BCI Competition 2003—Data Set Ia: Combining Gamma-Band Power With Slow Cortical Potentials to Improve Single-Trial Classification of Electroencephalographic Signals

An online hybrid BCI combining SSVEP and EOG-based eye movements

Hybrid brain-computer interface (hBCI) refers to a system composed of a single-modality BCI and another system. In this paper, we propose an online hybrid BCI combining steady-state visual evoked potential (SSVEP) and eye movements to improve the performance of BCI systems. Twenty buttons corresponding to 20 characters are evenly distributed in the five regions of the GUI and flash at the same time to arouse SSVEP. At the end of the flash, the buttons in the four regions move in different directions, and the subject continues to stare at the target with eyes to generate the corresponding eye movements. The CCA method and FBCCA method were used to detect SSVEP, and the electrooculography (EOG) waveform was used to detect eye movements. Based on the EOG features, this paper proposes a decision-making method based on SSVEP and EOG, which can further improve the performance of the hybrid BCI system. Ten healthy students took part in our experiment, and the average accuracy and information transfer rate of the system were 94.75% and 108.63 bits/min, respectively.

Poststroke Cognitive Impairment Research Progress on Application of Brain-Computer Interface

Brain-computer interfaces (BCIs), a new type of rehabilitation technology, pick up nerve cell signals, identify and classify their activities, and convert them into computer-recognized instructions. This technique has been widely used in the rehabilitation of stroke patients in recent years and appears to promote motor function recovery after stroke. At present, the application of BCI in poststroke cognitive impairment is increasing, which is a common complication that also affects the rehabilitation process. This paper reviews the promise and potential drawbacks of using BCI to treat poststroke cognitive impairment, providing a solid theoretical basis for the application of BCI in this area.

A novel approach of decoding EEG four-class motor imagery tasks via scout ESI and CNN

OBJECTIVE

To develop and implement a novel approach which combines the technique of scout EEG source imaging (ESI) with convolutional neural network (CNN) for the classification of motor imagery (MI) tasks.

APPROACH

The technique of ESI uses a boundary element method (BEM) and weighted minimum norm estimation (WMNE) to solve the EEG forward and inverse problems, respectively. Ten scouts are then created within the motor cortex to select the region of interest (ROI). We extract features from the time series of scouts using a Morlet wavelet approach. Lastly, CNN is employed for classifying MI tasks.

MAIN RESULTS

The overall mean accuracy on the Physionet database reaches 94.5% and the individual accuracy of each task reaches 95.3%, 93.3%, 93.6%, 96% for the left fist, right fist, both fists and both feet, correspondingly, validated using ten-fold cross validation. We report an increase of up to 14.4% for overall classification compared with the competitive results from the state-of-the-art MI classification methods. Then, we add four new subjects to verify the validity of the method and the overall mean accuracy is 92.5%. Furthermore, the global classifier was adapted to single subjects improving the overall mean accuracy to 94.54%.

SIGNIFICANCE

The combination of scout ESI and CNN enhances BCI performance of decoding EEG four-class MI tasks.

Hand, foot and lip representations in primary sensorimotor cortex: a high-density electroencephalography study

The primary sensorimotor cortex plays a major role in the execution of movements of the contralateral side of the body. The topographic representation of different body parts within this brain region is commonly investigated through functional magnetic resonance imaging (fMRI). However, fMRI does not provide direct information about neuronal activity. In this study, we used high-density electroencephalography (hdEEG) to map the representations of hand, foot, and lip movements in the primary sensorimotor cortex, and to study their neural signatures. Specifically, we assessed the event-related desynchronization (ERD) in the cortical space. We found that the performance of hand, foot, and lip movements elicited an ERD in beta and gamma frequency bands. The primary regions showing significant beta- and gamma-band ERD for hand and foot movements, respectively, were consistent with previously reported using fMRI. We observed relatively weaker ERD for lip movements, which may be explained by the fact that less fine movement control was required. Overall, our study demonstrated that ERD based on hdEEG data can support the study of motor-related neural processes, with relatively high spatial resolution. An interesting avenue may be the use of hdEEG for deeper investigations into the pathophysiology of neuromotor disorders.

Slow cortical potential signal classification using concave-convex feature

BACKGROUND

The classification of the slow cortical potential (SCP) signals plays a key role in a variety of research areas, including disease diagnostics, human-machine interaction, and education. The widely used classification methods, which combine multiple kinds of features, can be unsuitable in practical applications due to their low robustness to scenario changes.

