A spatial-frequency-temporal optimized feature sparse representation-based classification method for motor imagery EEG pattern recognition.

Entropy, the complexity measures for time series, has found numerous successful applications in brain signal analysis such as detection of epileptic seizure and monitoring the depth of anesthesia. Renyi entropy generalizes the well-known Shannon entropy, and hence providing better flexibility in application to real data. The objective of this paper is to evaluate the effectiveness of Renyi entropy as feature extraction method for motor imagery (MI)-based brain–computer interface (BCI). In this paper, Renyi entropy has been implemented in MI systems of various settings using BCI competition data sets. The classification accuracy of Renyi entropy in all data sets is benchmarked against common spatial pattern (CSP), the state-of-the-art feature extraction method. For common binary class data sets, Renyi entropy achieves an accuracy of approximately 3.4 % higher for BCI Competition II Data Set III and 0.87 % lower for BCI Competition III Data Set I, and there is no difference in accuracy for BCI Competition III Data Set IVc when compared against conventional CSP. In small sample setting, the average classification accuracy using Renyi entropy is approximately 3.4 and 0.3 % higher as compared to conventional CSP and best performing variant of regularized CSP, respectively. In addition, Renyi entropy is also compared to other chaos-inspired feature extraction methods, namely Katz and Higuchi which are implemented for MI systems by earlier researchers. The effect of implementing Renyi entropy on multiple narrower frequency sub-bands is also investigated in this study. In multi-class setting, Renyi entropy shows no statistical difference (p = 0.6022, paired t test) in accuracy when compared to the algorithm of the BCI competition winner. However, Renyi entropy has an advantage of requiring only one single application of feature extraction regardless of the number of classes, while multiple implementation of CSP is required as CSP is originally designed for binary class problem. The successful application of Renyi entropy in all the aforementioned settings indicates that Renyi entropy is a viable feature extraction alternative for MI-based BCI systems.

In motor imagery (MI) based brain-computer interface (BCI), common spatial pattern (CSP) is most popularly used for discriminant feature extraction. However, the performance of CSP depends on the operational frequency bands, which are selected manually or set to a broad frequency range in most of the previously developed applications. Due to subject to subject or even trial to trial variability of frequency band affected by MI task, these methods suffer from poor performance. We have proposed a novel approach, using combination of multivariate iterative filtering (MIF) and CSP (MIFCSP), to automatically select optimal frequency bands based on MIF which can be further used for discriminant feature extraction. MIF decomposes the signal into several multivariate intrinsic mode functions, from which features are extracted using CSP. We select the minimum number of most significant features for which highest classification accuracy is achieved. Subsequently, linear discriminant analysis (LDA) classifier is used to classify different MI tasks. Experimental results for BCI competition IV dataset 2a and BCI competition III-IIIa are presented. For left hand versus right hand MI classification, proposed MIFCSP method provides 83.18% and 84.44% average accuracy, respectively. Superior classification performance confirms that MIFCSP is a promising candidate for MI BCI application.

One of the popular feature extraction algorithms for motor imagery (MI)-based brain-computer interface (BCI) is common spatial pattern (CSP). However, CSP is also very susceptive to the selection of the filter bands, the time windows, and the channels. In this paper, we proposed a novel regularized CSP (RCSP) method to optimize feature extraction in MI-BCI. Then, a robust classifier based on AdaBoost algorithm was presented to perform the classification of MI tasks. Finally, the framework was verified on two public BCI datasets (dataset 1 from the BCI Competition IV and dataset IVa from BCI Competition III). The results suggest the proposed approach achieved superior performance compared with classical CSP and other competing methods. Overall, this method not only improved classification performance, but also reduced the data requirements of other subjects.

Studies have shown that a motor imagery electro encephalogram (EEG)-based brain-computer interface (BCI) system can be used as a rehabilitation tool for stroke patients. Efficient classification of EEG from stroke patients is fundamental in the BCI-based stroke rehabilitation systems. One of the most successful algorithms for EEG classification is the common spatial patterns (CSP). However, studies have reported that the performance of CSP heavily relies on its operational frequency band and channels configuration. To the best of our knowledge, there is no agreed upon clinical conclusion about motor imagery patterns of stroke patients. In this case, it is not available to obtain the active channels and frequency bands related to brain activities of stroke patients beforehand. Hence, for using the CSP algorithm, we usually set a relatively broad frequency range and channels, or try to find subject-related frequency bands and channels. To address this problem, we propose an adaptive boosting algorithm to perform autonomous selection of key channels and frequency band. In the proposed method, the spatial-spectral configurations are divided into multiple preconditions, and a new heuristic supervisor of stochastic gradient boost strategy is utilized to train weak classifiers under these preconditions. Extensive experiment comparisons have been performed on three datasets including two benchmark datasets from the famous BCI competition III and BCI competition IV as well as one self-acquired dataset from stroke patients. Results show that our algorithm yields relatively higher classification accuracies compared with seven state-of-the-art approaches. In addition, the spatial patterns (spatial weights) and spectral patterns (bandpass filters) determined by the algorithm can also be used for further analysis of the data, e.g., for brain source localization and physiological knowledge exploration.

