Roman Rosipal

Brain-computer interfaces for 1-D and 2-D cursor control: designs using volitional control of the EEG spectrum or steady-state visual evoked potentials

We have developed and tested two electroencephalogram (EEG)-based brain-computer interfaces (BCI) for users to control a cursor on a computer display. Our system uses an adaptive algorithm, based on kernel partial least squares classification (KPLS), to associate patterns in multichannel EEG frequency spectra with cursor controls. Our first BCI, Target Practice, is a system for one-dimensional device control, in which participants use biofeedback to learn voluntary control of their EEG spectra. Target Practice uses a KPLS classifier to map power spectra of 62-electrode EEG signals to rightward or leftward position of a moving cursor on a computer display. Three subjects learned to control motion of a cursor on a video display in multiple blocks of 60 trials over periods of up to six weeks. The best subjects average skill in correct selection of the cursor direction grew from 58% to 88% after 13 training sessions. Target Practice also implements online control of two artifact sources: 1) removal of ocular artifact by linear subtraction of wavelet-smoothed vertical and horizontal electrooculograms (EOG) signals, 2) control of muscle artifact by inhibition of BCI training during periods of relatively high power in the 40-64 Hz band. The second BCI, Think Pointer, is a system for two-dimensional cursor control. Steady-state visual evoked potentials (SSVEP) are triggered by four flickering checkerboard stimuli located in narrow strips at each edge of the display. The user attends to one of the four beacons to initiate motion in the desired direction. The SSVEP signals are recorded from 12 electrodes located over the occipital region. A KPLS classifier is individually calibrated to map multichannel frequency bands of the SSVEP signals to right-left or up-down motion of a cursor on a computer display. The display stops moving when the user attends to a central fixation point. As for Target Practice, Think Pointer also implements wavelet-based online removal of ocular artifact; however, in Think Pointer muscle artifact is controlled via adaptive normalization of the SSVEP. Training of the classifier requires about 3 min. We have tested our system in real-time operation in three human subjects. Across subjects and sessions, control accuracy ranged from 80% to 100% correct with lags of 1-5 s for movement initiation and turning. We have also developed a realistic demonstration of our system for control of a moving map display (http://ti.arc.nasa.gov/).

Prediction of Chaotic Time-Series with a Resource-Allocating RBF Network

One of the main problems associated with artificial neural networks on-line learning methods is the estimation of model order. In this paper, we report about a new approach to constructing a resource-allocating radial basis function network exploiting weights adaptation using recursive least-squares technique based on Givens QR decomposition. Further, we study the performance of pruning strategy we introduced to obtain the same prediction accuracy of the network with lower model order. The proposed methods were tested on the task of Mackey-Glass time-series prediction. Order of resulting networks and their prediction performance were superior to those previously reported by Platt [12].

Measures and Models for Predicting Cognitive Fatigue

We measured multichannel EEG spectra during a continuous mental arithmetic task and created statistical learning models of cognitive fatigue for single subjects. Sixteen subjects (4 F, 18-38 y) viewed 4-digit problems on a computer, solved the problems, and pressed keys to respond (inter-trial interval = 1 s). Subjects performed until either they felt exhausted or three hours had elapsed. Pre- and post-task measures of mood (Activation Deactivation Adjective Checklist, Visual Analogue Mood Scale) confirmed that fatigue increased and energy decreased over time. We examined response times (RT); amplitudes of ERP components N1, P2, and P300, readiness potentials; and power of frontal theta and parietal alpha rhythms for change as a function of time. Mean RT rose from 6.7 s to 7.9 s over time. After controlling for or rejecting sources of artifact such as EOG, EMG, motion, bad electrodes, and electrical interference, we found that frontal theta power rose by 29% and alpha power rose by 44% over the course of the task. We used 30-channel EEG frequency spectra to model the effects of time in single subjects using a kernel partial least squares (KPLS) classifier. We classified 13-s long EEG segments as being from the first or last 15 minutes of the task, using random sub-samples of each class. Test set accuracies ranged from 91% to 100% correct. We conclude that a KPLS classifier of multichannel spectral measures provides a highly accurate model of EEG-fatigue relationships and is suitable for on-line applications to neurological monitoring.

Extracting more information from EEG recordings for a better description of sleep

We are introducing and validating an EEG data-based model of the sleep process with an arbitrary number of different sleep stages and a high time resolution allowing modeling of sleep microstructure. In contrast to the standard practice of sleep staging, defined by scoring rules, we describe sleep via posterior probabilities of a finite number of states, not necessarily reflecting the traditional sleep stages. To test the proposed probabilistic sleep model (PSM) for validity, we correlate statistics derived from the state posteriors with the results of psychometric tests, physiological variables and questionnaires collected before and after sleep. Considering short, in this study 3 s long, data window the PSM allows describing the sleep process on finer time scale in comparison to the traditional sleep staging based on 20 or 30 s long data segments visual inspection. By combining sleep states and using two measures derived from the posterior curves we show that the average absolute correlations between the measures and subjective and objective sleep quality measures are considerably higher when compared with the analogous measures derived from hypnograms based on sleep staging. In most cases these differences are significant. The results obtained with the PSM support its wider use in sleep process modeling research and these results also suggest that EEG signals contain more information about sleep than what sleep profiles based on discrete stages can reveal. Therefore the standardized scoring of sleep may not be sufficient to reveal important sleep changes related to subjective and objective sleep quality indexes. The proposed PSM represents a promising alternative.

