In contrast, subject-independent BCI which can shorten or even eliminate the pre-calibration is more time-saving and meets the requirements of new users for quick access to the BCI. In this paper, we design a novel fusion neural network EEG classification framework that uses a specially designed generative adversarial network (GAN), called a filter bank GAN (FBGAN), to acquire high-quality EEG data for augmentation and a proposed discriminative feature network for motor imagery (MI) task recognition. Specifically, multiple sub-bands of MI EEG are first filtered using a filter bank approach, then sparse common spatial pattern (CSP) features are extracted from multiple bands of filtered EEG data, which constrains the GAN to maintain more spatial features of the EEG signal, and finally we design a convolutional recurrent network classification method with discriminative features (CRNN-DF) to recognize MI tasks based on the idea of feature enhancement. The hybrid neural network proposed in this study achieves an average classification accuracy of 72.74 ± 10.44% (mean ± std) in four-class tasks of BCI IV-2a, which is 4.77% higher than the state-of-the-art subject-independent classification method. A promising approach is provided to facilitate the practical application of BCI.

Comparison of subject-independent and subject-specific EEG-based BCI using LDA and SVM classifiers

Motor imagery brain-computer interface (MI-BCI) is one of the most used paradigms in EEG-based brain-computer interface (BCI). The current state-of-the-art in BCI involves tuning classifiers to subject-specific training data, acquired over several sessions, in order to perform calibration prior to actual use of the so-called subject-specific BCI system (SS-BCI). Herein, the goal is to provide a ready-to-use system requiring minimal effort for setup. Thus, our challenge was to design a subject-independent BCI (SI-BCI) to be used by any new user without the constraint of individual calibration. Outcomes from other studies with the same purpose were used to undertake comparisons and validate our findings. For the EEG signal processing, we used a combination of the delta (0.5-4Hz), alpha (8-13Hz), and beta+gamma (13-40Hz) bands at a stage prior to feature extraction. Next, we extracted features from the 27-channel EEG using common spatial pattern (CSP) and performed binary classification (MI of right- and left-hand) with linear discriminant analysis (LDA) and support vector machine (SVM) classifiers. These analyses were done for both the SS-BCI and SI-BCI models. We employed "leave-one-subject-out" (LOSO) arrangement and 10-fold cross-validation to evaluate our SI-BCI and SS-BCI systems, respectively. Compared with other two studies, our work was the only one that showed higher accuracy for the LDA classifier in SI-BCI as compared to SS-BCI. On the other hand, LDA accuracy was lower than accuracy achieved with SVM in both conditions (SI-BCI and SS-BCI). Our SS-BCI accuracy reached 76.85% using LDA and 94.20% using SVM and for SI-BCI we got 80.30% with LDA and 83.23% with SVM. We conclude that SI-BCI may be a feasible and relevant option, which can be used in scenarios where subjects are not able to submit themselves to long training sessions or to fast evaluation of the so called "BCI illiteracy." Comparatively, our strategy proved to be more efficient, giving us the best result for SI-BCI when faced against the classification performances of other three studies, even considering the caveat that different datasets were used in the comparison of the four studies.

Towards real-world BCI: CCSPNet, a compact subject-independent motor imagery framework

A conventional brain-computer interface (BCI) requires a complete data gathering, training, and calibration phase for each user before it can be used. In recent years, a number of subject-independent (SI) BCIs have been developed. Many of these methods yield a weaker performance compared to the subject-dependent (SD) approach, and some are computationally expensive. A potential real-world application would greatly benefit from a more accurate, compact, and computationally efficient subject-independent BCI. In this work, we propose a novel subject-independent BCI framework, named CCSPNet (Convolutional Common Spatial Pattern Network) that is trained on the motor imagery (MI) paradigm of a large-scale electroencephalography (EEG) signals database consisting of 400 trials for every 54 subjects who perform two-class hand-movement MI tasks. The proposed framework applies a wavelet kernel convolutional neural network (WKCNN) and a temporal convolutional neural network (TCNN) in order to represent and extract the spectral features of EEG signals. A common spatial pattern (CSP) algorithm is implemented for spatial feature extraction, and the number of CSP features is reduced by a dense neural network. Finally, the class label is determined by a linear discriminant analysis (LDA) classifier. The CCSPNet evaluation results show that it is possible to have a compact BCI that achieves both SD and SI state-of-the-art performance comparable to complex and computationally expensive models.

