Peiyang Li

Z-Score Linear Discriminant Analysis for EEG Based Brain-Computer Interfaces

Linear discriminant analysis (LDA) is one of the most popular classification algorithms for brain-computer interfaces (BCI). LDA assumes Gaussian distribution of the data, with equal covariance matrices for the concerned classes, however, the assumption is not usually held in actual BCI applications, where the heteroscedastic class distributions are usually observed. This paper proposes an enhanced version of LDA, namely z-score linear discriminant analysis (Z-LDA), which introduces a new decision boundary definition strategy to handle with the heteroscedastic class distributions. Z-LDA defines decision boundary through z-score utilizing both mean and standard deviation information of the projected data, which can adaptively adjust the decision boundary to fit for heteroscedastic distribution situation. Results derived from both simulation dataset and two actual BCI datasets consistently show that Z-LDA achieves significantly higher average classification accuracies than conventional LDA, indicating the superiority of the new proposed decision boundary definition strategy.

L1 norm based common spatial patterns decomposition for scalp EEG BCI.

BackgroundBrain computer interfaces (BCI) is one of the most popular branches in biomedical engineering. It aims at constructing a communication between the disabled persons and the auxiliary equipments in order to improve the patients’ life. In motor imagery (MI) based BCI, one of the popular feature extraction strategies is Common Spatial Patterns (CSP). In practical BCI situation, scalp EEG inevitably has the outlier and artifacts introduced by ocular, head motion or the loose contact of electrodes in scalp EEG recordings. Because outlier and artifacts are usually observed with large amplitude, when CSP is solved in view of L2 norm, the effect of outlier and artifacts will be exaggerated due to the imposing of square to outliers, which will finally influence the MI based BCI performance. While, L1 norm will lower the outlier effects as proved in other application fields like EEG inverse problem, face recognition, etc.MethodsIn this paper, we present a new CSP implementation using the L1 norm technique, instead of the L2 norm, to solve the eigen problem for spatial filter estimation with aim to improve the robustness of CSP to outliers. To evaluate the performance of our method, we applied our method as well as the standard CSP and the regularized CSP with Tikhonov regularization (TR-CSP), on both the peer BCI dataset with simulated outliers and the dataset from the MI BCI system developed in our group. The McNemar test is used to investigate whether the difference among the three CSPs is of statistical significance.ResultsThe results of both the simulation and real BCI datasets consistently reveal that the proposed method has much higher classification accuracies than the conventional CSP and the TR-CSP.ConclusionsBy combining L1 norm based Eigen decomposition into Common Spatial Patterns, the proposed approach can effectively improve the robustness of BCI system to EEG outliers and thus be potential for the actual MI BCI application, where outliers are inevitably introduced into EEG recordings.

Structural and functional correlates of motor imagery BCI performance: Insights from the patterns of fronto-parietal attention network.

Motor imagery (MI)-based brain-computer interfaces (BCIs) have been widely used for rehabilitation of motor abilities and prosthesis control for patients with motor impairments. However, MI-BCI performance exhibits a wide variability across subjects, and the underlying neural mechanism remains unclear. Several studies have demonstrated that both the fronto-parietal attention network (FPAN) and MI are involved in high-level cognitive processes that are crucial for the control of BCIs. Therefore, we hypothesized that the FPAN may play an important role in MI-BCI performance. In our study, we recorded multi-modal datasets consisting of MI electroencephalography (EEG) signals, T1-weighted structural and resting-state functional MRI data for each subject. MI-BCI performance was evaluated using the common spatial pattern to extract the MI features from EEG signals. One cortical structural feature (cortical thickness (CT)) and two measurements (degree centrality (DC) and eigenvector centrality (EC)) of node centrality were derived from the structural and functional MRI data, respectively. Based on the information extracted from the EEG and MRI, a correlation analysis was used to elucidate the relationships between the FPAN and MI-BCI performance. Our results show that the DC of the right ventral intraparietal sulcus, the EC and CT of the left inferior parietal lobe, and the CT of the right dorsolateral prefrontal cortex were significantly associated with MI-BCI performance. Moreover, the receiver operating characteristic analysis and machine learning classification revealed that the EC and CT of the left IPL could effectively predict the low-aptitude BCI users from the high-aptitude BCI users with 83.3% accuracy. Those findings consistently reveal that the individuals who have efficient FPAN would perform better on MI-BCI. Our findings may deepen the understanding of individual variability in MI-BCI performance, and also may provide a new biomarker to predict individual MI-BCI performance.

