Optimizing the Channel Selection and Classification Accuracy in EEG-Based BCI

A Riemannian Geometry Approach to Reduced and Discriminative Covariance Estimation in Brain Computer Interfaces

OBJECTIVE

Spatial covariance matrices are extensively employed as brain activity descriptors in brain computer interface (BCI) research that, typically, involve the whole array of sensors. Here, we introduce a methodological framework for delineating the subset of sensors, the covariance structure of which offers a reduced, but more powerful, representation of brain's coordination patterns that ultimately leads to reliable mind reading.

METHODS

Adopting a Riemannian geometry approach, we turn the problem of sensor selection as a maximization of a functional that is computed over the manifold of symmetric positive definite (SPD) matrices and encapsulates class separability in a way that facilitates the search among subsets of different size. The introduced optimization task, namely discriminative covariance reduction (DCR), lacks an analytical solution and is tackled via the cross-entropy optimization technique.

RESULTS

Based on two different EEG datasets and three distinct classification schemes, we demonstrate that the DCR approach provides a noteworthy gain in terms of accuracy (in some cases exceeding 20%) and a remarkable reduction in classification time (on average 82%). Additionally, results include the intriguing empirical finding that the pattern of selected sensors in the case of disabled persons depends on the type of disability.

CONCLUSION

The proposed DCR framework can speed up the classification time in BCI-systems operating on the SPD manifolds by simultaneously enhancing their reliability. This is achieved without sacrificing the neuroscientific interpretability endowed in the topographical arrangement of the selected sensors.

SIGNIFICANCE

Riemannian geometry is exploited for DCR in BCI systems, in a dimensionality-agnostic manner, guaranteeing improved performance.

Investigating EEG Patterns for Dual-Stimuli Induced Human Fear Emotional State

Most electroencephalography (EEG) based emotion recognition systems make use of videos and images as stimuli. Few used sounds, and even fewer studies were found involving self-induced emotions. Furthermore, most of the studies rely on single stimuli to evoke emotions. The question of "whether different stimuli for same emotion elicitation generate any subject-independent correlations" remains unanswered. This paper introduces a dual modality based emotion elicitation paradigm to investigate if emotions can be classified induced with different stimuli. A method has been proposed based on common spatial pattern (CSP) and linear discriminant analysis (LDA) to analyze human brain signals for fear emotions evoked with two different stimuli. Self-induced emotional imagery is one of the considered stimuli, while audio/video clips are used as the other stimuli. The method extracts features from the CSP algorithm and LDA performs classification. To investigate associated EEG correlations, a spectral analysis was performed. To further improve the performance, CSP was compared with other regularized techniques. Critical EEG channels are identified based on spatial filter weights. To the best of our knowledge, our work provides the first contribution for the assessment of EEG correlations in the case of self versus video induced emotions captured with a commercial grade EEG device.

Reduce Calibration Time in Motor Imagery Using Spatially Regularized Symmetric Positives-Definite Matrices Based Classification

Electroencephalogram (EEG) based motor imagery brain⁻computer interface (BCI) requires large number of subject specific training trials to calibrate the system for a new subject. This results in long calibration time that limits the BCI usage in practice. One major challenge in the development of a brain⁻computer interface is to reduce calibration time or completely eliminate it. To address this problem, existing approaches use covariance matrices of electroencephalography (EEG) trials as descriptors for decoding BCI but do not consider the geometry of the covariance matrices, which lies in the space of Symmetric Positive Definite (SPD) matrices. This inevitably limits their performance. We focus on reducing calibration time by introducing SPD based classification approach. However, SPD-based classification has limited applicability in small training sets because the dimensionality of covariance matrices is large in proportion to the number of trials. To overcome this drawback, our paper proposes a new framework that transforms SPD matrices in lower dimension through spatial filter regularized by prior information of EEG channels. The efficacy of the proposed approach was validated on the small sample scenario through Dataset IVa from BCI Competition III. The proposed approach achieved mean accuracy of 86.13 % and mean kappa of 0.72 on Dataset IVa. The proposed method outperformed other approaches in existing studies on Dataset IVa. Finally, to ensure the robustness of the proposed method, we evaluated it on Dataset IIIa from BCI Competition III and Dataset IIa from BCI Competition IV. The proposed method achieved mean accuracy 92.22 % and 81.21 % on Dataset IIIa and Dataset IIa, respectively.