Prototype-based Domain Generalization Framework for Subject-Independent Brain-Computer Interfaces.

Brain-computer interface (BCI) is challenging to use in practice due to the inter/intra-subject variability of electroencephalography (EEG). The BCI system, in general, necessitates a calibration technique to obtain subject/session-specific data in order to tune the model each time the system is utilized. This issue is acknowledged as a key hindrance to BCI, and a new strategy based on domain generalization has recently evolved to address it. In light of this, we've concentrated on developing an EEG classification framework that can be applied directly to data from unknown domains (i.e. subjects), using only data acquired from separate subjects previously. For this purpose, in this paper, we proposed a framework that employs the open-set recognition technique as an auxiliary task to learn subject-specific style features from the source dataset while helping the shared feature extractor with mapping the features of the unseen target dataset as a new unseen domain. Our aim is to impose cross-instance style in-variance in the same domain and reduce the open space risk on the potential unseen subject in order to improve the generalization ability of the shared feature extractor. Our experiments showed that using the domain information as an auxiliary network increases the generalization performance. Clinical relevance-This study suggests a strategy to improve the performance of the subject-independent BCI systems. Our framework can help to reduce the need for further calibration and can be utilized for a range of mental state monitoring tasks (e.g. neurofeedback, identification of epileptic seizures, and sleep disorders).

Motor imagery classification in brain-machine interface with machine learning algorithms: Classical approach to multi-layer perceptron model

Motor Imagery classification is a major topic in Brain-Computer Interface (BCI) because of its value for clinical restoration of impaired motor ability. Compared to the classical approaches combined with Machine Learning (ML) algorithms are primarily investigated during the past decade, the number of studies that employ Deep Learning methods on BCI applications is relatively limited. In this study, we aim to provide a comprehensive comparison between traditional classification methods and suggests the significance of Deep Learning-based BCI techniques, especially Multi-Layered Perceptron. In summary, with Electroencephalography (EEG) signals during motor imagery tasks, Support Vector Machine (SVM) showed the shortest training time and prediction speed with comparable accuracy among traditional ML-based algorithms. Notably, our subject-independent generalized MLP model succsfully classified the signals with ≈90% accuracy and half the classification time compared to traditional ML-based models. (1) This result suggests that this standard MLP model can become a bridging wireframe for further advanced subject-independent BCI with sophisticated optimization. (2) This result suggests the possibility of a much accurate and robust generalized BCI (subject independent) if this model integrates sophisticated optimization.

Learning Invariant Patterns Based on a Convolutional Neural Network and Big Electroencephalography Data for Subject-Independent P300 Brain-Computer Interfaces.

A brain-computer interface (BCI) measures and analyzes brain activity and converts this activity into computer commands to control external devices. In contrast to traditional BCIs that require a subject-specific calibration process before being operated, a subject-independent BCI learns a subject-independent model and eliminates subject-specific calibration for new users. However, building subject-independent BCIs remains difficult because electroencephalography (EEG) is highly noisy and varies by subject. In this study, we propose an invariant pattern learning method based on a convolutional neural network (CNN) and big EEG data for subject-independent P300 BCIs. The CNN was trained using EEG data from a large number of subjects, allowing it to extract subject-independent features and make predictions for new users. We collected EEG data from 200 subjects in a P300-based spelling task using two different types of amplifiers. The offline analysis showed that almost all subjects obtained significant cross-subject and cross-amplifier effects, with an average accuracy of more than 80%. Furthermore, more than half of the subjects achieved accuracies above 85%. These results indicated that our method was effective for building a subject-independent P300 BCI, with which more than 50% of users could achieve high accuracies without subject-specific calibration.

