Task Transfer Learning for EEG Classification in Motor Imagery-Based BCI System.

The motor-imagery brain-computer interface system (MI-BCI) has a board prospect for development. However, long calibration time and lack of enough MI commands limit its use in practice. In order to enlarge the command set, we add the combinations of traditional MI commands as new commands into the command set. We also design an algorithm based on transfer learning so as to decrease the calibration time for collecting EEG signal and training model. We create feature extractor based on data from traditional commands and transfer patterns through the data from new commands. Through the comparison of the average accuracy between our algorithm and traditional algorithms and the visualization of spatial patterns in our algorithm, we find that the accuracy of our algorithm is much higher than traditional algorithms, especially as for the low-quality datasets. Besides, the visualization of spatial patterns is meaningful. The algorithm based on transfer learning takes the advantage of the information from source data. We enlarge the command set while shortening the calibration time, which is of significant importance to the MI-BCI application.

Multi-class motor imagery EEG classification using collaborative representation-based semi-supervised extreme learning machine.

Both labeled and unlabeled data have been widely used in electroencephalographic (EEG)-based brain-computer interface (BCI). However, labeled EEG samples are generally scarce and expensive to collect, while unlabeled samples are considered to be abundant in real applications. Although the semi-supervised learning (SSL) allows us to utilize both labeled and unlabeled data to improve the classification performance as against supervised algorithms, it has been reported that unlabeled data occasionally undermine the performance of SSL in some cases. To overcome this challenge, we propose a collaborative representation-based semi-supervised extreme learning machine (CR-SSELM) algorithm to evaluate the risk of unlabeled samples by a new safety-control mechanism. Specifically, the ELM model is firstly used to predict unlabeled samples and then the collaborative representation (CR) approach is employed to reconstruct the unlabeled samples according to the obtained prediction results, from which the risk degree of unlabeled sample is defined. A risk-based regularization term is then constructed accordingly and embedded into the objective function of the SS-ELM. Experiments conducted on benchmark and EEG datasets demonstrate that the proposed method outperforms the ELM and SS-ELM algorithm. Moreover, the proposed CR-SSELM even offers the best performance while SS-ELM yields worse performance compared with its supervised counterpart (ELM). Graphical abstract This paper proposes a collaborative representation-based semi-supervised extreme learning machine (CR-SSELM) algorithm to evaluate the risk of unlabeled samples by a new safety-control mechanism. It is aim to solve the safety problem of SS-ELM method that SS-ELM yields worse performance than ELM. With the help of safety mechanism, the performance of our method is still better than supervised ELM method.

Modulation Effect of Acupuncture on Functional Brain Networks and Classification of Its Manipulation With EEG Signals.

Acupuncture manipulation is the key of Chinese medicine acupuncture therapy. In clinical practice, different acupuncture manipulations are required to achieve different therapeutic effects, which means it is crucial to distinguish different acupuncture manipulations. In this paper, we proposed a classification framework for different acupuncture manipulations, which employed the graph theory and machine learning method. Multichannel EEG signals evoked by acupuncture at "Zusanli" acupoint were recorded from healthy humans by two acupuncture manipulations: twirling-rotating (TR) and lifting-thrusting (LT). Phase locking value was used to estimate the phase synchronization of pair-wise EEG channels. It was found that acupunctured by TR manipulation exhibit significantly higher synchronization degree than acupunctured by LT manipulation. With the construction of functional brain network, the topological features of graph theory were extracted. Taken the network features as inputs, machine learning classifiers were established to classify acupuncture manipulations. The highest accuracy can achieve 92.14% with support vector machine. By further optimizing the network features utilized in machine learning classifiers, it was found that the combination of node betweenness and small world network index is the most effective factor for acupuncture manipulations classification. These findings suggested that our approach provides new ideas for automatically identify acupuncture manipulations from the perspective of functional brain networks and machine learning methods.

A BCI based visual-haptic neurofeedback training improves cortical activations and classification performance during motor imagery.