NEW METHOD

A flexible concave-convex (C-C) feature is reported. The C-C feature is extracted by two steps: (1) the low-frequency node coefficients of the SCP signals are first extracted using wavelet packet decomposition; (2) then the underlying trend of the low-frequency node coefficients is estimated using third-order polynomial fitting, and the feature is constructed using the minimum and maximum second derivative values of the trend curve as |y_min| - y_max where y is the second derivative value.

RESULTS

Experimental results on real datasets reveal that our method with the single C-C feature exhibits high average classification accuracies (92.5% and 84.9% on the BCI competition II dataset Ia and the TJU dataset). The accuracy can be further improved (94.5% and 85.9%) by adding the commonly used mean voltage feature and using the naive Bayesian classifier, indicating the flexibility and scalability of the proposed method.

COMPARISON WITH EXISTING METHODS

The proposed C-C feature based method outperforms state-of-the-art (SOTA) multi-feature classification method from the perspective of classification accuracy.

CONCLUSIONS

The effectiveness of the C-C feature for SCP classification is validated. The proposed feature will represent a useful contribution to the SCP classification, balancing the strengths of traditional features and the proposed one.

On the Feasibility of Using an Ear-EEG to Develop an Endogenous Brain-Computer Interface

Brain-computer interface (BCI) studies based on electroencephalography (EEG) measured around the ears (ear-EEGs) have mostly used exogenous paradigms involving brain activity evoked by external stimuli. The objective of this study is to investigate the feasibility of ear-EEGs for development of an endogenous BCI system that uses self-modulated brain activity. We performed preliminary and main experiments where EEGs were measured on the scalp and behind the ears to check the reliability of ear-EEGs as compared to scalp-EEGs. In the preliminary and main experiments, subjects performed eyes-open and eyes-closed tasks, and they performed mental arithmetic (MA) and light cognitive (LC) tasks, respectively. For data analysis, the brain area was divided into four regions of interest (ROIs) (i.e., frontal, central, occipital, and ear area). The preliminary experiment showed that the degree of alpha activity increase of the ear area with eyes closed is comparable to those of other ROIs (occipital > ear > central > frontal). In the main experiment, similar event-related (de)synchronization (ERD/ERS) patterns were observed between the four ROIs during MA and LC, and all ROIs showed the mean classification accuracies above 70% required for effective binary communication (MA vs. LC) (occipital = ear = central = frontal). From the results, we demonstrated that ear-EEG can be used to develop an endogenous BCI system based on cognitive tasks without external stimuli, which allows the usability of ear-EEGs to be extended.

Open Access Dataset for EEG+NIRS Single-Trial Classification

We provide an open access dataset for hybrid brain-computer interfaces (BCIs) using electroencephalography (EEG) and near-infrared spectroscopy (NIRS). For this, we con-ducted two BCI experiments (left vs. right hand motor imagery; mental arithmetic vs. resting state). The dataset was validated using baseline signal analysis methods, with which classification performance was evaluated for each modality and a combination of both modalities. As already shown in previous literature, the capability of discriminating different mental states can be en-hanced by using a hybrid approach, when comparing to single modality analyses. This makes the provided data highly suitable for hybrid BCI investigations. Since our open access dataset also comprises motion artifacts and physiological data, we expect that it can be used in a wide range of future validation approaches in multimodal BCI research.

A Synchronous Motor Imagery Based Neural Physiological Paradigm for Brain Computer Interface Speller

Brain Computer Interface (BCI) speller is a typical BCI-based application to help paralyzed patients express their thoughts. This paper proposed a novel motor imagery based BCI speller with Oct-o-spell paradigm for word input. Furthermore, an intelligent input method was used for improving the performance of the BCI speller. For the English word spelling experiment, we compared synchronous control with previous asynchronous control under the same experimental condition. There were no significant differences between these two control methods in the classification accuracy, information transmission rate (ITR) or letters per minute (LPM). And the accuracy rates of over 70% validated the feasibility for these two control strategies. It was indicated that MI-based synchronous control protocol was feasible for BCI speller. And the efficiency of the predictive text entry (PTE) mode was superior to that of the Non-PTE mode.

A novel method linking neural connectivity to behavioral fluctuations: Behavior-regressed connectivity

BACKGROUND

During an experimental session, behavioral performance fluctuates, yet most neuroimaging analyses of functional connectivity derive a single connectivity pattern. These conventional connectivity approaches assume that since the underlying behavior of the task remains constant, the connectivity pattern is also constant.

