Study of on-line adaptive discriminant analysis for EEG-based brain computer interfaces.

A study of different on-line adaptive classifiers, using various feature types is presented. Motor imagery brain computer interface (BCI) experiments were carried out with 18 naive able-bodied subjects. Experiments were done with three two-class, cue-based, electroencephalogram (EEG)-based systems. Two continuously adaptive classifiers were tested: adaptive quadratic and linear discriminant analysis. Three feature types were analyzed, adaptive autoregressive parameters, logarithmic band power estimates and the concatenation of both. Results show that all systems are stable and that the concatenation of features with continuously adaptive linear discriminant analysis classifier is the best choice of all. Also, a comparison of the latter with a discontinuously updated linear discriminant analysis, carried out in on-line experiments with six subjects, showed that on-line adaptation performed significantly better than a discontinuous update. Finally a static subject-specific baseline was also provided and used to compare performance measurements of both types of adaptation.

A fully automated correction method of EOG artifacts in EEG recordings.

OBJECTIVE: A fully automated method for reducing EOG artifacts is presented and validated. METHODS: The correction method is based on regression analysis and was applied to 18 recordings with 22 channels and approx. 6 min each. Two independent experts scored the original and corrected EEG in a blinded evaluation. RESULTS: The expert scorers identified in 5.9% of the raw data some EOG artifacts; 4.7% were corrected. After applying the EOG correction, the expert scorers identified in another 1.9% of the data some EOG artifacts, which were not recognized in the uncorrected data. CONCLUSIONS: The advantage of a fully automated reduction of EOG artifacts justifies the small additional effort of the proposed method and is a viable option for reducing EOG artifacts. The method has been implemented for offline and online analysis and is available through BioSig, an open source software library for biomedical signal processing. SIGNIFICANCE: Visual identification and rejection of EOG-contaminated EEG segments can miss many EOG artifacts, and is therefore not sufficient for removing EOG artifacts. The proposed method was able to reduce EOG artifacts by 80%.

A fully on-line adaptive BCI.

A viable fully on-line adaptive brain computer interface (BCI) is introduced. On-line experiments with nine naive and able-bodied subjects were carried out using a continuously adaptive BCI system. The data were analyzed and the viability of the system was studied. The BCI was based on motor imagery, the feature extraction was performed with an adaptive autoregressive model and the classifier used was an adaptive quadratic discriminant analysis. The classifier was on-line updated by an adaptive estimation of the information matrix (ADIM). The system was also able to provide continuous feedback to the subject. The success of the feedback was studied analyzing the error rate and mutual information of each session and this analysis showed a clear improvement of the subject's control of the BCI from session to session.

15 years of BCI research at Graz University of Technology: current projects.

Over the last 15 years, the Graz Brain-Computer Interface (BCI) has been developed and all components such as feature extraction and classification, mode of operation, mental strategy, and type of feedback have been investigated. Recent projects deal with the development of asynchronous BCIs, the presentation of feedback and applications for communication and control.

Mu rhythm (de)synchronization and EEG single-trial classification of different motor imagery tasks.

We studied the reactivity of EEG rhythms (mu rhythms) in association with the imagination of right hand, left hand, foot, and tongue movement with 60 EEG electrodes in nine able-bodied subjects. During hand motor imagery, the hand mu rhythm blocked or desynchronized in all subjects, whereas an enhancement of the hand area mu rhythm was observed during foot or tongue motor imagery in the majority of the subjects. The frequency of the most reactive components was 11.7 Hz +/- 0.4 (mean +/- SD). While the desynchronized components were broad banded and centered at 10.9 Hz +/- 0.9, the synchronized components were narrow banded and displayed higher frequencies at 12.0 Hz +/- 1.0. The discrimination between the four motor imagery tasks based on classification of single EEG trials improved when, in addition to event-related desynchronization (ERD), event-related synchronization (ERS) patterns were induced in at least one or two tasks. This implies that such EEG phenomena may be utilized in a multi-class brain-computer interface (BCI) operated simply by motor imagery.