MACRO: Multi-Attention Convolutional Recurrent Model for Subject-Independent ERP Detection

Due to the low signal-to-noise ratio, limited training samples, and large inter-subject variabilities in electroencephalogram (EEG) signals, developing a subject-independent brain-computer interface (BCI) system used for new users without any calibration is still challenging. In this letter, we propose a novel Multi-Attention Convolutional Recurrent mOdel (MACRO) for EEG-based event-related potential (ERP) detection in the subject-independent scenario. Specifically, the convolutional recurrent network is designed to capture the spatial-temporal features, while the multi-attention mechanism is integrated to focus on the most discriminative channels and temporal periods of EEG signals. Comprehensive experiments conducted on a benchmark dataset for RSVP-based BCIs show that our method achieves the best performance compared with the five state-of-the-art baseline methods. This result indicates that our method is able to extract the underlying subject-invariant EEG features and generalize to unseen subjects. Finally, the ablation studies verify the effectiveness of the designed multi-attention mechanism in MACRO for EEG-based ERP detection.

A New Framework for Automatic Detection of Motor and Mental Imagery EEG Signals for Robust 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.

A performance based feature selection technique for subject independent MI based BCI.

Significant research has been conducted in the field of brain computer interface (BCI) algorithm development, however, many of the resulting algorithms are both complex, and specific to a particular user as the most successful methodology can vary between individuals and sessions. The objective of this study was to develop a simple yet effective method of feature selection to improve the accuracy of a subject independent BCI algorithm and streamline the process of BCI algorithm development. Over the past several years, several high precision features have been suggested by researchers to classify different motor imagery tasks. This research applies fourteen of these features as a feature pool that can be used as a reference for future researchers. Additionally, we look for the most efficient feature or feature set with four different classifiers that best differentiates several motor imagery tasks. In this work we have successfully employed a feature fusion method to obtain the best sub-set of features. We have proposed a novel computer aided feature selection method to determine the best set of features for distinguishing between motor imagery tasks in lieu of the manual feature selection that has been performed in past studies. The features selected by this method were then fed into a Linear Discriminant Analysis, K-nearest neighbor, decision tree, or support vector machine classifier for classification to determine the overall performance. The methods used were a novel performance based additive feature fusion algorithm working in conjunction with machine learning in order to classify the motor imagery signals into particular states. The data used for this study was collected from BCI competition III dataset IVa. The result of this algorithm was a classification accuracy of 99% for a subject independent algorithm with less computation cost compared to traditional methods, in addition to multiple feature/classifier combinations that outperform current subject independent methods. The conclusion of this study and its significance is that it developed a viable methodology for simple, efficient feature selection and BCI algorithm development, which leads to an overall increase in algorithm classification accuracy.

Wavelet Entropy-Based Inter-subject Associative Cortical Source Localization for Sensorimotor BCI.

We propose event-related cortical sources estimation from subject-independent electroencephalography (EEG) recordings for motor imagery brain computer interface (BCI). By using wavelet-based maximum entropy on the mean (wMEM), task-specific EEG channels are selected to predict right hand and right foot sensorimotor tasks, employing common spatial pattern (CSP) and regularized common spatial pattern (RCSP). EEG from five healthy individuals (Dataset IVa, BCI Competition III) were evaluated by a cross-subject paradigm. Prediction performance was evaluated via a two-layer feed-forward neural network, where the classifier was trained and tested by data from two subjects independently. On average, the overall mean prediction accuracies obtained using all 118 channels are (55.98±6.53) and (71.20±5.32) in cases of CSP and RCSP, respectively, which are slightly lower than the accuracies obtained using only the selected channels, i.e., (58.95±6.90) and (71.41±6.65), respectively. The highest mean prediction accuracy achieved for a specific subject pair by using selected EEG channels was on average (90.36±5.59) and outperformed that achieved by using all available channels (86.07 ± 10.71). Spatially projected cortical sources approximated using wMEM may be useful for capturing inter-subject associative sensorimotor brain dynamics and pave the way toward an enhanced subject-independent BCI.