NEW METHOD

We introduce a novel method, behavior-regressed connectivity (BRC), to directly examine behavioral fluctuations within an experimental session and capture their relationship to changes in functional connectivity. This method employs the weighted phase lag index (WPLI) applied to a window of trials with a weighting function. Using two datasets, the BRC results are compared to conventional connectivity results during two time windows: the one second before stimulus onset to identify predictive relationships, and the one second after onset to capture task-dependent relationships.

RESULTS

In both tasks, we replicate the expected results for the conventional connectivity analysis, and extend our understanding of the brain-behavior relationship using the BRC analysis, demonstrating subject-specific BRC maps that correspond to both positive and negative relationships with behavior. Comparison with Existing Method(s): Conventional connectivity analyses assume a consistent relationship between behaviors and functional connectivity, but the BRC method examines performance variability within an experimental session to understand dynamic connectivity and transient behavior.

CONCLUSION

The BRC approach examines connectivity as it covaries with behavior to complement the knowledge of underlying neural activity derived from conventional connectivity analyses. Within this framework, BRC may be implemented for the purpose of understanding performance variability both within and between participants.

Order Statistics Concordance Coefficient With Applications to Multichannel Biosignal Analysis

In this paper, we propose a novel concordance coefficient, called order statistics concordance coefficient (OSCOC), to quantify the association among multichannel biosignals. To uncover its properties, we compare OSCOC with three other similar indexes, i.e., average Pearson's product moment correlation coefficient (APPMCC), Kendall's concordance coefficients (KCC), and average Kendall's tau (AKT), under a multivariate normal model (MNM), linear model (LM), and nonlinear model. To further demonstrate its usefulness, we present an example on atrial arrhythmia analysis based on real-world multichannel cardiac signals. Theoretical derivations as well as numerical results suggest that 1) under MNM and LM, OSCOC performs equally well with APPMCC, and outperforms the other two methods, 2) in nonlinear case, OSCOC even has better performance than KCC and AKT, which are well known to be robust under increasing nonlinear transformations, and 3) OSCOC performs the best in the case study of arrhythmia analysis in terms of the volume under the surface.

A Transform-Based Feature Extraction Approach for Motor Imagery Tasks Classification

In this paper, we present a new motor imagery classification method in the context of electroencephalography (EEG)-based brain–computer interface (BCI). This method uses a signal-dependent orthogonal transform, referred to as linear prediction singular value decomposition (LP-SVD), for feature extraction. The transform defines the mapping as the left singular vectors of the LP coefficient filter impulse response matrix. Using a logistic tree-based model classifier; the extracted features are classified into one of four motor imagery movements. The proposed approach was first benchmarked against two related state-of-the-art feature extraction approaches, namely, discrete cosine transform (DCT) and adaptive autoregressive (AAR)-based methods. By achieving an accuracy of 67.35%, the LP-SVD approach outperformed the other approaches by large margins (25% compared with DCT and 6 % compared with AAR-based methods). To further improve the discriminatory capability of the extracted features and reduce the computational complexity, we enlarged the extracted feature subset by incorporating two extra features, namely, Q- and the Hotelling’s \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} }{}$T^{2}$ \end{document} statistics of the transformed EEG and introduced a new EEG channel selection method. The performance of the EEG classification based on the expanded feature set and channel selection method was compared with that of a number of the state-of-the-art classification methods previously reported with the BCI IIIa competition data set. Our method came second with an average accuracy of 81.38%.

Combining firing rate and spike-train synchrony features in the decoding of motor cortical activity

Decoding of directional information in the motor cortex traditionally utilizes only firing rate information. However, information from other features could be extracted and combined with firing rate in order to increase classification accuracy. This study proposes the combination of firing rate and spike-train synchrony information in the decoding of motor cortical activity. Synchrony measures used are Event Synchronization (ES), SPIKE-Distance, and ISI-Distance. All data used for analyses were obtained from implanted electrode recordings of the primary motor cortex of a monkey that was trained to manipulate a motorized vehicle with 4 degrees of freedom (left, right, front and stop) via joystick control. Firstly, synchrony features could decode time periods, which were otherwise incorrectly decoded by firing rate alone, above chance levels. Secondly, using an ensemble classifier design for offline analysis, combining firing rate and ISI-distance information increases overall decoding accuracy by 1.1%. These results show that synchrony features in spike-trains do contain information not carried in firing rate. In addition, these results also demonstrate the feasibility of combining synchrony and firing rate for improving the classification accuracy of invasive brain-machine interface (BMI) in the control of neural prosthetics.