Learning Discriminative Spatiospectral Features of ERPs for Accurate Brain-Computer Interfaces

Constructing accurate predictive models is at the heart of brain-computer interfaces (BCIs) because these models can ultimately translate brain activities into communication and control commands. The majority of the previous work in BCI use spatial, temporal, or spatiotemporal features of event-related potentials (ERPs). In this study, we examined the discriminatory effect of their spatiospectral features to capture the most relevant set of neural activities from electroencephalographic recordings that represent users' mental intent. In this regard, we model ERP waveforms using a sum of sinusoids with unknown amplitudes, frequencies, and phases. The effect of this signal modeling step is to represent high-dimensional ERP waveforms in a substantially lower dimensionality space, which includes their dominant power spectral contents. We found that the most discriminative frequencies for accurate decoding of visual attention modulated ERPs lie in a spectral range less than 6.4 Hz. This was empirically verified by treating dominant frequency contents of ERP waveforms as feature vectors in the state-of-the-art machine learning techniques used herein. The constructed predictive models achieved remarkable performance, which for some subjects was as high as 94% as measured by the area under curve. Using these spectral contents, we further studied the discriminatory effect of each channel and proposed an efficient strategy to choose subject-specific subsets of channels that generally led to classifiers with comparable performance.

Tactile Stimulation Improves Sensorimotor Rhythm-based BCI Performance in Stroke Patients

OBJECTIVE

BCI decoding accuracy plays a crucial role in practical applications. With accurate feedback, BCI-based therapy determines beneficial neural plasticity in stroke patients. In this study, we aimed at improving sensorimotor rhythm (SMR)-based BCI performance by integrating motor tasks with tactile stimulation.

METHODS

Eleven stroke patients were recruited for three experimental conditions, i.e., motor attempt (MA) condition, tactile stimulation (TS) condition, and tactile stimulation-assisted motor attempt (TS-MA) condition. Tactile stimulation was delivered to the paretic hand wrist during both task and idle states using a DC vibrator.

RESULTS

We observed that the TS-MA condition achieved greater motor-related cortical activation (MRCA) in alpha-beta band when compared with both TS and MA conditions. Consequently, online BCI decoding accuracies between task and idle states were significantly improved from 74.5% in the MA condition to 85.1% in the TS-MA condition (p < 0.001), whereas the accuracy in the TS condition was 54.6% (approaching to the chance level of 50%).

CONCLUSION

This finding demonstrates that sensory afferent from peripheral nerves benefits the neural process of sensorimotor cortex in stroke patients. With appropriate sensory stimulation, MRCA is enhanced and corresponding brain patterns are more discriminative.

SIGNIFICANCE

This novel SMR-BCI paradigm shows great promise to facilitate the practical application of BCI-based stroke rehabilitation.

HD-EEG Based Classification of Motor-Imagery Related Activity in Patients With Spinal Cord Injury

Brain computer interfaces (BCIs) are thought to revolutionize rehabilitation after SCI, e.g., by controlling neuroprostheses, exoskeletons, functional electrical stimulation, or a combination of these components. However, most BCI research was performed in healthy volunteers and it is unknown whether these results can be translated to patients with spinal cord injury because of neuroplasticity. We sought to examine whether high-density EEG (HD-EEG) could improve the performance of motor-imagery classification in patients with SCI. We recorded HD-EEG with 256 channels in 22 healthy controls and 7 patients with 14 recordings (4 patients had more than one recording) in an event related design. Participants were instructed acoustically to either imagine, execute, or observe foot and hand movements, or to rest. We calculated Fast Fourier Transform (FFT) and full frequency directed transfer function (ffDTF) for each condition and classified conditions pairwise with support vector machines when using only 2 channels over the sensorimotor area, full 10-20 montage, high-density montage of the sensorimotor cortex, and full HD-montage. Classification accuracies were comparable between patients and controls, with an advantage for controls for classifications that involved the foot movement condition. Full montages led to better results for both groups (p < 0.001), and classification accuracies were higher for FFT than for ffDTF (p < 0.001), for which the feature vector might be too long. However, full-montage 10–20 montage was comparable to high-density configurations. Motor-imagery driven control of neuroprostheses or BCI systems may perform as well in patients as in healthy volunteers with adequate technical configuration. We suggest the use of a whole-head montage and analysis of a broad frequency range.

An Automatic Channel Selection Approach for ICA-Based Motor Imagery Brain Computer Interface

Independent component analysis (ICA) is a potential spatial filtering method for the implementation of motor imagery brain-computer interface (MIBCI). However, ICA-based MIBCI (ICA-MIBCI) is sensitive to electroencephalogram (EEG) channels and the quality of the training data, which are two crucial factors affecting the stability and classification performance of ICA-MIBCI. To address these problems, this paper is mainly focused on the investigation of EEG channel optimization. As a reference, we constructed a single-trial-based ICA-MIBCI system with commonly used channels and common spatial pattern-based MIBCI (CSP-MIBCI). To minimize the impact of artifacts on EEG channel optimization, a data-quality evaluation method, named "self-testing" in this paper, was used in a single-trial-based ICA-MIBCI system to evaluate the quality of single trials in each dataset; the resulting self-testing accuracies were used for the selection of high-quality trials. Given several candidate channel configurations, ICA filters were calculated using selected high-quality trials and applied to the corresponding ICA-MIBCI implementation. Optimal channels for each dataset were assessed and selected according to the self-testing results related to various candidate configurations. Forty-eight MI datasets of six subjects were employed in this study to validate the proposed methods. Experimental results revealed that the average classification accuracy of the optimal channels yielded a relative increment of 2.8% and 8.5% during self-testing, 14.4% and 9.5% during session-to-session transfer, and 36.2% and 26.7% during subject-to-subject transfer compared to CSP-MIBCI and ICA-MIBCI with fixed the channel configuration. This work indicates that the proposed methods can efficiently improve the practical feasibility of ICA-MIBCI.

