XDAWN Algorithm to Enhance Evoked Potentials: Application to Brain–Computer Interface

One problem in the development of brain-computer interface (BCI) systems is to minimize the amount of subject training on the premise of accurate classification. Hence, the challenge is how to train the BCI system effectively especially in the scenario with small amount of training data. In this paper, we introduce improved semisupervised adaptation based on common spatial pattern (CSP) features. The feature extraction and classification are performed jointly and iteratively. In the iteration step, training data are expanded by part of the testing data with labels which are predicted by a linear discriminant analysis classifier and/or a Bayesian linear discriminant analysis classifier in the previous iteration. Then CSP features are reextracted from the expanded training data, and the classifiers are retrained. Both self-training and cotraining paradigms are proposed for the improved semisupervised adaptation. Throughout the investigation on different number of initial training trials, we find that when a small number of training trials are used, e.g., a training session contains no more than 30 trials, similar classification performance to that of large training data items (40-50 trials) can be achieved. Effectiveness of the algorithms is verified by two competition datasets. Compared with several existing algorithms, the proposed semisupervised algorithms show improvements in classification accuracy for most of the competition datasets especially in the case of small training data.

Motor imagery classification in electroencephalography (EEG)-based brain-computer interface (BCI) systems is an important research area. To simplify the complexity of the classification, selected power bands and electrode channels have been widely used to extract and select features from raw EEG signals, but there is still a loss in classification accuracy in the state-of-the-art approaches. To solve this problem, we propose a discriminative feature extraction algorithm based on power bands with principle component analysis (PCA). First, the raw EEG signals from the motor cortex area were filtered using a bandpass filter with μ and β bands. This research considered the power bands within a 0.4 second epoch to select the optimal feature space region. Next, the total feature dimensions were reduced by PCA and transformed into a final feature vector set. The selected features were classified by applying a support vector machine (SVM). The proposed method was compared with a state-of-art power band feature and shown to improve classification accuracy.

The purpose of this study is to motivate the use of the simpler Linear Discriminant (LD) classifier as compared to the commonly used Multilayer-perceptron-backpropagation (MLP-BP) neural network for Brain Computer Interface (BCI) design. We investigated the performances of MLP-BP and LD classifiers for mental task based BCI design. In the experimental study, EEG signals from five mental tasks were recorded from four subjects and the classification performances of different combinations of two mental tasks were studied for each subject. Two different AR models were used to compute the features from the electroencephalogram signals: Burg's algorithm (ARB) and Least Square algorithm (ARLS). The results showed that in most cases, LD classifier gave superior classification performance as compared to MLP-BP, with reduced computational complexity. However, the best mental tasks for each subject were the same using both classifiers. ARLS gave the best performance (93.10%) using MLP-BP and (97.00%) using LD. As the best mental task combinations varied between subjects, we conclude that for different subjects, proper selection of mental tasks and feature extraction methods would be essential for a BCI design.

Objective. Classification of electroencephalography (EEG)-based motor imagery (MI) is a crucial non-invasive application in brain–computer interface (BCI) research. This paper proposes a novel convolutional neural network (CNN) architecture for accurate and robust EEG-based MI classification that outperforms the state-of-the-art methods. Approach. The proposed CNN model, namely EEG-inception, is built on the backbone of the inception-time network, which has showed to be highly efficient and accurate for time-series classification. Also, the proposed network is an end-to-end classification, as it takes the raw EEG signals as the input and does not require complex EEG signal-preprocessing. Furthermore, this paper proposes a novel data augmentation method for EEG signals to enhance the accuracy, at least by 3%, and reduce overfitting with limited BCI datasets. Main results. The proposed model outperforms all state-of-the-art methods by achieving the average accuracy of 88.4% and 88.6% on the 2008 BCI Competition IV 2a (four-classes) and 2b datasets (binary-classes), respectively. Furthermore, it takes less than 0.025 s to test a sample suitable for real-time processing. Moreover, the classification standard deviation for nine different subjects achieves the lowest value of 5.5 for the 2b dataset and 7.1 for the 2a dataset, which validates that the proposed method is highly robust. Significance. From the experiment results, it can be inferred that the EEG-inception network exhibits a strong potential as a subject-independent classifier for EEG-based MI tasks.