On the Individuality of Sleep EEG Spectra

Research in recent years has supported the hypothesis that many properties of the electroencephalogram (EEG) are specific to an individual. In this study, the intra- and inter-individual variations of sleep EEG signals were investigated. This was carried out by analyzing the stability of the average EEG spectra individually computed for the Rechtschaffen and Kales (RK) sleep stages. Six EEG channels were used to account for the topographical aspect of the analysis. Validity of the results was supported by considering a wide dataset of 174 subjects with normal sleep. Subjects spent two consecutive nights in the sleep laboratory during which EEG recordings were obtained. High similarity between average spectra of two consecutive nights was found considering an individual. More than 89% of the second night recordings were correctly assigned to their counterparts of the first night. The average spectra of sleep EEG computed for each RK sleep stage have shown a high degree of individuality.

Estimation of Human Signal Detection Performance from Event-Related Potentials Using Feed-Forward Neural Network Model

We compared linear and neural network models for estimating human signal detection performance from event-related potentials (ERP) elicited by task-relevant stimuli. Data consisted of ERPs and performance measures from five trained operators who monitored a radar display and detected and classified visual symbols at three contrast levels. The performance measure (PF1) was a composite of accuracy, speed, and confidence of classification responses. The ERPs, which were elicited by the symbols, were represented in the interval 0-1500 ms post-stimulus at three midline electrodes (Fz, Cz, Pz) using either principal component analysis (PCA) factors or coefficients of autoregressive (AR) models. We constructed individual models of PF1 from both PCA and AR representations using either linear regression or radial basis function (RBF) networks. Applying the normalized mean square error of approximation as a criterion, we found that the PCA representation was superior to AR and that RBF networks estimated PF1 much more accurately than linear regression. This suggests that nonlinear methods combined with suitable ERP feature extraction can provide more accurate and reliable estimates of display-monitoring performance than linear models.

Time Alignment as a Necessary Step in the Analysis of Sleep Probabilistic Curves

Abstract Sleep can be characterised as a dynamic process that has a finite set of sleep stages during the night. The standard Rechtschaffen and Kales sleep model produces discrete representation of sleep and does not take into account its dynamic structure. In contrast, the continuous sleep representation provided by the probabilistic sleep model accounts for the dynamics of the sleep process. However, analysis of the sleep probabilistic curves is problematic when time misalignment is present. In this study, we highlight the necessity of curve synchronisation before further analysis. Original and in time aligned sleep probabilistic curves were transformed into a finite dimensional vector space, and their ability to predict subjects’ age or daily measures is evaluated. We conclude that curve alignment significantly improves the prediction of the daily measures, especially in the case of the S2-related sleep states or slow wave sleep.

Estimation of Sleep Quality by Using Microstructure Profiles

Polysomnograhy is the standard method for objectively measuring sleep, both in patient diagnostics in the sleep laboratory and in clinical research. However, the correspondence between this objective measurement and a person’s subjective assessment of the sleep quality is surprisingly small, if existent. Considering standard sleep characteristics based on the Rechtschaffen and Kales sleep models and the Self-rating Sleep and Awakening Quality scale (SSA), the observed correlations are at most 0.35. An alternative way of sleep modelling - the probabilistic sleep model (PSM) characterises sleep with probability values of standard sleep stages Wake, S1, S2, slow wave sleep (SWS) and REM operating on three second long time segments. We designed sleep features based on the PSM which correspond to the standard sleep characteristics or reflect the dynamical behaviour of probabilistic sleep curves. The main goal of this work is to show whether the continuous sleep representation includes more information about the subjectively experienced quality of sleep than the traditional hypnogram. Using a linear combination of sleep features an improvement in correlation with the subjective sleep quality scores was observed in comparison to the case when a single sleep feature was considered.

ID 290 – Differences in sleep microstate curves among healthy sleepers and patients after stroke

Objective Sleep deprivation, whether from disorder or lifestyle, poses a significant risk in daytime performance. Ischemic stroke resulting in cerebral lesions is a well-known acute disorder that leaves affected patients strongly vulnerable to sleep disturbances that often lead to the above-mentioned impairments. The aim of this study is to identify objective sleep patterns being potential sources of disturbed sleep in stroke patients. Methods To overcome the well-known limits of the standardized sleep scoring into several discrete sleep stages we employed an EEG data-based probabilistic model of sleep with an arbitrary number of different sleep stages – sleep microstates – and a high time resolution. The probabilistic sleep model (PSM) characterizes sleep by posterior probabilities curves. On a wide collection of sleep recordings from healthy subjects and stroke patients we applied functional data clustering methods to sleep microstate curves of the PSM. Results We found differences between stroke patients and healthy subjects in sleep microstates associated with slow wave sleep. Considering weighted combinations of microstates a better separation of the two groups was obtained. We observed a connection between sleep structure and sleep quality questionnaires as well as a set of tests reflecting subjects’ daytime cognitive performance.

ID 306 – Mirror-box training in healthy subjects and a patient with hemiparesis

Objective Mirror therapy (MT) is an approach of neurorehabilitation improving motor functions after stroke. MT represents a mental process by which an individual rehearses a given motor action by reflecting movements of the non-paretic side in a mirror as if it were the affected side. Although a number of small-scale research studies have shown encouraging results, there is no clear consensus about the effectiveness of the therapy. The aim of this study is to investigate objective changes in EEG after MT. Methods A set of seven healthy volunteers carried-out five mirror-box training sessions. The same training is carried-out twice a week with a patient with hemiparesis for more than six months. The eleven channels of EEG placed over the sensorimotor and left occipital cortex are recorded. In addition to the standard power spectral analysis of EEG we decompose EEG into elemental components or “atoms.” We estimate EEG atoms using multiway parallel factor analysis (PARAFAC) for modeling. Results Compering resting EEG prior and after training we found statistically significant increase of the motor-related oscillatory μ -rhythm in a hemiparetic patient. Atomic decomposition of EEG shows stable spatio-frequency components of motor-related synchronization and desynchronization of EEG in a hemisphere contralateral to the mirror-box.