Learning Temporal Information for Brain-Computer Interface Using Convolutional Neural Networks

Deep learning (DL) methods and architectures have been the state-of-the-art classification algorithms for computer vision and natural language processing problems. However, the successful application of these methods in motor imagery (MI) brain-computer interfaces (BCIs), in order to boost classification performance, is still limited. In this paper, we propose a classification framework for MI data by introducing a new temporal representation of the data and also utilizing a convolutional neural network (CNN) architecture for classification. The new representation is generated from modifying the filter-bank common spatial patterns method, and the CNN is designed and optimized accordingly for the representation. Our framework outperforms the best classification method in the literature on the BCI competition IV-2a 4-class MI data set by 7% increase in average subject accuracy. Furthermore, by studying the convolutional weights of the trained networks, we gain an insight into the temporal characteristics of EEG.

Decoding Steady-State Visual Evoked Potentials From Electrocorticography

We report on a unique electrocorticography (ECoG) experiment in which Steady-State Visual Evoked Potentials (SSVEPs) to frequency- and phase-tagged stimuli were recorded from a large subdural grid covering the entire right occipital cortex of a human subject. The paradigm is popular in EEG-based Brain Computer Interfacing where selectable targets are encoded by different frequency- and/or phase-tagged stimuli. We compare the performance of two state-of-the-art SSVEP decoders on both ECoG- and scalp-recorded EEG signals, and show that ECoG-based decoding is more accurate for very short stimulation lengths (i.e., less than 1 s). Furthermore, whereas the accuracy of scalp-EEG decoding benefits from a multi-electrode approach, to address interfering EEG responses and noise, ECoG decoding enjoys only a marginal improvement as even a single electrode, placed over the posterior part of the primary visual cortex, seems to suffice. This study shows, for the first time, that EEG-based SSVEP decoders can in principle be applied to ECoG, and can be expected to yield faster decoding speeds using less electrodes.

Using brain connectivity metrics from synchrostates to perform motor imagery classification in EEG-based BCI systems

Phase synchronisation between different neural groups is considered an important source of information to understand the underlying mechanisms of brain cognition. This Letter investigated phase-synchronisation patterns from electroencephalogram (EEG) signals recorded from ten healthy participants performing motor imagery (MI) tasks using schematic emotional faces as stimuli. These phase-synchronised states, named synchrostates, are specific for each cognitive task performed by the user. The maximum and minimum number of occurrence states were selected for each subject and task to extract the connectivity network measures based on graph theory to feed a set of classification algorithms. Two MI tasks were successfully classified with the highest accuracy of 85% with corresponding sensitivity and specificity of 85%. In this work, not only the performance of different supervised learning techniques was studied, as well as the optimal subset of features to obtain the best discrimination rates. The robustness of this classification method for MI tasks indicates the possibility of expanding its use for online classification of the brain-computer interface (BCI) systems.

Improving Generalization Based on l1-Norm Regularization for EEG-Based Motor Imagery Classification

Multichannel electroencephalography (EEG) is widely used in typical brain-computer interface (BCI) systems. In general, a number of parameters are essential for a EEG classification algorithm due to redundant features involved in EEG signals. However, the generalization of the EEG method is often adversely affected by the model complexity, considerably coherent with its number of undetermined parameters, further leading to heavy overfitting. To decrease the complexity and improve the generalization of EEG method, we present a novel l₁-norm-based approach to combine the decision value obtained from each EEG channel directly. By extracting the information from different channels on independent frequency bands (FB) with l1-norm regularization, the method proposed fits the training data with much less parameters compared to common spatial pattern (CSP) methods in order to reduce overfitting. Moreover, an effective and efficient solution to minimize the optimization object is proposed. The experimental results on dataset IVa of BCI competition III and dataset I of BCI competition IV show that, the proposed method contributes to high classification accuracy and increases generalization performance for the classification of MI EEG. As the training set ratio decreases from 80 to 20%, the average classification accuracy on the two datasets changes from 85.86 and 86.13% to 84.81 and 76.59%, respectively. The classification performance and generalization of the proposed method contribute to the practical application of MI based BCI systems.