OBJECTIVE: We proposed a brain-computer interface (BCI) based visual-haptic neurofeedback training (NFT) by incorporating synchronous visual scene and proprioceptive electrical stimulation feedback. The goal of this work was to improve sensorimotor cortical activations and classification performance during motor imagery (MI). In addition, their correlations and brain network patterns were also investigated respectively. APPROACH: 64-channel electroencephalographic (EEG) data were recorded in nineteen healthy subjects during MI before and after NFT. During NFT sessions, the synchronous visual-haptic feedbacks were driven by real-time lateralized relative event-related desynchronization (lrERD). MAIN RESULTS: By comparison between previous and posterior control sessions, the cortical activations measured by multi-band (i.e. alpha_1: 8-10 Hz, alpha_2: 11-13 Hz, beta_1: 15-20 Hz and beta_2: 22-28 Hz) absolute ERD powers and lrERD patterns were significantly enhanced after the NFT. The classification performance was also significantly improved, achieving a ~9% improvement and reaching ~85% in mean classification accuracy from a relatively poor performance. Additionally, there were significant correlations between lrERD patterns and classification accuracies. The partial directed coherence based functional connectivity (FC) networks covering the sensorimotor area also showed an increase after the NFT. SIGNIFICANCE: These findings validate the feasibility of our proposed NFT to improve sensorimotor cortical activations and BCI performance during motor imagery. And it is promising to optimize conventional NFT manner and evaluate the effectiveness of motor training.

EEG signal based classification before and after combined Yoga and Sudarshan Kriya.

Nowadays, the style of living is restless and busy which has resulted in increased stress among many people. Stress causes various mental and health illness such as depression, anxiety, mood disorders, and aggressive behavior. Yoga and Sudarshan Kriya (SK) meditation are healthy ways to eradicate stress from people's lives. Based on the previous study, it has been analyzed that SK practice helps to enhance relaxation, management of emotion, alertness, focus, and antidepressant effect. In this paper, the combined impact of yoga and SK meditation has been analyzed on brain signals by using statistical parameters. To the best of the authors' knowledge, no such study has been conducted in the past. In this study, the pre and post Electroencephalogram (EEG) signals were captured from the control and study group before and after three months regular practice of combined yoga and SK. Discrete Wavelet Transform (DWT) has been used to decompose the signal into 6 sub-bands (0-4, 4-8, 8-16, 16-32, 32-64, 64-128) hertz (Hz) by using db4 wavelet for analysis, statistical features such as variance, standard deviation, kurtosis, zero crossing, maximum and minimum have been calculated from each sub-band. The obtained parameters have been validated by using Kruskal-Wallis statistical test. Further, Artificial Neural Network (ANN) has been applied on aforementioned statistical parameters to classify subjects as meditators and non-meditators. The experimental results indicated that the proposed method achieved 87.2% accuracy for classification and could be further extended to construct an accurate classification system for detection of meditators and non-meditators. This study forms a scientific foundation to encourage the use of meditation in clinical practices.

Improvement Motor Imagery EEG Classification Based on Regularized Linear Discriminant Analysis.

Mental tasks classification such as motor imagery, based on EEG signals is an important problem in brain computer interface systems (BCI). One of the major concerns in BCI is to have a high classification accuracy. The other concerning one is with the favorable result is guaranteed how to improve the computational efficiency. In this paper, Mu/Beta rhythm was obtained by bandpass filter from EEG signal. And the classical linear discriminant analysis (LDA) was used for deciding which rhythm can give the better classification performance. During this, the common spatial pattern (CSP) was used to project data subject to the ratio of projected energy of one class to that of the other class was maximized. The optimal projection dimension was determined corresponding to the maximum of area under the curve (AUC) for each participant. Eventually, regularized linear discriminant analysis (RLDA) is possible to decode the imagined motor sensed using electroencephalogram (EEG). Results show that higher classification accuracy can be provided by RLDA. And optimal projection dimensions determined by LDA and RLDA are of consistent solution, this improves computational efficiency of CSP-RLDA method without computation of projection dimension.

Multiclass Support Matrix Machines by Maximizing the Inter-Class Margin for Single Trial EEG Classification.

