Showing papers in "Computational Intelligence and Neuroscience in 2007"

Self-paced (asynchronous) BCI control of a wheelchair in virtual environments: a case study with a tetraplegic

Abstract: The aim of the present study was to demonstrate for the first time that brain waves can be used by a tetraplegic to control movements of his wheelchair in virtual reality (VR). In this case study, the spinal cord injured (SCI) subject was able to generate bursts of beta oscillations in the electroencephalogram (EEG) by imagination of movements of his paralyzed feet. These beta oscillations were used for a self-paced (asynchronous) brain-computer interface (BCI) control based on a single bipolar EEG recording. The subject was placed inside a virtual street populated with avatars. The task was to "go" from avatar to avatar towards the end of the street, but to stop at each avatar and talk to them. In average, the participant was able to successfully perform this asynchronous experiment with a performance of 90%, single runs up to 100%.

Automatic seizure detection based on time-frequency analysis and artificial neural networks

Abstract: The recording of seizures is of primary interest in the evaluation of epileptic patients. Seizure is the phenomenon of rhythmicity discharge from either a local area or the whole brain and the individual behavior usually lasts from seconds to minutes. Since seizures, in general, occur infrequently and unpredictably, automatic detection of seizures during long-term electroencephalograph (EEG) recordings is highly recommended. As EEG signals are nonstationary, the conventional methods of frequency analysis are not successful for diagnostic purposes. This paper presents a method of analysis of EEG signals, which is based on time-frequency analysis. Initially, selected segments of the EEG signals are analyzed using time-frequency methods and several features are extracted for each segment, representing the energy distribution in the time-frequency plane. Then, those features are used as an input in an artificial neural network (ANN), which provides the final classification of the EEG segments concerning the existence of seizures or not. We used a publicly available dataset in order to evaluate our method and the evaluation results are very promising indicating overall accuracy from 97.72% to 100%.

fMRI brain-computer interface: a tool for neuroscientific research and treatment

Abstract: Brain-computer interfaces based on functional magnetic resonance imaging (fMRI-BCI) allow volitional control of anatomically specific regions of the brain. Technological advancement in higher field MRI scanners, fast data acquisition sequences, preprocessing algorithms, and robust statistical analysis are anticipated to make fMRI-BCI more widely available and applicable. This noninvasive technique could potentially complement the traditional neuroscientific experimental methods by varying the activity of the neural substrates of a region of interest as an independent variable to study its effects on behavior. If the neurobiological basis of a disorder (e.g., chronic pain, motor diseases, psychopathy, social phobia, depression) is known in terms of abnormal activity in certain regions of the brain, fMRI-BCI can be targeted to modify activity in those regions with high specificity for treatment. In this paper, we review recent results of the application of fMRI-BCI to neuroscientific research and psychophysiological treatment.

Fully online multicommand brain-computer interface with visual neurofeedback using SSVEP paradigm

Abstract: We propose a new multistage procedure for a real-time brain-machine/computer interface (BCI). The developed system allows a BCI user to navigate a small car (or any other object) on the computer screen in real time, in any of the four directions, and to stop it if necessary. Extensive experiments with five young healthy subjects confirmed the high performance of the proposed online BCI system. The modular structure, high speed, and the optimal frequency band characteristics of the BCI platform are features which allow an extension to a substantially higher number of commands in the near future.

Canonical source reconstruction for MEG

Abstract: We describe a simple and efficient solution to the problem of reconstructing electromagnetic sources into a canonical or standard anatomical space. Its simplicity rests upon incorporating subject-specific anatomy into the forward model in a way that eschews the need for cortical surface extraction. The forward model starts with a canonical cortical mesh, defined in a standard stereotactic space. The mesh is warped, in a nonlinear fashion, to match the subject's anatomy. This warping is the inverse of the transformation derived from spatial normalization of the subject's structural MRI image, using fully automated procedures that have been established for other imaging modalities. Electromagnetic lead fields are computed using the warped mesh, in conjunction with a spherical head model (which does not rely on individual anatomy). The ensuing forward model is inverted using an empirical Bayesian scheme that we have described previously in several publications. Critically, because anatomical information enters the forward model, there is no need to spatially normalize the reconstructed source activity. In other words, each source, comprising the mesh, has a predetermined and unique anatomical attribution within standard stereotactic space. This enables the pooling of data from multiple subjects and the reporting of results in stereotactic coordinates. Furthermore, it allows the graceful fusion of fMRI and MEG data within the same anatomical framework.