Local temporal correlation common spatial patterns for single trial EEG classification during motor imagery.

Common spatial pattern (CSP) is one of the most popular and effective feature extraction methods for motor imagery-based brain-computer interface (BCI), but the inherent drawback of CSP is that the estimation of the covariance matrices is sensitive to noise. In this work, local temporal correlation (LTC) information was introduced to further improve the covariance matrices estimation (LTCCSP). Compared to the Euclidean distance used in a previous CSP variant named local temporal CSP (LTCSP), the correlation may be a more reasonable metric to measure the similarity of activated spatial patterns existing in motor imagery period. Numerical comparisons among CSP, LTCSP, and LTCCSP were quantitatively conducted on the simulated datasets by adding outliers to Dataset IVa of BCI Competition III and Dataset IIa of BCI Competition IV, respectively. Results showed that LTCCSP achieves the highest average classification accuracies in all the outliers occurrence frequencies. The application of the three methods to the EEG dataset recorded in our laboratory also demonstrated that LTCCSP achieves the highest average accuracy. The above results consistently indicate that LTCCSP would be a promising method for practical motor imagery BCI application.

Differentiating Between Psychogenic Nonepileptic Seizures and Epilepsy Based on Common Spatial Pattern of Weighted EEG Resting Networks

Discriminating psychogenic nonepileptic seizures (PNES) from epilepsy is challenging, and a reliable and automatic classification remains elusive. In this study, we develop an approach for discriminating between PNES and epilepsy using the common spatial pattern extracted from the brain network topology (SPN). The study reveals that 92% accuracy, 100% sensitivity, and 80% specificity were reached for the classification between PNES and focal epilepsy. The newly developed SPN of resting EEG may be a promising tool to mine implicit information that can be used to differentiate PNES from epilepsy.

The hybrid BCI system for movement control by combining motor imagery and moving onset visual evoked potential

OBJECTIVE Movement control is an important application for EEG-BCI (EEG-based brain-computer interface) systems. A single-modality BCI cannot provide an efficient and natural control strategy, but a hybrid BCI system that combines two or more different tasks can effectively overcome the drawbacks encountered in single-modality BCI control. APPROACH In the current paper, we developed a new hybrid BCI system by combining MI (motor imagery) and mVEP (motion-onset visual evoked potential), aiming to realize the more efficient 2D movement control of a cursor. MAIN RESULT The offline analysis demonstrates that the hybrid BCI system proposed in this paper could evoke the desired MI and mVEP signal features simultaneously, and both are very close to those evoked in the single-modality BCI task. Furthermore, the online 2D movement control experiment reveals that the proposed hybrid BCI system could provide more efficient and natural control commands. SIGNIFICANCE The proposed hybrid BCI system is compensative to realize efficient 2D movement control for a practical online system, especially for those situations in which P300 stimuli are not suitable to be applied.

The Time-Varying Networks in P300: A Task-Evoked EEG Study

P300 is an important event-related potential that can be elicited by external visual, auditory, and somatosensory stimuli. Various cognition-related brain functions (i.e., attention, intelligence, and working memory) and multiple brain regions (i.e., prefrontal, frontal, and parietal) are reported to be involved in the elicitation of P300. However, these studies do not investigate the instant interactions across the neural cortices from the hierarchy of milliseconds. Importantly, time-varying network analysis among these brain regions can uncover the detailed and dynamic information processing in the corresponding cognition process. In the current study, we utilize the adaptive directed transfer function to construct the time-varying networks of P300 based on scalp electroencephalographs, investigating the time-varying information processing in P300 that can depict the deeper neural mechanism of P300 from the network. Our analysis found that different stages of P300 evoked different brain networks, i.e., the center area performs as the central source during the decision process stage, while the source region is transferred to the right prefrontal cortex (rPFC) in the neuronal response stage. Moreover, during the neuronal response stage, the directed information that flows from the rPFC to the parietal cortex are remarkably important. These findings indicate that the two brain hemispheres exhibit asymmetrical functions in processing related information for different P300 stages, and this work may provide new evidence for our better understanding of the neural mechanism of P300 generation.

