Showing papers by "Gert Pfurtscheller published in 2000"

Optimal spatial filtering of single trial EEG during imagined hand movement

Abstract: The development of an electroencephalograph (EEG)-based brain-computer interface (BCI) requires rapid and reliable discrimination of EEG patterns, e.g., associated with imaginary movement. One-sided hand movement imagination results in EEG changes located at contra- and ipsilateral central areas. The authors demonstrate that spatial filters for multichannel EEG effectively extract discriminatory information from two populations of single-trial EEG, recorded during left- and right-hand movement imagery. The best classification results for three subjects are 90.8%, 92.7%, and 99.7%. The spatial filters are estimated from a set of data by the method of common spatial patterns and reflect the specific activation of cortical areas. The method performs a weighting of the electrodes according to their importance for the classification task. The high recognition rates and computational simplicity make it a promising method for an EEG-based brain-computer interface.

Current trends in Graz brain-computer interface (BCI) research

Abstract: Describes a research approach to develop a brain-computer interface (BCI) based on recognition of subject-specific EEG patterns. EEG signals recorded from sensorimotor areas during mental imagination of specific movements are classified on-line and used e.g. for cursor control. In a number of on-line experiments, various methods for EEG feature extraction and classification have been evaluated.

Real-time EEG analysis with subject-specific spatial patterns for a brain-computer interface (BCI)

Abstract: Electroencephalogram (EEG) recordings during right and left motor imagery allow one to establish a new communication channel for, e.g., patients with amyotrophic lateral sclerosis. Such an EEG-based brain-computer interface (BCI) can be used to develop a simple binary response for the control of a device. Three subjects participated in a series of on-line sessions to test if it is possible to use common spatial patterns to analyze EEG in real time in order to give feedback to the subjects. Furthermore, the classification accuracy that can be achieved after only three days of training was investigated. The patterns are estimated from a set of multichannel EEG data by the method of common spatial patterns and reflect the specific activation of cortical areas. By construction, common spatial patterns weight each electrode according to its importance to the discrimination task and suppress noise in individual channels by using correlations between neighboring electrodes. Experiments with three subjects resulted in an error rate of 2, 6 and 14% during on-line discrimination of left- and right-hand motor imagery after three days of training and make common spatial patterns a promising method for an EEG-based brain-computer interface.

Using time-dependent neural networks for EEG classification

Abstract: This paper compares two different topologies of neural networks. They are used to classify single trial electroencephalograph (EEG) data from a brain-computer interface (BCI). A short introduction to time series classification is given, and the used classifiers are described. Standard multilayer perceptrons (MLPs) are used as a standard method for classification. They are compared to finite impulse response (FIR) MLPs, which use FIR filters instead of static weights to allow temporal processing inside the classifier. A theoretical comparison of the two architectures is presented. The results of a BCI experiment with three different subjects are given and discussed. These results demonstrate the higher performance of the FIR MLP compared with the standard MLP.

Spatiotemporal ERD/ERS patterns during voluntary movement and motor imagery.

Abstract: Publisher Summary This chapter discusses the three phases during voluntary, self-paced movements—preparation, execution, and recovery. Each of these phases has its characteristic spatiotemporal ERD/ERS pattern. The preparatory phase is characterized by an onset of mu event-related desynchronization (ERD) prior to voluntary movement with a contralateral preponderance. The central beta desynchronization starts later around one second before movement onset, with a clear contralateral dominance. The Execution of movement is accompanied by a bilateral pattern of mu and central beta desynchronization with a clear focus close to the corresponding cortical representation area. In addition to this ERD, an enhancement of gamma band activity can be found parallel with the motor act. One important feature of this gamma ERS is its cortical topography concomitant with the functional anatomy of the sensorimotor cortex. Embedded in desynchronized mu rhythm are bursts of beta oscillations (post-movement beta ERS) focused to the primary motor area. Beta ERS is of special interest because of its strict somatotopic organization, its good signal (beta ERS)-to-noise (EEG with desynchronized mu rhythm) ratio and its coincidence with a reduced corticospinal excitability. The results on motor imagery can be interpreted such that execution and imagination of movement involve the same cortical network in the corresponding representation area.

A criterion for adaptive autoregressive models

Abstract: A criterion, similar to the information criterion of a stationary autoregressive (AR) model, is introduced for an adaptive (non-stationary) autoregressive model. It is applied to nonstationary EEG data. It is shown that the criterion can be used to determine the update coefficient, the model order and the estimation algorithm.

Describing the sleep EEG with an Adaptive Autoregressive Model

Abstract: Figure 1: Sleep analysis using AAR parameters (healthy subject). On top, the hypnogram scored by an expert is shown. Below, the classification with AAR parameters using channels C3-M2 and C4-M1 is given for deep sleep (green line), REM (red line) and awake (blue line) – the highest curve indicates the appropriate sleep stage. The bottom plot shows the variance of the inverse filtered process (logarithmic scale). Spikes indicate artefacts and transient events. EEG processing The EEG of polygraphic recordings (SIESTA database)3 from eight European sleep labs was analysed; ECG artefacts and line interference were minimised with regression analysis and 50Hz notch filtering. The data were downsampled to 100Hz. Next, the AAR parameters were estimated with Kalman filtering assuming a multivariate random walk of AAR parameters2,4.

Describing the sleep EEG with an Adaptive

Abstract: Summary Summary The spectral information of the sleep EEG is an important indicator for the sleep stage1. Adaptive autoregressive parameters can describe the time-varying spectrum. The AR spectrum is a maximum entropy spectral estimator, which is optimal with respect to the number of parameters. No selection of frequency bands is required if the AR parameters are combined by a classifier. Adaptive estimation algorithms are useful for the on-line and real- time sleep analysis2.