Vibrotactile feedback for brain-computer interface operation

Abstract: To be correctly mastered, brain-computer interfaces (BCIs) need an uninterrupted flow of feedback to the user. This feedback is usually delivered through the visual channel. Our aim was to explore the benefits of vibrotactile feedback during users' training and control of EEG-based BCI applications. A protocol for delivering vibrotactile feedback, including specific hardware and software arrangements, was specified. In three studies with 33 subjects (including 3 with spinal cord injury), we compared vibrotactile and visual feedback, addressing: (I) the feasibility of subjects' training to master their EEG rhythms using tactile feedback; (II) the compatibility of this form of feedback in presence of a visual distracter; (III) the performance in presence of a complex visual task on the same (visual) or different (tactile) sensory channel. The stimulation protocol we developed supports a general usage of the tactors; preliminary experimentations. All studies indicated that the vibrotactile channel can function as a valuable feedback modality with reliability comparable to the classical visual feedback. Advantages of using a vibrotactile feedback emerged when the visual channel was highly loaded by a complex task. In all experiments, vibrotactile feedback felt, after some training, more natural for both controls and SCI users.

Context-based filtering for assisted brain-actuated wheelchair driving

Abstract: Controlling a robotic device by using human brain signals is an interesting and challenging task. The device may be complicated to control and the nonstationary nature of the brain signals provides for a rather unstable input. With the use of intelligent processing algorithms adapted to the task at hand, however, the performance can be increased. This paper introduces a shared control system that helps the subject in driving an intelligent wheelchair with a noninvasive brain interface. The subject's steering intentions are estimated from electroencephalogram (EEG) signals and passed through to the shared control system before being sent to the wheelchair motors. Experimental results show a possibility for significant improvement in the overall driving performance when using the shared control system compared to driving without it. These results have been obtained with 2 healthy subjects during their first day of training with the brain-actuated wheelchair.

The self-paced Graz brain-computer interface: methods and applications

Abstract: We present the self-paced 3-class Graz brain-computer interface (BCI) which is based on the detection of sensorimotor electroencephalogram (EEG) rhythms induced by motor imagery. Self-paced operation means that the BCI is able to determine whether the ongoing brain activity is intended as control signal (intentional control) or not (non-control state). The presented system is able to automatically reduce electrooculogram (EOG) artifacts, to detect electromyographic (EMG) activity, and uses only three bipolar EEG channels. Two applications are presented: the freeSpace virtual environment (VE) and the Brainloop interface. The freeSpace is a computer-game-like application where subjects have to navigate through the environment and collect coins by autonomously selecting navigation commands. Three subjects participated in these feedback experiments and each learned to navigate through the VE and collect coins. Two out of the three succeeded in collecting all three coins. The Brainloop interface provides an interface between the Graz-BCI and Google Earth.

Online artifact removal for brain-computer interfaces using support vector machines and blind source separation

Abstract: We propose a combination of blind source separation (BSS) and independent component analysis (ICA) (signal decomposition into artifacts and nonartifacts) with support vector machines (SVMs) (automatic classification) that are designed for online usage In order to select a suitable BSS/ICA method, three ICA algorithms (JADE, Infomax, and FastICA) and one BSS algorithm (AMUSE) are evaluated to determine their ability to isolate electromyographic (EMG) and electrooculographic (EOG) artifacts into individual components An implementation of the selected BSS/ICA method with SVMs trained to classify EMG and EOG artifacts, which enables the usage of the method as a filter in measurements with online feedback, is described This filter is evaluated on three BCI datasets as a proof-of-concept of the method

Connecting neurons to a mobile robot: an in vitro bidirectional neural interface

Abstract: One of the key properties of intelligent behaviors is the capability to learn and adapt to changing environmental conditions. These features are the result of the continuous and intense interaction of the brain with the external world, mediated by the body. For this reason "embodiment" represents an innovative and very suitable experimental paradigm when studying the neural processes underlying learning new behaviors and adapting to unpredicted situations. To this purpose, we developed a novel bidirectional neural interface. We interconnected in vitro neurons, extracted from rat embryos and plated on a microelectrode array (MEA), to external devices, thus allowing real-time closed-loop interaction. The novelty of this experimental approach entails the necessity to explore different computational schemes and experimental hypotheses. In this paper, we present an open, scalable architecture, which allows fast prototyping of different modules and where coding and decoding schemes and different experimental configurations can be tested. This hybrid system can be used for studying the computational properties and information coding in biological neuronal networks with far-reaching implications for the future development of advanced neuroprostheses.