The temporal evolution of coarse location coding of objects: evidence for feedback

Objects occupy space. How does the brain represent the spatial location of objects? Retinotopic early visual cortex has precise location information but can only segment simple objects. On the other hand, higher visual areas can resolve complex objects but only have coarse location information. Thus coarse location of complex objects might be represented by either (a) feedback from higher areas to early retinotopic areas or (b) coarse position encoding in higher areas. We tested these alternatives by presenting various kinds of first- (edge-defined) and second-order (texture) objects. We applied multivariate classifiers to the pattern of EEG amplitudes across the scalp at a range of time points to trace the temporal dynamics of coarse location representation. For edge-defined objects, peak classification performance was high and early and thus attributable to the retinotopic layout of early visual cortex. For texture objects, it was low and late. Crucially, despite these differences in peak performance and timing, training a classifier on one object and testing it on others revealed that the topography at peak performance was the same for both first- and second-order objects. That is, the same location information, encoded by early visual areas, was available for both edge-defined and texture objects at different time points. These results indicate that locations of complex objects such as textures, although not represented in the bottom-up sweep, are encoded later by neural patterns resembling the bottom-up ones. We conclude that feedback mechanisms play an important role in coarse location representation of complex objects.

Decoding repetitive finger movements with brain activity acquired via non-invasive electroencephalography

We investigated how well repetitive finger tapping movements can be decoded from scalp electroencephalography (EEG) signals. A linear decoder with memory was used to infer continuous index finger angular velocities from the low-pass filtered fluctuations of the amplitude of a plurality of EEG signals distributed across the scalp. To evaluate the accuracy of the decoder, the Pearson's correlation coefficient (r) between the observed and predicted trajectories was calculated in a 10-fold cross-validation scheme. We also assessed attempts to decode finger kinematics from EEG data that was cleaned with independent component analysis (ICA), EEG data from peripheral sensors, and EEG data from rest periods. A genetic algorithm (GA) was used to select combinations of EEG channels that maximized decoding accuracies. Our results (lower quartile r = 0.18, median r = 0.36, upper quartile r = 0.50) show that delta-band EEG signals contain useful information that can be used to infer finger kinematics. Further, the highest decoding accuracies were characterized by highly correlated delta band EEG activity mostly localized to the contralateral central areas of the scalp. Spectral analysis of EEG also showed bilateral alpha band (8–13 Hz) event related desynchronizations (ERDs) and contralateral beta band (20–30 Hz) event related synchronizations (ERSs) localized over central scalp areas. Overall, this study demonstrates the feasibility of decoding finger kinematics from scalp EEG signals.

Genetic programming and serial processing for time series classification

This work describes an approach devised by the authors for time series classification. In our approach genetic programming is used in combination with a serial processing of data, where the last output is the result of the classification. The use of genetic programming for classification, although still a field where more research in needed, is not new. However, the application of genetic programming to classification tasks is normally done by considering the input data as a feature vector. That is, to the best of our knowledge, there are not examples in the genetic programming literature of approaches where the time series data are processed serially and the last output is considered as the classification result. The serial processing approach presented here fills a gap in the existing literature. This approach was tested in three different problems. Two of them are real world problems whose data were gathered for online or conference competitions. As there are published results of these two problems this gives us the chance to compare the performance of our approach against top performing methods. The serial processing of data in combination with genetic programming obtained competitive results in both competitions, showing its potential for solving time series classification problems. The main advantage of our serial processing approach is that it can easily handle very large datasets.

A brain-computer-interface for the detection and modulation of gamma band activity

Gamma band oscillations in the human brain (around 40 Hz) play a functional role in information processing, and a real-time assessment of gamma band activity could be used to evaluate the functional relevance more directly. Therefore, we developed a source based Brain-Computer-Interface (BCI) with an online detection of gamma band activity in a selective brain region in the visual cortex. The BCI incorporates modules for online detection of various artifacts (including microsaccades) and the artifacts were continuously fed back to the volunteer. We examined the efficiency of the source-based BCI for Neurofeedback training of gamma- and alpha-band (8–12 Hz) oscillations and compared the specificity for the spatial and frequency domain. Our results demonstrated that volunteers learned to selectively switch between modulating alpha- or gamma-band oscillations and benefited from online artifact information. The analyses revealed a high level of accuracy with respect to frequency and topography for the gamma-band modulations. Thus, the developed BCI can be used to manipulate the fast oscillatory activity with a high level of specificity. These selective modulations can be used to assess the relevance of fast neural oscillations for information processing in a more direct way, i.e., by the adaptive presentation of stimuli within well-described brain states.