Sparse Group Representation Model for Motor Imagery EEG Classification

A potential limitation of a motor imagery (MI) based brain-computer interface (BCI) is that it usually requires a relatively long time to record sufficient electroencephalogram (EEG) data for robust classifier training. The calibration burden during data acquisition phase will most probably cause a subject to be reluctant to use a BCI system. To alleviate this issue, we propose a novel sparse group representation model (SGRM) for improving the efficiency of MI-based BCI by exploiting the intersubject information. Specifically, preceded by feature extraction using common spatial pattern, a composite dictionary matrix is constructed with training samples from both the target subject and other subjects. By explicitly exploiting within-group sparse and group-wise sparse constraints, the most compact representation of a test sample of the target subject is then estimated as a linear combination of columns in the dictionary matrix. Classification is implemented by calculating the class-specific representation residual based on the significant training samples corresponding to the nonzero representation coefficients. Accordingly, the proposed SGRM method effectively reduces the required training samples from the target subject due to auxiliary data available from other subjects. With two public EEG data sets, extensive experimental comparisons are carried out between SGRM and other state-of-the-art approaches. Superior classification performance of our method using 40 trials of the target subject for model calibration (Averaged accuracy = 78.2%, Kappa = 0.57 and Averaged accuracy = 77.7%, Kappa = 0.55 for the two data sets, respectively) indicates its promising potential for improving the practicality of MI-based BCI.

A Study of the Effects of Electrode Number and Decoding Algorithm on Online EEG-Based BCI Behavioral Performance

Motor imagery–based brain–computer interface (BCI) using electroencephalography (EEG) has demonstrated promising applications by directly decoding users' movement related mental intention. The selection of control signals, e.g., the channel configuration and decoding algorithm, plays a vital role in the online performance and progressing of BCI control. While several offline analyses report the effect of these factors on BCI accuracy for a single session—performance increases asymptotically by increasing the number of channels, saturates, and then decreases—no online study, to the best of our knowledge, has yet been performed to compare for a single session or across training. The purpose of the current study is to assess, in a group of forty-five subjects, the effect of channel number and decoding method on the progression of BCI performance across multiple training sessions and the corresponding neurophysiological changes. The 45 subjects were divided into three groups using Laplacian Filtering (LAP/S) with nine channels, Common Spatial Pattern (CSP/L) with 40 channels and CSP (CSP/S) with nine channels for online decoding. At the first training session, subjects using CSP/L displayed no significant difference compared to CSP/S but a higher average BCI performance over those using LAP/S. Despite the average performance when using the LAP/S method was initially lower, but LAP/S displayed improvement over first three sessions, whereas the other two groups did not. Additionally, analysis of the recorded EEG during BCI control indicates that the LAP/S produces control signals that are more strongly correlated with the target location and a higher R-square value was shown at the fifth session. In the present study, we found that subjects' average online BCI performance using a large EEG montage does not show significantly better performance after the first session than a smaller montage comprised of a common subset of these electrodes. The LAP/S method with a small EEG montage allowed the subjects to improve their skills across sessions, but no improvement was shown for the CSP method.

Using Recent BCI Literature to Deepen our Understanding of Clinical Neurofeedback: A Short Review

In their recent paper, Alkoby et al. (2017) provide the readership with an extensive and very insightful review of the factors influencing NeuroFeedback (NF) performance. These factors are drawn from both the NF literature and the Brain-Computer Interface (BCI) literature. Our short review aims to complement Alkoby et al.'s review by reporting recent additions to the BCI literature. The object of this paper is to highlight this literature and discuss its potential relevance and usefulness to better understand the processes underlying NF and further improve the design of clinical trials assessing NF efficacy. Indeed, we are convinced that while NF and BCI are fundamentally different in many ways, both the BCI and NF communities could reach compelling achievements by building upon one another. By reviewing the recent BCI literature, we identified three types of factors that influence BCI performance: task-specific, cognitive/motivational and technology-acceptance-related factors. Since BCIs and NF share a common goal (i.e., learning to modulate specific neurophysiological patterns), similar cognitive and neurophysiological processes are likely to be involved during the training process. Thus, the literature on BCI training may help (1) to deepen our understanding of neurofeedback training processes and (2) to understand the variables that influence the clinical efficacy of NF. This may help to properly assess and/or control the influence of these variables during randomized controlled trials.

Information Theoretic Approaches for Motor-Imagery BCI Systems: Review and Experimental Comparison

Brain computer interfaces (BCIs) have been attracting a great interest in recent years. The common spatial patterns (CSP) technique is a well-established approach to the spatial filtering of the electroencephalogram (EEG) data in BCI applications. Even though CSP was originally proposed from a heuristic viewpoint, it can be also built on very strong foundations using information theory. This paper reviews the relationship between CSP and several information-theoretic approaches, including the Kullback-Leibler divergence, the Beta divergence and the Alpha-Beta log-det (AB-LD)divergence. We also revise other approaches based on the idea of selecting those features that are maximally informative about the class labels. The performance of all the methods will be also compared via experiments.