Nessi: an EEG-controlled web browser for severely paralyzed patients

Abstract: We have previously demonstrated that an EEG-controlled web browser based on self-regulation of slow cortical potentials (SCPs) enables severely paralyzed patients to browse the internet independently of any voluntary muscle control. However, this system had several shortcomings, among them that patients could only browse within a limited number of web pages and had to select links from an alphabetical list, causing problems if the link names were identical or if they were unknown to the user (as in graphical links). Here we describe a new EEG-controlled web browser, called Nessi, which overcomes these shortcomings. In Nessi, the open source browser, Mozilla, was extended by graphical in-place markers, whereby different brain responses correspond to different frame colors placed around selectable items, enabling the user to select any link on a web page. Besides links, other interactive elements are accessible to the user, such as e-mail and virtual keyboards, opening up a wide range of hypertext-based applications.

EEG-based brain-computer interface for tetraplegics

Abstract: Movement-disabled persons typically require a long practice time to learn how to use a brain-computer interface (BCI). Our aim was to develop a BCI which tetraplegic subjects could control only in 30 minutes. Six such subjects (level of injury C4-C5) operated a 6-channel EEG BCI. The task was to move a circle from the centre of the computer screen to its right or left side by attempting visually triggered right- or left-hand movements. During the training periods, the classifier was adapted to the user's EEG activity after each movement attempt in a supervised manner. Feedback of the performance was given immediately after starting the BCI use. Within the time limit, three subjects learned to control the BCI. We believe that fast initial learning is an important factor that increases motivation and willingness to use BCIs. We have previously tested a similar single-trial classification approach in healthy subjects. Our new results show that methods developed and tested with healthy subjects do not necessarily work as well as with motor-disabled patients. Therefore, it is important to use motor-disabled persons as subjects in BCI development.

Channel selection and feature projection for cognitive load estimation using ambulatory EEG

Abstract: We present an ambulatory cognitive state classification system to assess the subject's mental load based on EEG measurements. The ambulatory cognitive state estimator is utilized in the context of a real-time augmented cognition (AugCog) system that aims to enhance the cognitive performance of a human user through computer-mediated assistance based on assessments of cognitive states using physiological signals including, but not limited to, EEG. This paper focuses particularly on the offline channel selection and feature projection phases of the design and aims to present mutual-information-based techniques that use a simple sample estimator for this quantity. Analyses conducted on data collected from 3 subjects performing 2 tasks (n-back/Larson) at 2 difficulty levels (low/high) demonstrate that the proposed mutual-information-based dimensionality reduction scheme can achieve up to 94% cognitive load estimation accuracy.

The P300 as a marker of waning attention and error propensity

Abstract: Action errors can occur when routine responses are triggered inappropriately by familiar cues. Here, EEG was recorded as volunteers performed a "go/no-go" task of long duration that occasionally and unexpectedly required them to withhold a frequent, routine response. EEG components locked to the onset of relevant go trials were sorted according to whether participants erroneously responded to immediately subsequent no-go trials or correctly withheld their responses. Errors were associated with a significant relative reduction in the amplitude of the preceding P300, that is, a judgement could be made bout whether a response-inhibition error was likely before it had actually occurred. Furthermore, fluctuations in P300 amplitude across the task formed a reliable associate of individual error propensity, supporting its use as a marker of sustained control over action.

Towards development of a 3-state self-paced brain-computer interface

Abstract: Most existing brain-computer interfaces (BCIs) detect specific mental activity in a so-called synchronous paradigm. Unlike synchronous systems which are operational at specific system-defined periods, self-paced (asynchronous) interfaces have the advantage of being operational at all times. The low-frequency asynchronous switch design (LF-ASD) is a 2-state self-paced BCI that detects the presence of a specific finger movement in the ongoing EEG. Recent evaluations of the 2-state LF-ASD show an average true positive rate of 41% at the fixed false positive rate of 1%. This paper proposes two designs for a 3-state self-paced BCI that is capable of handling idle brain state. The two proposed designs aim at detecting right- and left-hand extensions from the ongoing EEG. They are formed of two consecutive detectors. The first detects the presence of a right- or a left-hand movement and the second classifies the detected movement as a right or a left one. In an offline analysis of the EEG data collected from four able-bodied individuals, the 3-state brain-computer interface shows a comparable performance with a 2-state system and significant performance improvement if used as a 2-state BCI, that is, in detecting the presence of a right- or a left-hand movement (regardless of the type of movement). It has an average true positive rate of 37.5% and 42.8% (at false positives rate of 1%) in detecting right- and left-hand extensions, respectively, in the context of a 3-state self-paced BCI and average detection rate of 58.1% (at false positive rate of 1%) in the context of a 2-state self-paced BCI.