Brain rhythms in mental time travel

The memory theorist Endel Tulving referred to the ability to search through one's memories, and revisit events and episodes from one's past, as mental time travel. This process involves the reactivation of past mental states reflecting the perceptual and conceptual characteristics of the original experience. Widely distributed neural circuitry is engaged in the service of memory search, and the dynamics of these circuits are reflected in rhythmic oscillatory signals at widespread frequencies, recorded both in the local field around neurons and more globally at the scalp. Retrieved-context theory provides a theoretical bridge between the behavioral phenomena exhibited by participants in memory search tasks, and the neural signals reflecting the dynamics of the underlying circuitry. Computational models based on this theory make broad predictions regarding the representational structure of neural activity recorded during these tasks. In recent work, researchers have used multivariate analytic techniques on topographic patterns of oscillatory neural activity to confirm critical predictions of retrieved-context theory. We review the cognitive theory motivating this recent work, and the analytic techniques being developed to create integrated neural-behavioral models of human memory search.

Increased frontomotor oscillations during tic suppression in children with Tourette syndrome

This work investigated whether Tourette syndrome patients exhibit alterations in neural oscillations during spontaneous expression and suppression of tics. Electroencephalograms (EEGs) were recorded from 9 medication-naïve children with Tourette syndrome and 10 age-matched healthy subjects in resting conditions and during tic suppression. Their cortical oscillations were examined using the power spectral method and partial directed coherence. The authors found increased oscillations of broad frequency bands in the frontomotor regions of patients during tic expression, suggesting the involvement of aberrant cortical oscillations in Tourette syndrome. More significantly, prominent increases in theta oscillation in the prefrontal area and directed frontomotor interactions in the theta and beta bands were observed during tic suppression. Furthermore, the directed EEG interaction from the frontal to motor regions was positively correlated with the severity of tic symptoms. These findings suggest that the frontal to motor interaction of cortical oscillations plays a significant role in tic suppression.

Review of the BCI Competition IV

The BCI competition IV stands in the tradition of prior BCI competitions that aim to provide high quality neuroscientific data for open access to the scientific community. As experienced already in prior competitions not only scientists from the narrow field of BCI compete, but scholars with a broad variety of backgrounds and nationalities. They include high specialists as well as students. The goals of all BCI competitions have always been to challenge with respect to novel paradigms and complex data. We report on the following challenges: (1) asynchronous data, (2) synthetic, (3) multi-class continuous data, (4) session-to-session transfer, (5) directionally modulated MEG, (6) finger movements recorded by ECoG. As after past competitions, our hope is that winning entries may enhance the analysis methods of future BCIs.

Classification of multichannel EEG patterns using parallel hidden Markov models

In this paper, a parallel hidden-Markov-model (PHMM)-based approach is proposed for the problem of multichannel electroencephalogram (EEG) patterns classification. The approach is based on multi-channel representation of the EEG signals using a parallel combination of HMMs, where each model represents a particular channel. The performance of the proposed algorithm is studied using an artificial EEG database, and two real EEG databases: a database of two classes of EEGs elicited during a task of imagery of hand upward and downward movements of a computer screen cursor (db Ia), and a database of two classes of sensorimotor EEGs elicited during a feedback-regulated left-right motor imagery task (db III). The results show that the proposed algorithm outperforms other commonly used methods with classification rate improvement of 2 and 10% for db Ia and db III, respectively. In addition, the proposed method outperforms a support vector machine classifier with a linear kernel, when both classifiers utilize the same feature set. The results also show that a model architecture which includes a left-to-right scheme with no skips, five states and three Gaussians, outperforms the other tested architectures due to the fact that it allows a better modeling of the temporal sequencing of the EEG components.

Toward functioning and usable brain-computer interfaces (BCIs): a literature review

PURPOSE

The aim of this paper is to provide an exhaustive review of the literature about brain-computer interfaces (BCIs) that could be used with these paralysed patients. The electroencephalography (EEG) is the best candidate for the continuous use in the environment of patients' houses, due to its portability and ease of use. For this reason, the present paper will focus on this kind of BCI. Moreover, it is our aim to focus more on the patients, regarding their active role in the modulation of the brain activity. This leads to a differentiation between studies that use an active regulation and studies that use a non-active regulation.