Electroencephalogram (EEG) signals are one of the most widely used noninvasive signals in brain–computer interfaces. Large dimensional EEG recordings suffer from poor signal-to-noise ratio. These signals are very much prone to artifacts and noise, so sufficient preprocessing is done on raw EEG signals before using them for classification or regression. Properly selected spatial filters enhance the signal quality and subsequently improve the rate and accuracy of classifiers, but their applicability to solve regression problems is quite an unexplored objective. This paper extends common spatial patterns (CSP) to EEG state space using fuzzy time delay and thereby proposes a novel approach for spatial filtering. The approach also employs a novel fuzzy information theoretic framework for filter selection. Experimental performance on EEG-based reaction time (RT) prediction from a lane-keeping task data from 12 subjects demonstrated that the proposed spatial filters can significantly increase the EEG signal quality. A comparison based on root-mean-squared error (RMSE), mean absolute percentage error (MAPE), and correlation to true responses is made for all the subjects. In comparison to the baseline fuzzy CSP regression one versus rest, the proposed Fuzzy Time-delay Common Spatio-Spectral filters reduced the RMSE on an average by $\text{9.94}\%$ , increased the correlation to true RT on an average by $\text{7.38}\%$ , and reduced the MAPE by $\text{7.09}\%$ .

In this paper, to develop a mobile robot by using a BCI to issue a motion command including turning left and right and going forward, we propose a new P300 Brain-computer interface (BCI). Three kinds of P300 visual stimuli were first designed. And then we developed the corresponding BCI systems based on the three stimuli and compared their performance by using a linear discriminant analysis classifier with the features selected from EEG potentials via principal component analysis. Experimental results from three participants suggest that the BCIs with the last two kinds of stimuli can select a desired command with over 80% accuracy in about four seconds of selection time, showing that using the proposed BCI to control a robot is feasible.

Emotion recognition from single-channel EEG signals using a two-stage correlation and instantaneous frequency-based filtering method

The crucial problem which has to be solved when an effective brain-computer interface (BCI) is to be design is: how to reduce the huge space of features extracted from raw EEG signals? One of the techniques of feature selection often used by BCI researches are genetic algorithms (GA). This approach, in its classic form, allows obtaining a feature set which gives the high classification precision, however, the dimension of this set is often still too large to create a reliable classifier. The paper presents a modified version of genetic algorithm, which is capable of choosing feature sets of a slightly lower classification precision but significantly smaller number of features. The practical application of the proposed algorithm will be presented via a benchmark EEG set submitted to the second BCI Competition (data set III - motor imaginary).

Elimination of EOG signals from raw EEG signals using step size based recursive least squares- least mean fourth adaptive algorithm

Brain–computer interface (BCI) based on motor imagery electroencephalogram (EEG) has been widely used in various applications. Despite the previous efforts, the remained major challenges are effective feature extraction and the time-consuming calibration procedure. To address these issues, a novel multiattention adaptation network integrating the multiple attention mechanism and transfer learning is proposed to classify the EEG signals. First, the multiattention layer is introduced to automatically capture the dominant brain regions relevant to mental tasks without incorporating any prior knowledge about the physiology. Then, a multiattention convolutional neural network is employed to extract deep representation from raw EEG signals. Especially, a domain discriminator is applied to deep representation to reduce the differences between sessions for target subjects. The extensive experiments are conducted on three public EEG datasets (Dataset IIa and IIb of BCI Competition IV, and High Gamma dataset), achieving the competitive performance with average classification accuracy of 81.48%, 82.54%, and 93.97%, respectively. All the results outperform the state-of-the-art algorithms demonstrate the effectiveness and robustness of the proposed method. Importantly, we confirm that it is easier and more appropriate to transfer the information from local brain regions than from the whole brain. This enhances the transfer ability of deep features and, hence, it improves the performance of BCI systems.

Recent developments in Brain Computer Interfacing (BCI) and neuroprosthetics have played a vital role for disable people to expect better life quality. In this contribution Electroencephalographic (EEG) signals acquired from six healthy test subjects, are used for the offline analysis of BCI through classification of four lower limb movements including talocrural (ankle) joint dorsi-planter flexion and knee joint extension-flexion. Fourteen channel Emotive EPOC head set is used to acquire EEG signals from sensorimotor cortex area of brain, using a particular data acquisition timeline protocol. Features are extracted in time domain from raw EEG data. Power spectral density, variance, mean value and kurtosis features are applied on raw EEG signals. Multiple classification algorithms are implemented for discrimination of four lower limb movements within data set. The paper uses Quadratic discriminant analysis, Naïve Bayes and Support vector machine classifiers to stratify the movement intent of lower limb. Maximum classification accuracies achieved through various classifiers are; 86.35% with average band power & QDA, 84.38% with mean value & QDA and 78.13% with power spectral density & Quadratic-SVM. The presented findings are optimistic in making the path easier towards the development of BCIs with rich EEG based control signals using noninvasive technology.