An algorithm for idle-state detection in motor-imagery-based brain-computer interface

Abstract: For a robust brain-computer interface (BCI) system based on motor imagery (MI), it should be able to tell when the subject is not concentrating on MI tasks (the "idle state") so that real MI tasks could be extracted accurately. Moreover, because of the diversity of idle state, detecting idle state without training samples is as important as classifying MI tasks. In this paper, we propose an algorithm for solving this problem. A three-class classifier was constructed by combining two two-class classifiers, one specified for idle-state detection and the other for these two MI tasks. Common spatial subspace decomposition (CSSD) was used to extract the features of event-related desynchronization (ERD) in two motor imagery tasks. Then Fisher discriminant analysis (FDA) was employed in the design of two two-class classifiers for completion of detecting each task, respectively. The algorithm successfully provided a way to solve the problem of "idle-state detection without training samples." The algorithm was applied to the dataset IVc from BCI competition III. A final result with mean square error of 0.30 was obtained on the testing set. This is the winning algorithm in BCI competition III. In addition, the algorithm was also validated by applying to the EEG data of an MI experiment including "idle" task.

Canonical decomposition of ictal scalp EEG and accurate source localisation: principles and simulation study

Abstract: Long-term electroencephalographic (EEG) recordings are important in the presurgical evaluation of refractory partial epilepsy for the delineation of the ictal onset zones. In this paper, we introduce a new concept for an automatic, fast, and objective localisation of the ictal onset zone in ictal EEG recordings. Canonical decomposition of ictal EEG decomposes the EEG in atoms. One or more atoms are related to the seizure activity. A single dipole was then fitted to model the potential distribution of each epileptic atom. In this study, we performed a simulation study in order to estimate the dipole localisation error. Ictal dipole localisation was very accurate, even at low signal-to-noise ratios, was not affected by seizure activity frequency or frequency changes, and was minimally affected by the waveform and depth of the ictal onset zone location. Ictal dipole localisation error using 21 electrodes was around 10.0 mm and improved more than tenfold in the range of 0.5-1.0 mm using 148 channels. In conclusion, our simulation study of canonical decomposition of ictal scalp EEG allowed a robust and accurate localisation of the ictal onset zone.

Extracting rhythmic brain activity for brain-computer interfacing through constrained independent component analysis

Abstract: We propose a technique based on independent component analysis (ICA) with constraints, applied to the rhythmic electroen-cephalographic (EEG) data recorded from a brain-computer interfacing (BCI) system. ICA is a technique that can decompose the recorded EEG into its underlying independent components and in BCI involving motor imagery, the aim is to isolate rhythmic activity over the sensorimotor cortex. We demonstrate that, through the technique of spectrally constrained ICA, we can learn a spatial filter suited to each individual EEG recording. This can effectively extract discriminatory information from two types of single-trial EEG data. Through the use of the ICA algorithm, the classification accuracy is improved by about 25%, on average, compared to the performance on the unpreprocessed data. This implies that this ICA technique can be reliably used to identify and extract BCI-related rhythmic activity underlying the recordings where a particular filter is learned for each subject. The high classification rate and low computational cost make it a promising algorithm for application to an online BCI system.

Classifying EEG for brain-computer interface: learning optimal filters for dynamical system features

Abstract: Classification of multichannel EEG recordings during motor imagination has been exploited successfully for brain-computer interfaces (BCI). In this paper, we consider EEG signals as the outputs of a networked dynamical system (the cortex), and exploit synchronization features from the dynamical system for classification. Herein, we also propose a new framework for learning optimal filters automatically from the data, by employing a Fisher ratio criterion. Experimental evaluations comparing the proposed dynamical system features with the CSP and the AR features reveal their competitive performance during classification. Results also show the benefits of employing the spatial and the temporal filters optimized using the proposed learning approach.

The estimation of cortical activity for brain-computer interface: applications in a domotic context

Abstract: In order to analyze whether the use of the cortical activity, estimated from noninvasive EEG recordings, could be useful to detect mental states related to the imagination of limb movements, we estimate cortical activity from high-resolution EEG recordings in a group of healthy subjects by using realistic head models. Such cortical activity was estimated in region of interest associated with the subject's Brodmann areas by using a depth-weighted minimum norm technique. Results showed that the use of the cortical-estimated activity instead of the unprocessed EEG improves the recognition of the mental states associated to the limb movement imagination in the group of normal subjects. The BCI methodology presented here has been used in a group of disabled patients in order to give them a suitable control of several electronic devices disposed in a three-room environment devoted to the neurorehabilitation. Four of six patients were able to control several electronic devices in this domotic context with the BCI system.