METHOD

Relevant articles in the BCIs field were selected using MEDLINE and PsycINFO.

RESULTS

Research through data banks produced 980 results, which were reduced to 127 after exclusion criteria selection. These references were divided in four categories, based on the use of active or non-active regulation, and on the event related potential used.

CONCLUSIONS

In most of the examined works, the focus was on the development of systems and algorithms able to recognise and classify brain events. Although this kind of research is fundamental, a user-centred point of view was rarely adopted. [Box: see text].

An online EEG-based brain-computer interface for controlling hand grasp using an adaptive probabilistic neural network

This paper presents a new online single-trial EEG-based brain-computer interface (BCI) for controlling hand holding and sequence of hand grasping and opening in an interactive virtual reality environment. The goal of this research is to develop an interaction technique that will allow the BCI to be effective in real-world scenarios for hand grasp control. One of the major challenges in the BCI research is the subject training. Currently, in most online BCI systems, the classifier was trained offline using the data obtained during the experiments without feedback, and used in the next sessions in which the subjects receive feedback. We investigated whether the subject could achieve satisfactory online performance without offline training while the subjects receive feedback from the beginning of the experiments during hand movement imagination. Another important issue in designing an online BCI system is the machine learning to classify the brain signal which is characterized by significant day-to-day and subject-to-subject variations and time-varying probability distributions. Due to these variabilities, we introduce the use of an adaptive probabilistic neural network (APNN) working in a time-varying environment for classification of EEG signals. The experimental evaluation on ten naïve subjects demonstrated that an average classification accuracy of 75.4% was obtained during the first experiment session (day) after about 3 min of online training without offline training, and 81.4% during the second session (day). The average rates during third and eighth sessions are 79.0% and 84.0%, respectively, using previously calculated classifier during the first sessions, without online training and without the need to calibrate. The results obtained from more than 5000 trials on ten subjects showed that the method could provide a robust performance over different experiment sessions and different subjects.

Electrical neuroimaging of single trials to identify laterality and brain regions involved in finger movements

Thought-controlled neuroprostheses could allow paralyzed patients to interact with the external world using brain waves. Thus far, the fastest and more accurate control of neuroprostheses is achieved through direct recordings of neural activity [Nicolelis, M.A., 2001. Actions from thoughts. Nature 409, 403-407; Donoghue, J.P., 2002. Connecting cortex to machines: recent advances in brain interfaces. Nat. Neurosci. 5 (Suppl.), 1085-1088]. However, invasive recordings have inherent medical risks. Here we discuss some approaches that could enhance the speed and accuracy of non-invasive devices, namely, (1) enlarging the spectral analysis to include higher frequency oscillations, able to transmit substantial information over short analysis windows; (2) using spectral analysis procedures that minimize the variance of the estimates; and (3) transforming EEG recorded activity into local field potential estimates (eLFP). Theoretical and experimental arguments are used to explain why it is erroneous to think that scalp EEG cannot sense high frequency oscillations and how this might hinders further developments. We further illustrate how non-invasive eLFPs derived from the scalp-recorded electroencephalogram (EEG) can be combined with robust, broad band spectral analysis to accurately detect (off-line) the laterality of upcoming hand movements. Interestingly, the use of pattern recognition to select the brain voxels differentially engaged by the explored tasks leads to sound neural activation images. Consequently, our results indicate that both research lines, i.e., neuroprosthetics and electrical neuroimaging, might effectively benefit from their mutual interaction.

EEG-based classification for elbow versus shoulder torque intentions involving stroke subjects