Accurate classification of Electroencephalogram (EEG) signals plays an important role in diagnoses of different type of mental activities. One of the most important challenges, associated with classification of EEG signals is how to design an efficient classifier consisting of strong generalization capability. Aiming to improve the classification performance, in this paper, we propose a novel multiclass support matrix machine (M-SMM) from the perspective of maximizing the inter-class margins. The objective function is a combination of binary hinge loss that works on C matrices and spectral elastic net penalty as regularization term. This regularization term is a combination of Frobenius and nuclear norm, which promotes structural sparsity and shares similar sparsity patterns across multiple predictors. It also maximizes the inter-class margin that helps to deal with complex high dimensional noisy data. The extensive experiment results supported by theoretical analysis and statistical tests show the effectiveness of the M-SMM for solving the problem of classifying EEG signals associated with motor imagery in brain-computer interface applications.

Deep learning for electroencephalogram (EEG) classification tasks: a review.

OBJECTIVE: Electroencephalography (EEG) analysis has been an important tool in neuroscience with applications in neuroscience, neural engineering (e.g. Brain-computer interfaces, BCI's), and even commercial applications. Many of the analytical tools used in EEG studies have used machine learning to uncover relevant information for neural classification and neuroimaging. Recently, the availability of large EEG data sets and advances in machine learning have both led to the deployment of deep learning architectures, especially in the analysis of EEG signals and in understanding the information it may contain for brain functionality. The robust automatic classification of these signals is an important step towards making the use of EEG more practical in many applications and less reliant on trained professionals. Towards this goal, a systematic review of the literature on deep learning applications to EEG classification was performed to address the following critical questions: (1) Which EEG classification tasks have been explored with deep learning? (2) What input formulations have been used for training the deep networks? (3) Are there specific deep learning network structures suitable for specific types of tasks? APPROACH: A systematic literature review of EEG classification using deep learning was performed on Web of Science and PubMed databases, resulting in 90 identified studies. Those studies were analyzed based on type of task, EEG preprocessing methods, input type, and deep learning architecture. MAIN RESULTS: For EEG classification tasks, convolutional neural networks, recurrent neural networks, deep belief networks outperform stacked auto-encoders and multi-layer perceptron neural networks in classification accuracy. The tasks that used deep learning fell into five general groups: emotion recognition, motor imagery, mental workload, seizure detection, event related potential detection, and sleep scoring. For each type of task, we describe the specific input formulation, major characteristics, and end classifier recommendations found through this review. SIGNIFICANCE: This review summarizes the current practices and performance outcomes in the use of deep learning for EEG classification. Practical suggestions on the selection of many hyperparameters are provided in the hope that they will promote or guide the deployment of deep learning to EEG datasets in future research.

Towards optimal visual presentation design for hybrid EEG-fTCD brain-computer interfaces.

OBJECTIVE: In this paper, we introduce a novel hybrid brain-computer interface (BCI) system that measures electrical brain activity as well as cerebral blood velocity using electroencephalography (EEG) and functional transcranial Doppler ultrasound (fTCD) respectively in response to flickering mental rotation (MR) and flickering word generation (WG) cognitive tasks as well as a fixation cross that represents the baseline. This work extends our previous approach, in which we showed that motor imagery induces simultaneous changes in EEG and fTCD to enable task discrimination; and hence, provides a design approach for a hybrid BCI. Here, we show that instead of using motor imagery, the proposed visual stimulation technique enables the design of an EEG-fTCD based BCI with higher accuracy. APPROACH: Features based on the power spectrum of EEG and fTCD signals were calculated. Mutual information and support vector machines were used for feature selection and classification purposes. MAIN RESULTS: EEG-fTCD combination outperformed EEG by 4.05% accuracy for MR versus baseline problem and by 5.81% accuracy for WG versus baseline problem. An average accuracy of 92.38% was achieved for MR versus WG problem using the hybrid combination. Average transmission rates of 4.39, 3.92, and 5.60 bits min-1 were obtained for MR versus baseline, WG versus baseline, and MR versus WG problems respectively. SIGNIFICANCE: In terms of accuracy, the current visual presentation outperforms the motor imagery visual presentation we designed before for the EEG-fTCD system by 10% accuracy for task versus task problem. Moreover, the proposed system outperforms the state of the art hybrid EEG-fNIRS BCIs in terms of accuracy and/or information transfer rate. Even though there are still limitations of the proposed system, such promising results show that the proposed hybrid system is a feasible candidate for real-time BCIs.