A semisupervised support vector machines algorithm for BCI systems

Abstract: As an emerging technology, brain-computer interfaces (BCIs) bring us new communication interfaces which translate brain activities into control signals for devices like computers, robots, and so forth. In this study, we propose a semisupervised support vector machine (SVM) algorithm for brain-computer interface (BCI) systems, aiming at reducing the time-consuming training process. In this algorithm, we apply a semisupervised SVM for translating the features extracted from the electrical recordings of brain into control signals. This SVM classifier is built from a small labeled data set and a large unlabeled data set. Meanwhile, to reduce the time for training semisupervised SVM, we propose a batch-mode incremental learning method, which can also be easily applied to the online BCI systems. Additionally, it is suggested in many studies that common spatial pattern (CSP) is very effective in discriminating two different brain states. However, CSP needs a sufficient labeled data set. In order to overcome the drawback of CSP, we suggest a two-stage feature extraction method for the semisupervised learning algorithm. We apply our algorithm to two BCI experimental data sets. The offline data analysis results demonstrate the effectiveness of our algorithm.

Editorial: brain-computer interfaces towards practical implementations and potential applications

Abstract: Brain-computer interfaces (BCIs) are systems that use brain signals (electric, magnetic, metabolic) to control external devices such as computers, switches, wheelchairs, or neuroprosthesis. While BCI research hopes to create new communication channels for disabled or elderly persons using their brain signals, recently efforts have been focused on developing potential applications in rehabilitation, multimedia communication, and relaxation (such as immersive virtual reality control). The various BCI systems use different methods to extract the user’s intentions from her/his brain electrical activity. Many researchers world wide are actually investigating and testing several promising BCI paradigms, including (i) measuring the brain activities over the primary motor cortex that results from imaginary limbs and tongue movements, (ii) detecting the presence of EEG periodic waveforms, called steady-state visual evoked potentials (SSVEPs), elicited by flashing light sources (e.g., LEDs or phase-reversing checkerboards), and (iii) identifying event-related potentials (ERPs) in EEG that follow an event noticed by the user (or his/her intention), for example, P300 peak waveforms after a target/rare (oddball) stimulus among a sequence the user pay attention to. One promising extension of BCI is to incorporate various neurofeedbacks to train subjects to modulate EEG brain patterns and parameters such as event-related potentials (ERPs), event-related desynchronization (ERD), sensorimotor rhythm (SMR), or slow cortical potentials (SCPs) to meet a specific criterion or to learn self-regulation skills. The subject then changes their brain patterns in response to some feedbacks. Such integration of neurofeedback in BCI is an emerging technology for rehabilitation, but we believe it is also a new paradigm in neuroscience that might reveal previously unknown brain activities associated with behavior or self-regulated mental states. The possibility of automatic context-awareness as a new interface goes far beyond the standard BCI with simple feedback control. BCI relies increasingly on findings from other disciplines, especially, neuroscience, information technology, biomedical engineering, machine learning, and clinical rehabilitation. This special issue covers the following topics: noninvasive BCI systems (EEG, MEG, fMRI) for decoding and classification neural activity in humans; comparisons of linear versus nonlinear signal processing for decoding and classifying neural activity; multimodal neural imaging methods for BCI; systems for monitoring brain mental states to enable cognitive user interfaces; online and offline algorithms for decoding brain activity; signal processing and machine learning methods for handling artifacts and noise in BCI systems; neurofeedback and BCI; applications of BCI, especially, in therapy and rehabilitation; new technologies for BCI, especially, multielectrode technologies interfacing, telemetry, wireless communication for BCI. This special issue includes 23 contributions which cover a wide range of techniques and approaches for BCI and related problems.

A framework to support automated classification and labeling of brain electromagnetic patterns

Abstract: This paper describes a framework for automated classification and labeling of patterns in electroencephalographic (EEG) and magnetoencephalographic (MEG) data. We describe recent progress on four goals: 1) specification of rules and concepts that capture expert knowledge of event-related potentials (ERP) patterns in visual word recognition; 2) implementation of rules in an automated data processing and labeling stream; 3) data mining techniques that lead to refinement of rules; and 4) iterative steps towards system evaluation and optimization. This process combines top-down, or knowledge-driven, methods with bottom-up, or data-driven, methods. As illustrated here, these methods are complementary and can lead to development of tools for pattern classification and labeling that are robust and conceptually transparent to researchers. The present application focuses on patterns in averaged EEG (ERP) data. We also describe efforts to extend our methods to represent patterns inMEG data, as well as EM patterns in source (anatomical) space. The broader aim of this work is to design an ontology-based system to support cross-laboratory, cross-paradigm, and cross-modal integration of brain functional data. Tools developed for this project are implemented in MATLAB and are freely available on request.