The ultimate aim for classifying elbow versus shoulder torque intentions is to develop robust brain-computer interface (BCI) devices for patients who suffer from movement disorders following brain injury such as stroke. In this paper, we investigate the advanced classification approach classifier-enhanced time-frequency synthesized spatial pattern algorithm (classifier-enhanced TFSP) in classifying a subject's intent of generating an isometric shoulder abduction (SABD) or elbow flexion (EF) torque using signals obtained from 163 scalp electroencephalographic (EEG) electrodes. Two classifiers, the support vector classifier (SVC) and the classification and regression tree (CART), are integrated in the TFSP algorithm that decomposes the signal into a weighted time, frequency and spatial feature space. The resulting high-performing methods (SVC-TFSP and CART-TFSP) are then applied to experimental data collected in four healthy subjects and two stroke subjects. Results are compared with the original TFSP, and significantly higher reliability in both healthy subjects (92% averaged over four healthy subjects) and stroke subjects (75% averaged over two subjects) are achieved. The accuracies of classifier-enhanced TFSP methods are further improved after a rejection scheme is applied (approximately 100% in healthy subjects and >80% in stroke subjects). The results are among the highest reliability reported in literature for tasks with spatial representations on the motor cortex as close as shoulder and elbow. The paper also discusses the impact of applying rejection strategy in detail and reports the existence of an optimal rejection rate on a stroke subject. The results indicate that the proposed algorithms are promising for future use of rehabilitative BCI applications in neurologically impaired patients.

A simple classification tool for single-trial analysis of ERP components

Event-related potentials (ERPs) were recorded by measuring a dense sensor EEG from eight healthy volunteers in a visual oddball experiment. Single trials were analyzed with an extremely simple high-dimensional version of discriminant analysis. The question was how many of the target trials contribute to the average P3, and to test whether other components in the ERP are sensitive to discriminate between target and non-target trials. One common classification rule for all participants expressing the P3 component correctly classified 88% of the ERPs of all subjects in response to a target or non-target trial. For four of the eight participants, there were strong differences in an early ERP component over the occipital recording sites. Their individual classification rules, obtained from the training data in the time interval up to 200 ms, correctly classified 85% of the trials of the test data.

A survey of signal processing algorithms in brain-computer interfaces based on electrical brain signals

Brain-computer interfaces (BCIs) aim at providing a non-muscular channel for sending commands to the external world using the electroencephalographic activity or other electrophysiological measures of the brain function. An essential factor in the successful operation of BCI systems is the methods used to process the brain signals. In the BCI literature, however, there is no comprehensive review of the signal processing techniques used. This work presents the first such comprehensive survey of all BCI designs using electrical signal recordings published prior to January 2006. Detailed results from this survey are presented and discussed. The following key research questions are addressed: (1) what are the key signal processing components of a BCI, (2) what signal processing algorithms have been used in BCIs and (3) which signal processing techniques have received more attention?

EMG and EOG artifacts in brain computer interface systems: A survey

It is widely accepted in the brain computer interface (BCI) research community that neurological phenomena are the only source of control in any BCI system. Artifacts are undesirable signals that can interfere with neurological phenomena. They may change the characteristics of neurological phenomena or even be mistakenly used as the source of control in BCI systems. Electrooculography (EOG) and electromyography (EMG) artifacts are considered among the most important sources of physiological artifacts in BCI systems. Currently, however, there is no comprehensive review of EMG and EOG artifacts in BCI literature. This paper reviews EOG and EMG artifacts associated with BCI systems and the current methods for dealing with them. More than 250 refereed journal and conference papers are reviewed and categorized based on the type of neurological phenomenon used and the methods employed for handling EOG and EMG artifacts. This study reveals weaknesses in BCI studies related to reporting the methods of handling EMG and EOG artifacts. Most BCI papers do not report whether or not they have considered the presence of EMG and EOG artifacts in the brain signals. Only a small percentage of BCI papers report automated methods for rejection or removal of artifacts in their systems. As the lack of dealing with artifacts may result in the deterioration of the performance of a particular BCI system during practical applications, it is necessary to develop automatic methods to handle artifacts or to design BCI systems whose performance is robust to the presence of artifacts.

EEG-based Discrimination of Elbow/Shoulder Torques using Brain Computer Interface Algorithms: Implications for Rehabilitation

Brain computer interface (BCI) algorithms are used to predict the torque generation in the direction of shoulder abduction or elbow flexion using scalp EEG signals from 163 electrodes. Based on features extracted from both frequency and time domains, three classifiers are employed including support vector classifier, classification trees and K nearest neighbor. Support vector classifier achieves the highest recognition rate of 92.9% on two able-bodied subjects in average. The recognition rates we obtained on the able-bodied subjects are among the highest compared with previous reports on predicting motor intent using scalp EEG. This demonstrates the feasibility of separating the shoulder/elbow torques using scalp EEG as well as the potential of support vector classifier in applications of BCI. Preliminary experiments on two hemiparetic stroke subjects using support vector classifier reports an accuracy of 84.1% in average, which shows an increased difficulty in predicting intent presumably due to cortical reorganization resulting from the stroke.