Android Feedback-Based Training Modulates Sensorimotor Rhythms During Motor Imagery.

EEG-based brain computer interface (BCI) systems have demonstrated potential to assist patients with devastating motor paralysis conditions. However, there is great interest in shifting the BCI trend toward applications aimed at healthy users. Although BCI operation depends on technological factors (i.e., EEG pattern classification algorithm) and human factors (i.e., how well the person can generate good quality EEG patterns), it is the latter that is least investigated. In order to control a motor imagery-based BCI, users need to learn to modulate their sensorimotor brain rhythms by practicing motor imagery using a classical training protocol with an abstract visual feedback. In this paper, we investigate a different BCI training protocol using a human-like android robot (Geminoid HI-2) to provide realistic visual feedback. The proposed training protocol addresses deficiencies of the classical approach and takes the advantage of body-abled user capabilities. Experimental results suggest that android feedback-based BCI training improves the modulation of sensorimotor rhythms during motor imagery task. Moreover, we discuss how the influence of body ownership transfer illusion toward the android might have an effect on the modulation of event-related desynchronization/synchronization activity.

Is Implicit Motor Imagery a Reliable Strategy for a Brain-Computer Interface?

Explicit motor imagery (eMI) is a widely used brain-computer interface (BCI) paradigm, but not everybody can accomplish this task. Here, we propose a BCI based on implicit motor imagery (iMI). We compared classification accuracy between eMI and iMI of hands. Fifteen able-bodied people were asked to judge the laterality of hand images presented on a computer screen in a lateral or medial orientation. This judgment task is known to require mental rotation of a person's own hands, which in turn is thought to involve iMI. The subjects were also asked to perform eMI of the hands. Their electroencephalography was recorded. Linear classifiers were designed based on common spatial patterns. For discrimination between left hand and right hand, the classifier achieved maximum of 81 ± 8% accuracy for eMI and 83 ± 3% for iMI. These results show that iMI can be used to achieve similar classification accuracy as eMI. Additional classification was performed between iMI in medial and lateral orientations of a single hand; the classifier achieved 81 ± 7% for the left hand and 78 ± 7% for the right hand, which indicate distinctive spatial patterns of cortical activity for iMI of a single hand in different directions. These results suggest that a special BCI based on iMI may be constructed, for people who cannot perform explicit imagination, for rehabilitation of movement, or for treatment of bodily spatial neglect.

Classification of different reaching movements from the same limb using EEG.

OBJECTIVE: Brain-computer-interfaces (BCIs) have been proposed not only as assistive technologies but also as rehabilitation tools for lost functions. However, due to the stochastic nature, poor spatial resolution and signal to noise ratio from electroencephalography (EEG), multidimensional decoding has been the main obstacle to implement non-invasive BCIs in real-live rehabilitation scenarios. This study explores the classification of several functional reaching movements from the same limb using EEG oscillations in order to create a more versatile BCI for rehabilitation. APPROACH: Nine healthy participants performed four 3D center-out reaching tasks in four different sessions while wearing a passive robotic exoskeleton at their right upper limb. Kinematics data were acquired from the robotic exoskeleton. Multiclass extensions of Filter Bank Common Spatial Patterns (FBCSP) and a linear discriminant analysis (LDA) classifier were used to classify the EEG activity into four forward reaching movements (from a starting position towards four target positions), a backward movement (from any of the targets to the starting position and rest). Recalibrating the classifier using data from previous or the same session was also investigated and compared. MAIN RESULTS: Average EEG decoding accuracy were significantly above chance with 67%, 62.75%, and 50.3% when decoding three, four and six tasks from the same limb, respectively. Furthermore, classification accuracy could be increased when using data from the beginning of each session as training data to recalibrate the classifier. SIGNIFICANCE: Our results demonstrate that classification from several functional movements performed by the same limb is possible with acceptable accuracy using EEG oscillations, especially if data from the same session are used to recalibrate the classifier. Therefore, an ecologically valid decoding could be used to control assistive or rehabilitation mutli-degrees of freedom (DoF) robotic devices using EEG data. These results have important implications towards assistive and rehabilitative neuroprostheses control in paralyzed patients.