Brain-computer interface (BCI) provides the brain with a new communication and control channel for conveying messages and commands to the outside world. BCIs require effective on-line processing of EEG or P300 which appeared just 300ms after the event happened. In this paper, we use a method of Bayesian linear discriminant analysis (BLDA) to classify P300 signals from the data set of BCI Competition III. P300 are obtained when subjects were facing a screen on which flashed objects were displayed. Before training a classification parameter for the BLDA, several preprocessing operations were applied to the data including filtering, trial extraction et al. With the BLDA algorithm, the classification accuracy in our experiment could be up to above 80%, depends on the averaged times of trials and SNR of the data. In summary, it is suitable to use LDA in the P300-based BCI system, and LDA will be a promising method to extract feature for BCI designs.

One of the challenges of using brain-computer interfaces (BCIs) over extended periods of time is the variation of the users' performance from one experimental day to another. The goal of the current study is to propose a performance estimator for an electroencephalography-based motor imagery BCI by assessing the reliability of a command (i.e., predicting a 'short' or 'long' command delivery time, CDT). Using a short time window (<1.5 s, shorter than the delivery time) of the mental task execution and a linear discriminant analysis classifier, we could reliably differentiate between short and long CDT (Area under the sensitivity-specificity curve, AUC . 0.8) for 9 healthy subjects. Moreover, we assessed the feasibility of providing online adaptive assistance using the performance estimator in a BCI game by comparing two conditions: (i) allowing a 'fixed timeout' to deliver each command or (ii) providing 'adaptive assistance' by giving more time if the performance estimator detects a long CDT. The results revealed that providing adaptive assistance increases the ratio of correct commands significantly cantly (p <0.01). Moreover, the task load index (measured via the NASA TLX questionnaire) shows a significantly higher user acceptance in case of providing adaptive assistance (p <0.01). Furthermore, the results obtained in this study were used to simulate a robotic navigation scenario, which showed how adaptive assistance improved performance.

Brain-computer interfaces (BCIs) based on electroencephalography (EEG) enable neural activity interpretation for device control, with motor imagery (MI) serving as a key paradigm for decoding imagined movements. Efficient feature extraction from raw EEG signals is essential to improve classification accuracy while minimizing reliance on extensive preprocessing. In this study, we introduce new hybrid architectures to enhance MI classification using data augmentation and a limited number of EEG channels. The first model combines a shallow convolutional neural network and a gated recurrent unit (CNN-GRU), while the second incorporates a convolutional neural network with a bidirectional gated recurrent unit (CNN-Bi-GRU). Evaluated using the publicly available PhysioNet dataset, the CNN-GRU classifier achieved peak mean accuracy rates of 99.71%, 99.73%, 99.61%, and 99.86% for tasks involving left fist (LF), right fist (RF), both fists (LRF), and both feet (BF), respectively. The experimental results provide compelling evidence that our proposed models outperform current state-of-the-art methods, underscoring their efficiency on small-scale EEG datasets. The CNN-GRU and CNN-Bi-GRU architectures exhibit superior predictive reliability, offering a faster, cost-effective solution for user-adaptable MI-BCI applications.

Objective. A brain–computer interface (BCI) equips humans with the ability to control computers and technical devices mentally. However, the enormous data and the existing irrelevant features of the electrocorticogram signal limit the performance of the classifier. To address these problems, a novel signal processing framework for a binary motor imagery-based BCI system (MI–BCI) is proposed in this paper. Approach. Stockwell transform and Bayesian linear discriminant analysis were applied to feature extraction and classification, respectively, and a genetic algorithm (GA) was used in the process of feature selection to extract the most relevant features for classification. The superiority of the algorithm is demonstrated through test results based on the BCI Competition III dataset I. Main results. By comparing the processes with or without feature selection, the performance of the classification was proven to improve using the GA. By adjusting the parameters of the GA, the best feature set (selected 48.6% features) was selected to achieve classification sensitivity, specificity, precision, and accuracy of 94%, 98%, 97.9%, and 96%, respectively, exceeding the results of the existing state-of-the art algorithms. Significance. As the proposed method can reduce the number of features and select the best feature set, its classification performance was improved and the classification time was shortened; thus, it can be applied to various BCI systems.