Spatiotemporal Beamforming: A Transparent and Unified Decoding Approach to Synchronous Visual Brain-Computer Interfacing

Brain-Computer Interfaces (BCIs) decode brain activity with the aim to establish a direct communication channel with an external device. Albeit they have been hailed to (re-)establish communication in persons suffering from severe motor- and/or communication disabilities, only recently BCI applications have been challenging other assistive technologies. Owing to their considerably increased performance and the advent of affordable technological solutions, BCI technology is expected to trigger a paradigm shift not only in assistive technology but also in the way we will interface with technology. However, the flipside of the quest for accuracy and speed is most evident in EEG-based visual BCI where it has led to a gamut of increasingly complex classifiers, tailored to the needs of specific stimulation paradigms and use contexts. In this contribution, we argue that spatiotemporal beamforming can serve several synchronous visual BCI paradigms. We demonstrate this for three popular visual paradigms even without attempting to optimizing their electrode sets. For each selectable target, a spatiotemporal beamformer is applied to assess whether the corresponding signal-of-interest is present in the preprocessed multichannel EEG signals. The target with the highest beamformer output is then selected by the decoder (maximum selection). In addition to this simple selection rule, we also investigated whether interactions between beamformer outputs could be employed to increase accuracy by combining the outputs for all targets into a feature vector and applying three common classification algorithms. The results show that the accuracy of spatiotemporal beamforming with maximum selection is at par with that of the classification algorithms and interactions between beamformer outputs do not further improve that accuracy.

Electrode channel selection based on backtracking search optimization in motor imagery brain-computer interfaces

Common spatial pattern algorithm is widely used to estimate spatial filters in motor imagery based brain-computer interfaces. However, use of a large number of channels will make common spatial pattern tend to over-fitting and the classification of electroencephalographic signals time-consuming. To overcome these problems, it is necessary to choose an optimal subset of the whole channels to save computational time and improve the classification accuracy. In this paper, a novel method named backtracking search optimization algorithm is proposed to automatically select the optimal channel set for common spatial pattern. Each individual in the population is a N-dimensional vector, with each component representing one channel. A population of binary codes generate randomly in the beginning, and then channels are selected according to the evolution of these codes. The number and positions of 1's in the code denote the number and positions of chosen channels. The objective function of backtracking search optimization algorithm is defined as the combination of classification error rate and relative number of channels. Experimental results suggest that higher classification accuracy can be achieved with much fewer channels compared to standard common spatial pattern with whole channels.

Efficient Hardware Implementation of Real-Time Low-Power Movement Intention Detector System Using FFT and Adaptive Wavelet Transform

The brain-computer interfacing (BCI), a platform to extract features and classify different motor movement tasks from noisy and highly correlated electroencephalogram signals, is limited mostly by the complex and power-hungry algorithms. Among different techniques recently devised to tackle this issue, real-time onset detection, due to its negligible delay and minimal power overhead, is the most efficient one. Here, we propose a novel algorithm that outperforms the state-of-the-art design by sixfold in terms of speed, without sacrificing the accuracy for a real-time, hand movement intention detection based on the adaptive wavelet transform with only 1 s detection delay and maximum sensitivity of 88% and selectivity of 78% (only 7% loss of sensitivity).

An improved P300 pattern in BCI to catch user's attention

OBJECTIVE

Brain-computer interfaces (BCIs) can help patients who have lost control over most muscles but are still conscious and able to communicate or interact with the environment. One of the most popular types of BCI is the P300-based BCI. With this BCI, users are asked to count the number of appearances of target stimuli in an experiment. To date, the majority of visual P300-based BCI systems developed have used the same character or picture as the target for every stimulus presentation, which can bore users. Consequently, users attention may decrease or be negatively affected by adjacent stimuli.

APPROACH

In this study, a new stimulus is presented to increase user concentration. Honeycomb-shaped figures with 1-3 red dots were used as stimuli. The number and the positions of the red dots in the honeycomb-shaped figure were randomly changed during BCI control. The user was asked to count the number of the dots presented in each flash instead of the number of times they flashed. To assess the performance of this new stimulus, another honeycomb-shaped stimulus, without red dots, was used as a control condition.

MAIN RESULTS

The results showed that the honeycomb-shaped stimuli with red dots obtained significantly higher classification accuracies and information transfer rates (p  <  0.05) compared to the honeycomb-shaped stimulus without red dots.

SIGNIFICANCE

The results indicate that this proposed method can be a promising approach to improve the performance of the BCI system and can be an efficient method in daily application.

Enhanced inter-subject brain computer interface with associative sensorimotor oscillations

Electroencephalography (EEG) captures electrophysiological signatures of cortical events from the scalp with high-dimensional electrode montages. Usually, excessive sources produce outliers and potentially affect the actual event related sources. Besides, EEG manifests inherent inter-subject variability of the brain dynamics, at the resting state and/or under the performance of task(s), caused probably due to the instantaneous fluctuation of psychophysiological states. A wavelet coherence (WC) analysis for optimally selecting associative inter-subject channels is proposed here and is being used to boost performances of motor imagery (MI)-based inter-subject brain computer interface (BCI). The underlying hypothesis is that optimally associative inter-subject channels can reduce the effects of outliers and, thus, eliminate dissimilar cortical patterns. The proposed approach has been tested on the dataset IVa from BCI competition III, including EEG data acquired from five healthy subjects who were given visual cues to perform 280 trials of MI for the right hand and right foot. Experimental results have shown increased classification accuracy (81.79%) using the WC-based selected 16 channels compared to the one (56.79%) achieved using all the available 118 channels. The associative channels lie mostly around the sensorimotor regions of the brain, reinforced by the previous literature, describing spatial brain dynamics during sensorimotor oscillations. Apparently, the proposed approach paves the way for optimised EEG channel selection that could boost further the efficiency and real-time performance of BCI systems.