Autoregressive model in the Lp norm space for EEG analysis

The autoregressive (AR) model is widely used in electroencephalogram (EEG) analyses such as waveform fitting, spectrum estimation, and system identification. In real applications, EEGs are inevitably contaminated with unexpected outlier artifacts, and this must be overcome. However, most of the current AR models are based on the L2 norm structure, which exaggerates the outlier effect due to the square property of the L2 norm. In this paper, a novel AR object function is constructed in the Lp (p≤1) norm space with the aim to compress the outlier effects on EEG analysis, and a fast iteration procedure is developed to solve this new AR model. The quantitative evaluation using simulated EEGs with outliers proves that the proposed Lp (p≤1) AR can estimate the AR parameters more robustly than the Yule-Walker, Burg and LS methods, under various simulated outlier conditions. The actual application to the resting EEG recording with ocular artifacts also demonstrates that Lp (p≤1) AR can effectively address the outliers and recover a resting EEG power spectrum that is more consistent with its physiological basis.

An Adaptive Motion-Onset VEP-Based Brain-Computer Interface

Motion-onset visual evoked potential (mVEP) has been recently proposed for EEG-based brain-computer interface (BCI) system. It is a scalp potential of visual motion response, and typically composed of three components: P1, N2, and P2. Usually several repetitions are needed to increase the signal-to-noise ratio (SNR) of mVEP, but more repetitions will cost more time thus lower the efficiency. Considering the fluctuation of subjects state across time, the adaptive repetitions based on the subjects real-time signal quality is important for increasing the communication efficiency of mVEP-based BCI. In this paper, the amplitudes of the three components of mVEP are proposed to build a dynamic stopping criteria according to the practical information transfer rate (PITR) from the training data. During online test, the repeated stimulus stopped once the predefined threshold was exceeded by the real-time signals and then another circle of stimulus newly began. Evaluation tests showed that the proposed dynamic stopping strategy could significantly improve the communication efficiency of mVEP-based BCI that the average PITR increases from 14.5 bit/min of the traditional fixed repetition method to 20.8 bit/min. The improvement has great value in real-life BCI applications because the communication efficiency is very important.

The extraction of motion-onset VEP BCI features based on deep learning and compressed sensing

BACKGROUND Motion-onset visual evoked potentials (mVEP) can provide a softer stimulus with reduced fatigue, and it has potential applications for brain computer interface(BCI)systems. However, the mVEP waveform is seriously masked in the strong background EEG activities, and an effective approach is needed to extract the corresponding mVEP features to perform task recognition for BCI control. NEW METHOD In the current study, we combine deep learning with compressed sensing to mine discriminative mVEP information to improve the mVEP BCI performance. RESULTS The deep learning and compressed sensing approach can generate the multi-modality features which can effectively improve the BCI performance with approximately 3.5% accuracy incensement over all 11 subjects and is more effective for those subjects with relatively poor performance when using the conventional features. COMPARISON WITH EXISTING METHODS Compared with the conventional amplitude-based mVEP feature extraction approach, the deep learning and compressed sensing approach has a higher classification accuracy and is more effective for subjects with relatively poor performance. CONCLUSIONS According to the results, the deep learning and compressed sensing approach is more effective for extracting the mVEP feature to construct the corresponding BCI system, and the proposed feature extraction framework is easy to extend to other types of BCIs, such as motor imagery (MI), steady-state visual evoked potential (SSVEP)and P300.