Pure visual imagery as a potential approach to achieve three classes of control for implementation of BCI in non-motor disorders.

OBJECTIVE: The achievement of multiple instances of control with the same type of mental strategy represents a way to improve flexibility of brain-computer interface (BCI) systems. Here we test the hypothesis that pure visual motion imagery of an external actuator can be used as a tool to achieve three classes of electroencephalographic (EEG) based control, which might be useful in attention disorders. APPROACH: We hypothesize that different numbers of imagined motion alternations lead to distinctive signals, as predicted by distinct motion patterns. Accordingly, a distinct number of alternating sensory/perceptual signals would lead to distinct neural responses as previously demonstrated using functional magnetic resonance imaging (fMRI). We anticipate that differential modulations should also be observed in the EEG domain. EEG recordings were obtained from twelve participants using three imagery tasks: imagery of a static dot, imagery of a dot with two opposing motions in the vertical axis (two motion directions) and imagery of a dot with four opposing motions in vertical or horizontal axes (four directions). The data were analysed offline. MAIN RESULTS: An increase of alpha-band power was found in frontal and central channels as a result of visual motion imagery tasks when compared with static dot imagery, in contrast with the expected posterior alpha decreases found during simple visual stimulation. The successful classification and discrimination between the three imagery tasks confirmed that three different classes of control based on visual motion imagery can be achieved. The classification approach was based on a support vector machine (SVM) and on the alpha-band relative spectral power of a small group of six frontal and central channels. Patterns of alpha activity, as captured by single-trial SVM closely reflected imagery properties, in particular the number of imagined motion alternations. SIGNIFICANCE: We found a new mental task based on visual motion imagery with potential for the implementation of multiclass (3) BCIs. Our results are consistent with the notion that frontal alpha synchronization is related with high internal processing demands, changing with the number of alternation levels during imagery. Together, these findings suggest the feasibility of pure visual motion imagery tasks as a strategy to achieve multiclass control systems with potential for BCI and in particular, neurofeedback applications in non-motor (attentional) disorders.

Vowel Imagery Decoding toward Silent Speech BCI Using Extreme Learning Machine with Electroencephalogram.

The purpose of this study is to classify EEG data on imagined speech in a single trial. We recorded EEG data while five subjects imagined different vowels, /a/, /e/, /i/, /o/, and /u/. We divided each single trial dataset into thirty segments and extracted features (mean, variance, standard deviation, and skewness) from all segments. To reduce the dimension of the feature vector, we applied a feature selection algorithm based on the sparse regression model. These features were classified using a support vector machine with a radial basis function kernel, an extreme learning machine, and two variants of an extreme learning machine with different kernels. Because each single trial consisted of thirty segments, our algorithm decided the label of the single trial by selecting the most frequent output among the outputs of the thirty segments. As a result, we observed that the extreme learning machine and its variants achieved better classification rates than the support vector machine with a radial basis function kernel and linear discrimination analysis. Thus, our results suggested that EEG responses to imagined speech could be successfully classified in a single trial using an extreme learning machine with a radial basis function and linear kernel. This study with classification of imagined speech might contribute to the development of silent speech BCI systems.

Does a Healing Procedure Referring to Theta Rhythms Also Generate Theta Rhythms in the Brain?