Correlation-based channel selection and regularized feature optimization for MI-based BCI

Common spatial patterns (CSP) is a successful algorithm in motor imagery (MI) based brain-computer interfaces (BCI). However, the performance of the algorithm in electroencephalography (EEG) classification depends largely on the subject's specific frequency band. In this paper, we proposed a new wavelet packet coefficients weighted CSP (WPW-CSP) algorithm to optimize the frequency band of the specific subject for motor imagery (MI) classification. The algorithm is applied to 5 MI data sets of two classes. The results suggest that the proposed algorithm achieves a 4% increase of classification accuracy in off-line analysis, compared to the original CSP algorithm using 8–30 Hz wide band.

Motor Imagery (MI) based Brain Computer Inter-face (BCI) is a promising neurorehabilitation tool for treating motor impaired stroke survivors. It enables the MI electroencephalogram (EEG) signals to be converted/mapped into customized robotic and assisting commands. Even though stroke causes varying effects in the brain, the EEG signals have shown promises towards the MI classification of post-stroke subjects. This paper presents a MI based left and right wrist dorsiflexion classification performed on 6 stoke subjects. The MI EEG data are recorded from 16 electrode locations on the subject’s scalp. Three different feature extraction methods are used to compare and find the best performing one; the first one is based on the Wavelet Packet Decomposition (WPD) combined with Higher Order Statistics (HOS) which is compared with the widely used Common Spatial Pattern (CSP) and Filter Bank Common Spatial Pattern (FBCSP) filter method. The MI classifications are performed using Random Forest (RF) algorithm to achieve a mean accuracy that exceeds 70% for the WPD+HOS method, while outperforming the CSP and FBCSP based methods.

While often presented as promising assistive technologies for motor-impaired users, electroencephalography (EEG)-based Brain-Computer Interfaces (BCIs) remain barely used outside laboratories due to low reliability in real-life conditions. There is thus a need to design long-term reliable BCIs that can be used outside-of-the-lab by end-users, e.g., severely motor-impaired ones. Therefore, we propose and evaluate the design of a multi-class Mental Task (MT)-based BCI for longitudinal training (20 sessions over 3 months) of a tetraplegic user for the CYBATHLON BCI series 2019. In this BCI championship, tetraplegic pilots are mentally driving a virtual car in a racing video game. We aimed at combining a progressive user MT-BCI training with a newly designed machine learning pipeline based on adaptive Riemannian classifiers shown to be promising for real-life applications. We followed a two step training process: the first 11 sessions served to train the user to control a 2-class MT-BCI by performing either two cognitive tasks (REST and MENTAL SUBTRACTION) or two motor-imagery tasks (LEFT-HAND and RIGHT-HAND). The second training step (9 remaining sessions) applied an adaptive, session-independent Riemannian classifier that combined all 4 MT classes used before. Moreover, as our Riemannian classifier was incrementally updated in an unsupervised way it would capture both within and between-session non-stationarity. Experimental evidences confirm the effectiveness of this approach. Namely, the classification accuracy improved by about 30% at the end of the training compared to initial sessions. We also studied the neural correlates of this performance improvement. Using a newly proposed BCI user learning metric, we could show our user learned to improve his BCI control by producing EEG signals matching increasingly more the BCI classifier training data distribution, rather than by improving his EEG class discrimination. However, the resulting improvement was effective only on synchronous (cue-based) BCI and it did not translate into improved CYBATHLON BCI game performances. For the sake of overcoming this in the future, we unveil possible reasons for these limited gaming performances and identify a number of promising future research directions. Importantly, we also report on the evolution of the user's neurophysiological patterns and user experience throughout the BCI training and competition.

Motor imagery (MI) is the most used paradigm in Brain-Computer Interface (BCI). As in other BCI paradigms, it is divided into feature extraction and classification. In this study, we implemented two feature extraction methods, one based on the well-known Common Spatial Pattern (CSP) algorithm and the other based on a not so well-known electroencephalogram (EEG) source localization technique called Low-Resolution Brain Electromagnetic Tomography (LORETA). We evaluated 30 right-handed subjects from an EEG data set made publicly available through Giga Science, where participants performed MI of left- and right-hand movements. After feature extraction with CSP and LORETA, MI tasks classification were carried out using the Linear Discriminant Analysis (LDA), Support Vector Machines (SVM), Naïve Bayes (NB) and Multi-Layer Perceptron (MLP) algorithms. Finally, we evaluated classification performance with all possible combination of classifiers and feature extraction methods. For all classifiers, the CSP feature extraction method performed better than LORETA. The best classification accuracy for the LORETA method was 71.2% and for the CSP method was 94.2%, both achieved with SVM.