The implicit function as squashing time model: a novel parallel nonlinear EEG analysis technique distinguishing mild cognitive impairment and Alzheimer's disease subjects with high degree of accuracy

Abstract: This paper presents the results obtained using a protocol based on special types of artificial neural networks (ANNs) assembled in a novel methodology able to compress the temporal sequence of electroencephalographic (EEG) data into spatial invariants for the automatic classification of mild cognitive impairment (MCI) and Alzheimer's disease (AD) subjects. With reference to the procedure reported in our previous study (2007), this protocol includes a new type of artificial organism, named TWIST. The working hypothesis was that compared to the results presented by the workgroup (2007); the new artificial organism TWIST could produce a better classification between AD and MCI. Material and methods. Resting eyes-closed EEG data were recorded in 180 AD patients and in 115 MCI subjects. The data inputs for the classification, instead of being the EEG data, were the weights of the connections within a nonlinear autoassociative ANN trained to generate the recorded data. The most relevant features were selected and coincidently the datasets were split in the two halves for the final binary classification (training and testing) performed by a supervised ANN. Results. The best results distinguishing between AD and MCI were equal to 94.10% and they are considerable better than the ones reported in our previous study (∼92%) (2007). Conclusion. The results confirm the working hypothesis that a correct automatic classification of MCI and AD subjects can be obtained by extracting spatial information content of the resting EEG voltage by ANNs and represent the basis for research aimed at integrating spatial and temporal information content of the EEG.

A concept for extending the applicability of constraint-induced movement therapy through motor cortex activity feedback using a neural prosthesis

Abstract: This paper describes a concept for the extension of constraint-induced movement therapy (CIMT) through the use of feedback of primary motor cortex activity. CIMT requires residual movement to act as a source of feedback to the patient, thus preventing its application to those with no perceptible movement. It is proposed in this paper that it is possible to provide feedback of the motor cortex effort to the patient by measurement with near infrared spectroscopy (NIRS). Significant changes in such effort may be used to drive rehabilitative robotic actuators, for example. This may provide a possible avenue for extending CIMT to patients hitherto excluded as a result of severity of condition. In support of such a paradigm, this paper details the current status of CIMT and related attempts to extend rehabilitation therapy through the application of technology. An introduction to the relevant haemodynamics is given including a description of the basic technology behind a suitable NIRS system. An illustration of the proposed therapy is described using a simple NIRS system driving a robotic arm during simple upper-limb unilateral isometric contraction exercises with healthy subjects.

Temporal and spatial features of single-trial EEG for brain-computer interface

Abstract: Brain-computer interface (BCI) systems create a novel communication channel from the brain to an output device bypassing conventional motor output pathways of nerves and muscles. Modern BCI technology is essentially based on techniques for the classification of single-trial brain signals. With respect to the topographic patterns of brain rhythm modulations, the common spatial patterns (CSPs) algorithm has been proven to be very useful to produce subject-specific and discriminative spatial filters; but it didn't consider temporal structures of event-related potentials which may be very important for single-trial EEG classification. In this paper, we propose a new framework of feature extraction for classification of hand movement imagery EEG. Computer simulations on real experimental data indicate that independent residual analysis (IRA) method can provide efficient temporal features. Combining IRA features with the CSP method, we obtain the optimal spatial and temporal features with which we achieve the best classification rate. The high classification rate indicates that the proposed method is promising for an EEG-based brain-computer interface.