BACKGROUND/OBJECTIVES: ThetaHealing® (Vianna Stibal, Kalispell, MT) is a spiritual healing method in which the practitioner and client engage in joint meditations during several healing sessions. It is claimed that these meditation periods are characterized by a "theta state" in which the presence of theta-waves in the electroencephalograph (EEG) frequency spectrum of both the healer and the client is supposed. This study sought to test this hypothesis as well as the presence of synchronicities in the two EEGs. METHODS: Measurements were obtained with a dual EEG system with 2 × 32 channels, allowing for simultaneous EEG measurements of healer and client. Ten healers and 10 clients performed 10 ThetaHealing sessions while the EEG was measured. RESULTS: Theta frequency band did not increase in healers or in clients. Rather, the contrary was found, with a significant decrease in theta-2 band during healing in healers. Small correlations were seen between the Fourier amplitudes of healer and client in the theta-2 band, as well as small phase synchronicities in theta frequencies. CONCLUSION: The hypothesis that ThetaHealing is associated with an enhanced generation of theta frequencies in the brain could not be confirmed. This finding makes no claim about whether ThetaHealing is beneficial from a clinical perspective.

Optimal set of EEG features for emotional state classification and trajectory visualization in Parkinson's disease.

In addition to classic motor signs and symptoms, individuals with Parkinson's disease (PD) are characterized by emotional deficits. Ongoing brain activity can be recorded by electroencephalograph (EEG) to discover the links between emotional states and brain activity. This study utilized machine-learning algorithms to categorize emotional states in PD patients compared with healthy controls (HC) using EEG. Twenty non-demented PD patients and 20 healthy age-, gender-, and education level-matched controls viewed happiness, sadness, fear, anger, surprise, and disgust emotional stimuli while fourteen-channel EEG was being recorded. Multimodal stimulus (combination of audio and visual) was used to evoke the emotions. To classify the EEG-based emotional states and visualize the changes of emotional states over time, this paper compares four kinds of EEG features for emotional state classification and proposes an approach to track the trajectory of emotion changes with manifold learning. From the experimental results using our EEG data set, we found that (a) bispectrum feature is superior to other three kinds of features, namely power spectrum, wavelet packet and nonlinear dynamical analysis; (b) higher frequency bands (alpha, beta and gamma) play a more important role in emotion activities than lower frequency bands (delta and theta) in both groups and; (c) the trajectory of emotion changes can be visualized by reducing subject-independent features with manifold learning. This provides a promising way of implementing visualization of patient's emotional state in real time and leads to a practical system for noninvasive assessment of the emotional impairments associated with neurological disorders.

Decoding auditory attention to instruments in polyphonic music using single-trial EEG classification.

OBJECTIVE: Polyphonic music (music consisting of several instruments playing in parallel) is an intuitive way of embedding multiple information streams. The different instruments in a musical piece form concurrent information streams that seamlessly integrate into a coherent and hedonistically appealing entity. Here, we explore polyphonic music as a novel stimulation approach for use in a brain-computer interface. APPROACH: In a multi-streamed oddball experiment, we had participants shift selective attention to one out of three different instruments in music audio clips. Each instrument formed an oddball stream with its own specific standard stimuli (a repetitive musical pattern) and oddballs (deviating musical pattern). MAIN RESULTS: Contrasting attended versus unattended instruments, ERP analysis shows subject- and instrument-specific responses including P300 and early auditory components. The attended instrument can be classified offline with a mean accuracy of 91% across 11 participants. SIGNIFICANCE: This is a proof of concept that attention paid to a particular instrument in polyphonic music can be inferred from ongoing EEG, a finding that is potentially relevant for both brain-computer interface and music research.

Complexity and familiarity enhance single-trial detectability of imagined movements with electroencephalography.