Sparse Bayesian Classification of EEG for Brain-Computer Interface

Regularization has been one of the most popular approaches to prevent overfitting in electroencephalogram (EEG) classification of brain-computer interfaces (BCIs). The effectiveness of regularization is often highly dependent on the selection of regularization parameters that are typically determined by cross-validation (CV). However, the CV imposes two main limitations on BCIs: 1) a large amount of training data is required from the user and 2) it takes a relatively long time to calibrate the classifier. These limitations substantially deteriorate the system's practicability and may cause a user to be reluctant to use BCIs. In this paper, we introduce a sparse Bayesian method by exploiting Laplace priors, namely, SBLaplace, for EEG classification. A sparse discriminant vector is learned with a Laplace prior in a hierarchical fashion under a Bayesian evidence framework. All required model parameters are automatically estimated from training data without the need of CV. Extensive comparisons are carried out between the SBLaplace algorithm and several other competing methods based on two EEG data sets. The experimental results demonstrate that the SBLaplace algorithm achieves better overall performance than the competing algorithms for EEG classification.

ReliefF-Based EEG Sensor Selection Methods for Emotion Recognition

Electroencephalogram (EEG) signals recorded from sensor electrodes on the scalp can directly detect the brain dynamics in response to different emotional states. Emotion recognition from EEG signals has attracted broad attention, partly due to the rapid development of wearable computing and the needs of a more immersive human-computer interface (HCI) environment. To improve the recognition performance, multi-channel EEG signals are usually used. A large set of EEG sensor channels will add to the computational complexity and cause users inconvenience. ReliefF-based channel selection methods were systematically investigated for EEG-based emotion recognition on a database for emotion analysis using physiological signals (DEAP). Three strategies were employed to select the best channels in classifying four emotional states (joy, fear, sadness and relaxation). Furthermore, support vector machine (SVM) was used as a classifier to validate the performance of the channel selection results. The experimental results showed the effectiveness of our methods and the comparison with the similar strategies, based on the F-score, was given. Strategies to evaluate a channel as a unity gave better performance in channel reduction with an acceptable loss of accuracy. In the third strategy, after adjusting channels’ weights according to their contribution to the classification accuracy, the number of channels was reduced to eight with a slight loss of accuracy (58.51% ± 10.05% versus the best classification accuracy 59.13% ± 11.00% using 19 channels). In addition, the study of selecting subject-independent channels, related to emotion processing, was also implemented. The sensors, selected subject-independently from frontal, parietal lobes, have been identified to provide more discriminative information associated with emotion processing, and are distributed symmetrically over the scalp, which is consistent with the existing literature. The results will make a contribution to the realization of a practical EEG-based emotion recognition system.

Discriminative channel addition and reduction for filter bank common spatial pattern in motor imagery BCI

An electroencephalography (EEG)-based Motor Imagery Brain-Computer Interface (MI-BCI) requires a long setup time if a large number of channels is used, and EEG from noisy or irrelevant channels may adversely affect the classification performance. To address this issue, this paper proposed 2 approaches to systematically select discriminative channels for EEG-based MI-BCI. The proposed Discriminative Channel Addition (DCA) approach and the Discriminative Channel Reduction (DCR) approach selects subject-specific discriminative channels by iteratively adding or removing channels based on the cross-validation classification accuracies obtained using the Filter Bank Common Spatial Pattern algorithm. The performances of the proposed approaches were evaluated on the BCI Competition IV Dataset 2a. The results on 2-class and 4-class MI data showed that DCA, which iteratively adds channels, selected 13~14 channels that consistently yielded better cross-validation accuracies on the training data and session-to-session transfer accuracies on the evaluation data compared to the use of a full 22-channel setup. Hence, this results in a reduced channel setup that could improve the classification accuracy of the MI-BCI after removing less discriminative channels.

Selection of effective EEG channels in brain computer interfaces based on inconsistencies of classifiers

This paper proposed a novel method to select the effective Electroencephalography (EEG) channels for the motor imagery tasks based on the inconsistencies from multiple classifiers. The inconsistency criterion for channel selection was designed based on the fluctuation of the classification accuracies among different classifiers when the noisy channels were included. These noisy channels were then identified and removed till a required number of channels was selected or a predefined classification accuracy with reference to baseline was obtained. Experiments conducted on a data set of 13 healthy subjects performing hand grasping and idle revealed that the EEG channels from the motor area were most frequently selected. Furthermore, the mean increases of 4.07%, 3.10% and 1.77% of the averaged accuracies in comparison with the four existing channel selection methods were achieved for the non-feedback, feedback and calibration sessions, respectively, by selecting as low as seven channels. These results further validated the effectiveness of our proposed method.