In this chapter, motor imagery (MI) based brain-computer interface (BCI) is introduced incorporating the explanation of key components required to design a practical BCI device. Its application to the medical and nonmedical sector is discussed in detail. In the experimental study, a feature extraction method using time, frequency, and phase analysis of Motor imagery EEG is presented. For the classification of MI task, EEG signals are decomposed using a dual-tree complex wavelet transform (DTCWT) and then time, frequency, and phase features are extracted. The validation of the proposed method is conducted using BCI competition IV dataset 2b. A Support vector machine (SVM) classifier is used to perform the classification task. Performance of the proposed method is compared with the standard feature extraction methods. The proposed scheme achieved a larger average classification accuracy of 82.81% which is better than that obtained by other methods.

This paper is focused on the experimental approach to explore the potential of independent component analysis (ICA) in the context of motor imagery (MI)-based brain-computer interface (BCI). We presented a simple and efficient algorithmic framework of ICA-based MI BCI (ICA-MIBCI) for the evaluation of four classical ICA algorithms (Infomax, FastICA, Jade, and Sobi) as well as a simplified Infomax (sInfomax). Two novel performance indexes, self-test accuracy and the number of invalid ICA filters, were employed to assess the performance of MIBCI based on different ICA variants. As a reference method, common spatial pattern (CSP), a commonly-used spatial filtering method, was employed for the comparative study between ICA-MIBCI and CSP-MIBCI. The experimental results showed that sInfomax-based spatial filters exhibited significantly better transferability in session to session and subject to subject transfer as compared to CSP-based spatial filters. The online experiment was also introduced to demonstrate the practicability and feasibility of sInfomax-based MIBCI. However, four classical ICA variants, especially FastICA, Jade, and Sobi, performed much worse as compared to sInfomax and CSP in terms of classification accuracy and stability. We consider that conventional ICA-based spatial filtering methods tend to be overfitting while applied to real-life electroencephalogram data. Nevertheless, the sInfomax-based experimental results indicate that ICA methods have a great space for improvement in the application of MIBCI. We believe that this paper could bring forth new ideas for the practical implementation of ICA-MIBCI.

Multimodal collaborative BCI system based on the improved CSP feature extraction algorithm

The study aimed to compare the effects of combined action observation and motor imagery (AOMI) and motor imagery (MI)-based brain-computer interface (BCI) training on upper limb recovery, cortical excitation, and cognitive task performance in chronic stroke patients. 17 chronic stroke patients were recruited and randomly assigned to AOMI-based BCI (n = 9) and MI-based BCI groups (n = 8). The AOMI-based BCI group received AOMI-based BCI training via functional electrical stimulation (FES) feedback, whereas the MI-based BCI group obtained MI-based BCI training via FES feedback. Both groups participated in training for 12 sessions (3 days/week, consecutive four weeks). To evaluate upper limb function recovery, the Fugl–Meyer Assessment for upper extremity (FMA-UE) was employed. Event-related desynchronization (ERD) and online classification accuracy were utilized to measure cortical excitation of the affected sensorimotor hand region and cognitive task performance, respectively. Both AOMI and MI-based BCI training improved upper limb function in chronic stroke patients. However, the AOMI-based BCI group showed significantly greater motor gain than the MI-based BCI group. In addition, the AOMI-based BCI group demonstrated significantly greater cortical excitation of the affected sensorimotor hand region and cognitive task performance. The correlation analysis revealed that higher cognitive task performance during AOMI-based BCI training may promote greater cortical excitation of the affected sensorimotor hand region, which contributes to greater upper limb function improvement compared to MI-based BCI training.

Neural networks (NNs) can be deployed in many different ways in signal processing applications. This paper illustrates how neural networks are employed in a prediction based preprocessing framework, referred to as neural-time-series-prediction-preprocessing (NTSPP), in an electroencephalogram (EEG)-based brain-computer interface (BCI). NTSPP has been shown to increase feature separability by mapping the original EEG signals via time-series-prediction to a higher dimensional space. Preliminary results of a similar novel framework are also presented where, instead of using predictive NNs, auto-associative NNs are employed and features are extracted from the output of auto-associative NNs trained to specialize on EEG signals for particular brain states. The results show that this preprocessing framework referred to as auto-associative NN preprocessing (ANNP) also has the potential to improve the performance of BCIs. Both the NTSPP and ANNP are compared with and deployed in conjunction with the well know common spatial patterns (CSP) to produce a BCI system which significantly outperforms either approach operating independently and has the potential to produce good performances even with a lower number of EEG channels compared to a multichannel BCI. Multichannel BCIs normally perform better that 2-3 channel BCIs however reducing the number of EEG channels required can positively impact on the time needed to mount electrodes and minimize the obtrusiveness of the electrode montage for the user. It is also shown that NTSPP can improve the potential for employing existing BCI methods with minimal subject-specific parameter tuning to deploy the BCI autonomously. Results are presented with six different classification approaches including various statistical classifiers such as Linear Discriminant Analysis (LDA), Support Vector Machines (SVM) and a Bayes classifier.

F190. Mindfulness based stress reduction’s influence on brain-computer interface control