Does A Subject Independent Dynamic Stopping Model for P300 Speller Work on Different Flash Durations and Inter Stimulus Intervals?

Event-related potential (ERP)-based brain- computer interfacing (BCI) is an effective communication method. However, calibration itself can be unintuitive and tedious for users. The no-calibration Subject Independent Brain Computer Interface (SIBCI) is a popular solution to the lengthy calibration. Researches have proved the subject independent model is efficient in some P300 spellers, but it is still need to be explored whether the subject independent model works when the flash durations (FDs) and the inter stimulus intervals (ISIs) are changed in a P300 speller. This study introduces a subject independent dynamical stopping model (SIDSM), which based on a subject independent model to dynamically stop the data collection process. The performance of the SIDSM is studied by modifying the FDs and ISIs in online experiments for 8 subjects. Results showed the SIDSM has an average accuracy of 92.45% for different settings. This research proved that the SIDSM is very robust to different stimulus parameters as good performance is observed across all experimental sessions.

A transplantation of subject-independent model in cross-platform BCI

With the development of wearable technology, portable wireless systems have been used gradually for collecting electroencephalogram (EEG) signals. However, the introduction of portable collection devices always means a descent in signal-to-noise ratio (SNR) of EEG. Subject-independent brain-computer interface (BCI) avoids conventional calibration procedure for new users. However, whether subject-independent model can be used in cross-platform BCI has not been discussed so far. This paper transplanted the subject-independent model from a high-SNR platform to a lower one for recognition in P300-Speller. After comparing their EEG features elicited from diverse collection platforms, a model adjustment strategy was proposed to increase recognition accuracy. By model adjustment, the average accuracy was 85.00% in online spell experiments. The results indicate it is feasible for subject-independent model transplantation, especially after model adjustment strategy. It provides technology supported for further development of cross-platform BCI.

An approach to improve the performance of subject-independent BCIs-based on motor imagery allocating subjects by gender.

BackgroundOne of the difficulties for the implementation of Brain-Computer Interface (BCI) systems for motor impaired patients is the time consumed in the system design process, since patients do not have the adequate physical nor psychological conditions to complete the process. For this reason most of BCIs are designed in a subject-dependent approach using data of healthy subjects. The developing of subject-independent systems is an option to decrease the required training sessions to design a BCI with patient functionality. This paper presents a proof-of-concept study to evaluate subject-independent system based on hand motor imagery taking gender into account.MethodsSubject-Independent BCIs are proposed using Common Spatial Patterns and log variance features of two groups of healthy subjects; one of the groups was composed by people of male gender and the other one by people of female gender. The performance of the developed gender-specific BCI designs was evaluated with respect to a subject-independent BCI designed without taking gender into account, and afterwards its performance was evaluated with data of two healthy subjects that were not included in the initial sample. As an additional test to probe the potential use for subcortical stroke patients we applied the methodology to two patients with right hand weakness. T-test was employed to determine the significance of the difference between traditional approach and the proposed gender-specific approach.ResultsFor most of the tested conditions, the gender-specific BCIs have a statistically significant better performance than those that did not take gender into account. It was also observed that with a BCI designed with log-variance features in the alpha and beta band of healthy subjects’ data, it was possible to classify hand motor imagery of subcortical stroke patients above the practical level of chance.ConclusionsA larger subjects’ sample test may be necessary to improve the performances of the gender-specific BCIs and to further test this methodology on different patients. The reduction of complexity in the implementation of BCI systems could bring these systems closer to applications such as controlling devices for the motor rehabilitation of stroke patients, and therefore, contribute to a more effective neurological rehabilitation.

Brain Computer Interfacing: A Multi-Modal Perspective

Multi-modal techniques have received increasing interest in the neuroscientific and brain computer interface (BCI) communities in recent times. Two aspects of multi-modal imaging for BCI will be reviewed. First, the use of recordings of multiple subjects to help find subject-independent BCI classifiers is considered. Then, multi-modal neuroimaging methods involving combined electroencephalogram and near-infrared spectroscopy measurements are discussed, which can help achieve enhanced and robust BCI performance.