Multivariate analysis of single-sweep evoked brain potentials for pharmaco-electroencephalography

BACKGROUND AND AIMS

Current findings on altered evoked potentials (EPs) caused by morphine are based on common alterations for a group of subjects after drug administration. However, this ignores the analysis of individual responses, which may explain the clinical differences in efficacy. Therefore, we explored the individual responses to morphine in terms of the altered single-sweep characteristics in a placebo-controlled crossover study. To account for multifactorial mechanisms, several characteristics were assessed simultaneously by multivariate pattern analysis (MVPA).

METHODS

EPs were recorded from 62 channels and obtained before and after morphine and placebo administration during repeated electrical stimulations of the oesophagus in 12 healthy males. Additionally, the pain detection threshold was recorded to reflect the subjective analgesic effect in each subject. The characteristics of the sweeps were extracted by a multivariate matching pursuit algorithm with Gabor atoms implemented with a variable amplitude and constant phase across the sweeps. The single-sweep amplitudes were used as input to an MVPA algorithm to discriminate individual responses. The accuracy of the MVPA for each individual subject was used for correlation analysis of the analgesic effect.

RESULTS

The mean classification accuracy when discriminating pre- and posttreatment morphine responses was 72% (p = 0.01). The individual classification accuracy was positively correlated to the analgesic effect of morphine (p = 0.03). Furthermore, the 2 posttreatment responses were classified and validated by the classification of the 2 pretreatment responses (p = 0.001).

CONCLUSIONS

The alterations in the single-sweep EPs after morphine reflect the analgesic effect. The MVPA approach is a novel methodology for monitoring the individual efficacy of analgesics.

Sparse Bayesian Learning for Obtaining Sparsity of EEG Frequency Bands Based Feature Vectors in Motor Imagery Classification

Effective common spatial pattern (CSP) feature extraction for motor imagery (MI) electroencephalogram (EEG) recordings usually depends on the filter band selection to a large extent. Subband optimization has been suggested to enhance classification accuracy of MI. Accordingly, this study introduces a new method that implements sparse Bayesian learning of frequency bands (named SBLFB) from EEG for MI classification. CSP features are extracted on a set of signals that are generated by a filter bank with multiple overlapping subbands from raw EEG data. Sparse Bayesian learning is then exploited to implement selection of significant features with a linear discriminant criterion for classification. The effectiveness of SBLFB is demonstrated on the BCI Competition IV IIb dataset, in comparison with several other competing methods. Experimental results indicate that the SBLFB method is promising for development of an effective classifier to improve MI classification.

A Wearable Channel Selection-Based Brain-Computer Interface for Motor Imagery Detection

Motor imagery-based brain-computer interface (BCI) is a communication interface between an external machine and the brain. Many kinds of spatial filters are used in BCIs to enhance the electroencephalography (EEG) features related to motor imagery. The approach of channel selection, developed to reserve meaningful EEG channels, is also an important technique for the development of BCIs. However, current BCI systems require a conventional EEG machine and EEG electrodes with conductive gel to acquire multi-channel EEG signals and then transmit these EEG signals to the back-end computer to perform the approach of channel selection. This reduces the convenience of use in daily life and increases the limitations of BCI applications. In order to improve the above issues, a novel wearable channel selection-based brain-computer interface is proposed. Here, retractable comb-shaped active dry electrodes are designed to measure the EEG signals on a hairy site, without conductive gel. By the design of analog CAR spatial filters and the firmware of EEG acquisition module, the function of spatial filters could be performed without any calculation, and channel selection could be performed in the front-end device to improve the practicability of detecting motor imagery in the wearable EEG device directly or in commercial mobile phones or tablets, which may have relatively low system specifications. Finally, the performance of the proposed BCI is investigated, and the experimental results show that the proposed system is a good wearable BCI system prototype.

RSTFC: A Novel Algorithm for Spatio-Temporal Filtering and Classification of Single-Trial EEG

Learning optimal spatio-temporal filters is a key to feature extraction for single-trial electroencephalogram (EEG) classification. The challenges are controlling the complexity of the learning algorithm so as to alleviate the curse of dimensionality and attaining computational efficiency to facilitate online applications, e.g., brain-computer interfaces (BCIs). To tackle these barriers, this paper presents a novel algorithm, termed regularized spatio-temporal filtering and classification (RSTFC), for single-trial EEG classification. RSTFC consists of two modules. In the feature extraction module, an l2 -regularized algorithm is developed for supervised spatio-temporal filtering of the EEG signals. Unlike the existing supervised spatio-temporal filter optimization algorithms, the developed algorithm can simultaneously optimize spatial and high-order temporal filters in an eigenvalue decomposition framework and thus be implemented highly efficiently. In the classification module, a convex optimization algorithm for sparse Fisher linear discriminant analysis is proposed for simultaneous feature selection and classification of the typically high-dimensional spatio-temporally filtered signals. The effectiveness of RSTFC is demonstrated by comparing it with several state-of-the-arts methods on three brain-computer interface (BCI) competition data sets collected from 17 subjects. Results indicate that RSTFC yields significantly higher classification accuracies than the competing methods. This paper also discusses the advantage of optimizing channel-specific temporal filters over optimizing a temporal filter common to all channels.