A review of classification algorithms for EEG-based brain–computer interfaces

In this paper we review classification algorithms used to design brain-computer interface (BCI) systems based on electroencephalography (EEG). We briefly present the commonly employed algorithms and describe their critical properties. Based on the literature, we compare them in terms of performance and provide guidelines to choose the suitable classification algorithm(s) for a specific BCI.

A self-paced brain interface system that uses movement related potentials and changes in the power of brain rhythms

Movement execution results in the simultaneous generation of movement-related potentials (MRP) as well as changes in the power of Mu and Beta rhythms. This paper proposes a new self-paced multi-channel BI that combines features extracted from MRPs and from changes in the power of Mu and Beta rhythms. We developed a new algorithm to classify the high-dimensional feature space. It uses a two-stage multiple-classifier system (MCS). First, an MCS classifies each neurological phenomenon separately using the information extracted from specific EEG channels (EEG channels are selected by a genetic algorithm). In the second stage, another MCS combines the outputs of MCSs developed in the first stage. Analysis of the data of four able-bodied subjects shows the superior performance of the proposed algorithm compared with a scheme where the features were all combined in a single feature vector and then classified.

A Comprehensive Survey of Brain Interface Technology Designs

In this work we present the first comprehensive survey of Brain Interface (BI) technology designs published prior to January 2006. Detailed results from this survey, which was based on the Brain Interface Design Framework proposed by Mason and Birch, are presented and discussed to address the following research questions: (1) which BI technologies are directly comparable, (2) what technology designs exist, (3) which application areas (users, activities and environments) have been targeted in these designs, (4) which design approaches have received little or no research and are possible opportunities for new technology, and (5) how well are designs reported. The results of this work demonstrate that meta-analysis of high-level BI design attributes is possible and informative. The survey also produced a valuable, historical cross-reference where BI technology designers can identify what types of technology have been proposed and by whom.

Utilizing gamma band to improve mental task based brain-computer interface design

A common method for designing brain-computer Interface (BCI) is to use electroencephalogram (EEG) signals extracted during mental tasks. In these BCI designs, features from EEG such as power and asymmetry ratios from delta, theta, alpha, and beta bands have been used in classifying different mental tasks. In this paper, the performance of the mental task based BCI design is improved by using spectral power and asymmetry ratios from gamma (24-37 Hz) band in addition to the lower frequency bands. In the experimental study, EEG signals extracted during five mental tasks from four subjects were used. Elman neural network (ENN) trained by the resilient backpropagation algorithm was used to classify the power and asymmetry ratios from EEG into different combinations of two mental tasks. The results indicated that ((1) the classification performance and training time of the BCI design were improved through the use of additional gamma band features; (2) classification performances were nearly invariant to the number of ENN hidden units or feature extraction method.

Feature extraction for EEG-based brain–computer interfaces by wavelet packet best basis decomposition

A method based on wavelet packet best basis decomposition (WPBBD) is investigated for the purpose of extracting features of electroencephalogram signals produced during motor imagery tasks in brain-computer interfaces. The method includes the following three steps. (1) Original signals are decomposed by wavelet packet transform (WPT) and a wavelet packet library can be formed. (2) The best basis for classification is selected from the library. (3) Subband energies included in the best basis are used as effective features. Three different motor imagery tasks are discriminated using the features. The WPBBD produces a 70.3% classification accuracy, which is 4.2% higher than that of the existing wavelet packet method.

The BCI competition 2003: progress and perspectives in detection and discrimination of EEG single trials

Interest in developing a new method of man-to-machine communication--a brain-computer interface (BCI)--has grown steadily over the past few decades. BCIs create a new communication channel between the brain and an output device by bypassing conventional motor output pathways of nerves and muscles. These systems use signals recorded from the scalp, the surface of the cortex, or from inside the brain to enable users to control a variety of applications including simple word-processing software and orthotics. BCI technology could therefore provide a new communication and control option for individuals who cannot otherwise express their wishes to the outside world. Signal processing and classification methods are essential tools in the development of improved BCI technology. We organized the BCI Competition 2003 to evaluate the current state of the art of these tools. Four laboratories well versed in EEG-based BCI research provided six data sets in a documented format. We made these data sets (i.e., labeled training sets and unlabeled test sets) and their descriptions available on the Internet. The goal in the competition was to maximize the performance measure for the test labels. Researchers worldwide tested their algorithms and competed for the best classification results. This paper describes the six data sets and the results and function of the most successful algorithms.