OBJECTIVE: We sought to determine whether the sensorimotor rhythms (SMR) elicited during motor imagery (MI) of complex and familiar actions could be more reliably detected with electroencephalography (EEG), and subsequently classified on a single-trial basis, than those elicited during relatively simpler imagined actions. METHODS: Groups of healthy volunteers, including experienced pianists and ice hockey players, performed MI of varying complexity and familiarity. Their electroencephalograms were recorded and compared using brain-computer interface (BCI) approaches and spectral analyses. RESULTS: Relative to simple MI, significantly more participants produced classifiable SMR for complex MI. During MI of performance of a complex musical piece, the EEG of the experienced pianists was classified significantly more accurately than during MI of performance of a simpler musical piece. The accuracy of EEG classification was also significantly more sustained during complex MI. CONCLUSION: MI of complex actions results in EEG responses that are more reliably classified for more individuals than MI of relatively simpler actions, and familiarity with actions enhances these responses in some cases. SIGNIFICANCE: The accuracy of SMR-based BCIs in non-communicative patients may be improved by employing familiar and complex actions. Increased sensitivity to MI may also improve diagnostic accuracy for severely brain-injured patients in a vegetative state.

Automatic classification of artifactual ICA-components for artifact removal in EEG signals.

BACKGROUND: Artifacts contained in EEG recordings hamper both, the visual interpretation by experts as well as the algorithmic processing and analysis (e.g. for Brain-Computer Interfaces (BCI) or for Mental State Monitoring). While hand-optimized selection of source components derived from Independent Component Analysis (ICA) to clean EEG data is widespread, the field could greatly profit from automated solutions based on Machine Learning methods. Existing ICA-based removal strategies depend on explicit recordings of an individual's artifacts or have not been shown to reliably identify muscle artifacts. METHODS: We propose an automatic method for the classification of general artifactual source components. They are estimated by TDSEP, an ICA method that takes temporal correlations into account. The linear classifier is based on an optimized feature subset determined by a Linear Programming Machine (LPM). The subset is composed of features from the frequency-, the spatial- and temporal domain. A subject independent classifier was trained on 640 TDSEP components (reaction time (RT) study, n = 12) that were hand labeled by experts as artifactual or brain sources and tested on 1080 new components of RT data of the same study. Generalization was tested on new data from two studies (auditory Event Related Potential (ERP) paradigm, n = 18; motor imagery BCI paradigm, n = 80) that used data with different channel setups and from new subjects. RESULTS: Based on six features only, the optimized linear classifier performed on level with the inter-expert disagreement (<10% Mean Squared Error (MSE)) on the RT data. On data of the auditory ERP study, the same pre-calculated classifier generalized well and achieved 15% MSE. On data of the motor imagery paradigm, we demonstrate that the discriminant information used for BCI is preserved when removing up to 60% of the most artifactual source components. CONCLUSIONS: We propose a universal and efficient classifier of ICA components for the subject independent removal of artifacts from EEG data. Based on linear methods, it is applicable for different electrode placements and supports the introspection of results. Trained on expert ratings of large data sets, it is not restricted to the detection of eye- and muscle artifacts. Its performance and generalization ability is demonstrated on data of different EEG studies.

Application of nonlinear dynamics analysis in assessing unconsciousness: a preliminary study.

OBJECTIVES: To quantify the degree of unconsciousness with EEG nonlinear analysis and investigate the change of EEG nonlinear properties under different conditions. METHODS: Twenty-one subjects in persistent vegetative state (PVS), 16 in minimally conscious state (MCS) and 30 normal conscious subjects (control group) with brain trauma or stroke were involved in the study. EEG was recorded under three conditions: eyes closed, auditory stimuli and painful stimuli. EEG nonlinear indices such as Lempel-Ziv complexity (LZC), approximate entropy (ApEn) and cross-approximate entropy (cross-ApEn) were calculated for all the subjects. RESULTS: The PVS subjects had the lowest nonlinear indices followed by the MCS subjects and the control group had the highest. The PVS and MCS group had poorer response to auditory and painful stimuli than the control group. Under painful stimuli, nonlinear indices of subjects who recovered (REC) increased more significantly than non-REC subjects. CONCLUSIONS: With EEG nonlinear analysis, the degree of suppression for PVS and MCS could be quantified. The changes of brain function for unconscious subjects could be captured by EEG nonlinear analysis. SIGNIFICANCE: EEG nonlinear analysis could characterise the changes of brain function for unconscious state and might have some value in predicting prognosis of unconscious subjects.