A novel channel selection method for optimal classification in different motor imagery BCI paradigms

BACKGROUND

For sensorimotor rhythms based brain-computer interface (BCI) systems, classification of different motor imageries (MIs) remains a crucial problem. An important aspect is how many scalp electrodes (channels) should be used in order to reach optimal performance classifying motor imaginations. While the previous researches on channel selection mainly focus on MI tasks paradigms without feedback, the present work aims to investigate the optimal channel selection in MI tasks paradigms with real-time feedback (two-class control and four-class control paradigms).

METHODS

In the present study, three datasets respectively recorded from MI tasks experiment, two-class control and four-class control experiments were analyzed offline. Multiple frequency-spatial synthesized features were comprehensively extracted from every channel, and a new enhanced method IterRelCen was proposed to perform channel selection. IterRelCen was constructed based on Relief algorithm, but was enhanced from two aspects: change of target sample selection strategy and adoption of the idea of iterative computation, and thus performed more robust in feature selection. Finally, a multiclass support vector machine was applied as the classifier. The least number of channels that yield the best classification accuracy were considered as the optimal channels. One-way ANOVA was employed to test the significance of performance improvement among using optimal channels, all the channels and three typical MI channels (C3, C4, Cz).

RESULTS

The results show that the proposed method outperformed other channel selection methods by achieving average classification accuracies of 85.2, 94.1, and 83.2 % for the three datasets, respectively. Moreover, the channel selection results reveal that the average numbers of optimal channels were significantly different among the three MI paradigms.

CONCLUSIONS

It is demonstrated that IterRelCen has a strong ability for feature selection. In addition, the results have shown that the numbers of optimal channels in the three different motor imagery BCI paradigms are distinct. From a MI task paradigm, to a two-class control paradigm, and to a four-class control paradigm, the number of required channels for optimizing the classification accuracy increased. These findings may provide useful information to optimize EEG based BCI systems, and further improve the performance of noninvasive BCI.

Classification of brain signals associated with imagination of hand grasping, opening and reaching by means of wavelet-based common spatial pattern and mutual information

An important issue in designing a practical brain-computer interface (BCI) is the selection of mental tasks to be imagined. Different types of mental tasks have been used in BCI including left, right, foot, and tongue motor imageries. However, the mental tasks are different from the actions to be controlled by the BCI. It is desirable to select a mental task to be consistent with the desired action to be performed by BCI. In this paper, we investigated the detecting the imagination of the hand grasping, hand opening, and hand reaching in one hand using electroencephalographic (EEG) signals. The results show that the ERD/ERS patterns, associated with the imagination of hand grasping, opening, and reaching are different. For classification of brain signals associated with these mental tasks and feature extraction, a method based on wavelet packet, regularized common spatial pattern (CSP), and mutual information is proposed. The results of an offline analysis on five subjects show that the two-class mental tasks can be classified with an average accuracy of 77.6% using proposed method. In addition, we examine the proposed method on datasets IVa from BCI Competition III and IIa from BCI Competition IV.

Optimizing spatial patterns with sparse filter bands for motor-imagery based brain-computer interface

BACKGROUND

Common spatial pattern (CSP) has been most popularly applied to motor-imagery (MI) feature extraction for classification in brain-computer interface (BCI) application. Successful application of CSP depends on the filter band selection to a large degree. However, the most proper band is typically subject-specific and can hardly be determined manually.

NEW METHOD

This study proposes a sparse filter band common spatial pattern (SFBCSP) for optimizing the spatial patterns. SFBCSP estimates CSP features on multiple signals that are filtered from raw EEG data at a set of overlapping bands. The filter bands that result in significant CSP features are then selected in a supervised way by exploiting sparse regression. A support vector machine (SVM) is implemented on the selected features for MI classification.

RESULTS

Two public EEG datasets (BCI Competition III dataset IVa and BCI Competition IV IIb) are used to validate the proposed SFBCSP method. Experimental results demonstrate that SFBCSP help improve the classification performance of MI.

COMPARISON WITH EXISTING METHODS

The optimized spatial patterns by SFBCSP give overall better MI classification accuracy in comparison with several competing methods.

CONCLUSIONS

The proposed SFBCSP is a potential method for improving the performance of MI-based BCI.