Editorial: EEG/MEG signal processing

Abstract: Since its invention by the Hans Berger of the electroencephalography (EEG) in 1929, it was strong scientific curiosity in analysis of human brain activity. In fact, the electroencephalography (EEG) and magnetoencephalography (MEG) have developed into one of the most important and widely used quantitative diagnostic tools in analysis of brain signals and patterns. EEG and MEG potentially contain a rich source of information related to functional, physiological, and pathological status of the brain. In particularly, they are essential for the identification of mental disorders and brain rhythms extremely useful for the diagnosis and monitoring of brain activity and offer not only the functional but also pathological, physiological, and metabolic changes within the brain and perhaps other parts in the body. Recording and analysis of the EEG and MEG now involve a considerable amount of signal processing; for S/N enhancement, feature detection, source localization, automated classification, compression, hidden information extraction, and dynamic modeling. These involve a variety of innovative signal processing methods, including adaptive techniques, time-frequency and time-scale procedures, artificial neural networks and fuzzy logic, higher-order statistics and nonlinear schemes, fractals, hierarchical trees, Bayesian approaches, and parametric modeling. This special issue contributes to the current status of EEG and MEG signal processing and analysis, with particular regard to recent innovations. It reports some promising achievements by academic and commercial research institutions and individuals, and provides an insight into future developments within this exciting and challenging area of functional brain imaging. Noninvasive functional brain imaging has become an important tool used by neurophysiologists, cognitive psychologists, cognitive scientists, and other researchers interested in brain function. In the last five decades the technology of noninvasive functional imaging has flowered, and researchers today can choose from EEG, MEG, PET, SPECT, MRI, NIRS and fMRI. Each method has its own strengths and weaknesses. Development of signal processing tools mitigates the problems and alleviates some of the weaknesses. This issue includes the following contributions which cover a wide range of signal processing techniques for analysis, understanding, and recognition of EEG/MEG information. The first paper, “Canonical Source Reconstruction for MEG” by J. Mattout et al., describes a new, simple but efficient solution to the problem of reconstructing electromagnetic sources into a canonical or standard anatomical space. Electromagnetic lead fields are computed using the warped mesh; in conjunction with a spherical head-model (which does not rely on individual anatomy). The ensuing forward model is inverted using an empirical Bayesian scheme that was described previously in several publications. This enables the pooling of data from multiple subjects and the reporting of results in stereotactic coordinates. Furthermore, it allows the graceful fusion of fMRI and MEG data within the same anatomical framework. The second paper, “A subspace method for dynamical estimation of Evoked Potentials” by S. Georgiadis et al., describes method for single-channel trial-to-trial EP characteristics estimation. Prior information about phase-locked properties of the EPs is assessed by means of estimated signal subspace and eigenvalue decomposition. Then for those situations that dynamic fluctuations from stimulus-to-stimulus could be expected, prior information can be exploited by means of state-space modeling and recursive Bayesian mean square estimation methods (Kalman filtering and smoothing). The authors demonstrate that a few dominant eigenvectors of the data correlation matrix are able to model trend-like changes of some component of the EPs, and that Kalman smoother algorithm is to be preferred in terms of better tracking capabilities and mean square error reduction. They also demonstrate the effect of strong artifacts, particularly eye blinks, on the quality of the signal subspace and EP estimates by means of Independent Component Analysis (ICA) applied as a prepossessing step to the multichannel measurements. The third paper, “Inferring functional brain states using temporal evolution of regularized classifiers,” by A. Zhdanov et al., proposes a framework for functional brain state inference problem that utilizes the temporal information present in the brain signals. This application suggests that the relation between the regularization parameters and the temporal profile of the classifier helps improving the classifier accuracy. In the fourth paper, “Removing ocular movement artefacts by a Joint Smoothened Subspace Estimator (JSSE),” by R. Robert Phlypo et al., a joint smoothened subspace estimator calculates the low and high order statistic information subject to the constraint that the resulting estimated ocular movement artifact source is smooth in time domain. This results in combination of blind source separation with different order statistics. The results have been compared to those of well known blind source separation methods and have shown the capability of the system in mitigating the ocular artefacts automatically. The fifth contribution, “A framework to support automated classification and labeling of brain electromagnetic patterns,” by G. A. Frishkoff et al., focuses on patterns in averaged EEG (ERP) data to define high-level rules and concepts for ERP components and to design an automated data processing system that implements these rules. This is with a broader objective of designing an oncology-based system to support cross laboratory, cross paradigm, and cross modal integration of brain functional data. The next paper “Statistical modeling and analysis of laser-evoked potentials of electrocorticogram recordings from awake humans,” by Z. Chen et al., provides a comprehensive analysis of electrocorticogram recorded using invasive laser stimulation. Both averaging and single trial laser-evoked potentials (LEP) have been considered. Then the LEPs have been extracted from both types of trials, and the variations in power, amplitude, and latency have been studied using probabilistic modeling, factor analysis, independent component analysis, wavelet domain and quantitative and qualitative analyses. The seventh paper “A Novel constrained topographic independent component analysis for separation of epileptic seizure signals,” by Min Jing and Saeid Sanei addresses a constrained source separation method which exploits the correlation among the nearby brain sources as well as characteristics of the seizure signals in space and frequency domains to highlight the sources of interest. In this method the space-frequency characteristics of the data is utilized as the constraint term in the update equation of the topographic ICA system. The results clearly show that the synchronously generated seizure sources are grouped together. The next paper, “Clustering approach to long term spatio-temporal interactions in Epileptic Electroencephalograph,” by A. Hegde et al., attempts to identify the spatio-temporal interactions of an epileptic brain using an existing non-linear dependency measure based on a clustering approach. The mutual interactions have been analyzed using an index measure based on a self-organizing map (SOM) network. The results report a long term structural connectivity related to various seizure states. In addition, the authors have aimed at developing engineering tools to determine spatio-temporal groupings in a multivariate epileptic brain. The ninth paper, “Automatic Seizure Detection based on Time-Frequency Analysis and Artificial Neural Networks,” by A. T. Tzallas et al., uses an artificial neural network system for detection of epileptic seizures from a set of features estimated from time-frequency domain EEG data. Next paper, “Canonical decomposition of ictal scalp EEG and accurate source localisation: Principles and simulation study,” by M. De Vos et al., uses a dipole-based method for localization of epileptic seizure sources. In this method a canonical decomposition procedure extracts the seizure source by a three-way model assumption. The eleventh paper, “The implicit function as squashing time Model, a novel parallel nonlinear EEG analysis technique distinguishing mild cognitive impairment, Alzheimer's disease and normal aged subjects with high degree of accuracy,” by M. Buscema et al., introduces an ANN-based method in which the MCI and AD can be classified based on the spatial information content of the restino EEGs. In this procedure the ANNs do not use EEGs as the input; rather, the inputs for the classification are the weights of the connections within the ANN to generate the recorded EEG data. The introduced TWIST system selects the best features. The last paper, “The P300 as a marker of waning attention and error propensity,” by Avijit Kumar Datta, Rhodri Cusack, Kari Hawkins, Joost Heutink, Christopher Rorden, Ian Robertson, and Tom Manly, studies and examines the variation of P300 ERP with respect to the error in responding to the stimuli. During the course of this research it has been found that errors are associated with significant reduction in the amplitude of preceding P300, and the fluctuations in P300 amplitude across the task formed a reliable associate of individual error propensity, supporting its use as a marker of our sustained control over action.

Clustering approach to quantify long-term spatio-temporal interactions in epileptic intracranial electroencephalography

Abstract: Abnormal dynamical coupling between brain structures is believed to be primarily responsible for the generation of epileptic seizures and their propagation. In this study, we attempt to identify the spatio-temporal interactions of an epileptic brain using a previously proposed nonlinear dependency measure. Using a clustering model, we determine the average spatial mappings in an epileptic brain at different stages of a complex partial seizure. Results involving 8 seizures from 2 epileptic patients suggest that there may be a fixed pattern associated with regional spatio-temporal dynamics during the interictal to pre-post-ictal transition.

High-resolution movement EEG classification

Abstract: The aim of the contribution is to analyze possibilities of high-resolution movement classification using human EEG. For this purpose, a database of the EEG recorded during right-thumb and little-finger fast flexion movements of the experimental subjects was created. The statistical analysis of the EEG was done on the subject's basis instead of the commonly used grand averaging. Statistically significant differences between the EEG accompanying movements of both fingers were found, extending the results of other so far published works. The classifier based on hidden Markov models was able to distinguish between movement and resting states (classification score of 94-100%), but it was unable to recognize the type of the movement. This is caused by the large fraction of other (nonmovement related) EEG activities in the recorded signals. A classification method based on advanced EEG signal denoising is being currently developed to overcome this problem.

Statistical modeling and analysis of laser-evoked potentials of electrocorticogram recordings from awake humans

Abstract: This article is devoted to statistical modeling and analysis of electrocorticogram (ECoG) signals induced by painful cutaneous laser stimuli, which were recorded from implanted electrodes in awake humans. Specifically, with statistical tools of factor analysis and independent component analysis, the pain-induced laser-evoked potentials (LEPs) were extracted and investigated under different controlled conditions. With the help of wavelet analysis, quantitative and qualitative analyses were conducted regarding the LEPs' attributes of power, amplitude, and latency, in both averaging and single-trial experiments. Statistical hypothesis tests were also applied in various experimental setups. Experimental results reported herein also confirm previous findings in the neurophysiology literature. In addition, single-trial analysis has also revealed many new observations that might be interesting to the neuroscientists or clinical neurophysiologists. These promising results show convincing validation that advanced signal processing and statistical analysis may open new avenues for future studies of such ECoG or other relevant biomedical recordings.