Adaptive on-line classification for EEG-based brain computer interfaces with AAR parameters and band power estimates.

We present the result of on-line feedback Brain Computer Interface experiments using adaptive and non-adaptive feature extraction methods with an on-line adaptive classifier based on Quadratic Discriminant Analysis. Experiments were performed with 12 naïve subjects, feedback was provided from the first moment and no training sessions were needed. Experiments run in three different days with each subject. Six of them received feedback with Adaptive Autoregressive parameters and the rest with logarithmic Band Power estimates. The study was done using single trial analysis of each of the sessions and the value of the Error Rate and the Mutual Information of the classification were used to discuss the results. Finally, it was shown that even subjects starting with a low performance were able to control the system in a few hours: and contrary to previous results no differences between AAR and BP estimates were found.

Interrater reliability between scorers from eight European sleep laboratories in subjects with different sleep disorders.

Interrater variability of sleep stage scorings is a well-known phenomenon. The SIESTA project offered the opportunity to analyse interrater reliability (IRR) between experienced scorers from eight European sleep laboratories within a large sample of patients with different (sleep) disorders: depression, general anxiety disorder with and without non-organic insomnia, Parkinson's disease, period limb movements in sleep and sleep apnoea. The results were based on 196 recordings from 98 patients (73 males: 52.3 +/- 12.1 years and 25 females: 49.5 +/- 11.9 years) for which two independent expert scorings from two different laboratories were available. Cohen's kappa was used to evaluate the IRR on the basis of epochs and intraclass correlation was used to analyse the agreement on quantitative sleep parameters. The overall level of agreement when five different stages were distinguished was kappa = 0.6816 (76.8%), which in terms of kappa reflects a 'substantial' agreement (Landis and Koch, 1977). For different groups of patients kappa values varied from 0.6138 (Parkinson's disease) to 0.8176 (generalized anxiety disorder). With regard to (sleep) stages, the IRR was highest for rapid eye movement (REM), followed by Wake, slow-wave sleep (SWS), non-rapid eye movement 2 (NREM2) and NREM1. The results of regression analysis showed that age and sex only had a statistically significant effect on kappa when the (sleep) stages are considered separately. For NREM2 and SWS a statistically significant decrease of IRR with age has been observed and the IRR for SWS was lower for males than for females. These variations of IRR most probably reflect changes of the sleep electroencephalography (EEG) with age and gender.

Graz-BCI: state of the art and clinical applications.

The Graz-brain-computer interface (BCI) is a cue-based system using the imagery of motor action as the appropriate mental task. Relevant clinical applications of BCI-based systems for control of a virtual keyboard device and operations of a hand orthosis are reported. Additionally, it is demonstrated how information transfer rates of 17 b/min can be acquired by real time classification of oscillatory activity.

Estimating the mutual information of an EEG-based Brain-Computer Interface.

An EEG-based Brain-Computer Interface (BCI) could be used as an additional communication channel between human thoughts and the environment. The efficacy of such a BCI depends mainly on the transmitted information rate. Shannon's communication theory was used to quantify the information rate of BCI data. For this purpose, experimental EEG data from four BCI experiments was analyzed off-line. Subjects imaginated left and right hand movements during EEG recording from the sensorimotor area. Adaptive autoregressive (AAR) parameters were used as features of single trial EEG and classified with linear discriminant analysis. The intra-trial variation as well as the inter-trial variability, the signal-to-noise ratio, the entropy of information, and the information rate were estimated. The entropy difference was used as a measure of the separability of two classes of EEG patterns.

Rapid prototyping of an EEG-based brain-computer interface (BCI).

The electroencephalogram (EEG) is modified by motor imagery and can be used by patients with severe motor impairments (e.g., late stage of amyotrophic lateral sclerosis) to communicate with their environment. Such a direct connection between the brain and the computer is known as an EEG-based brain-computer interface (BCI). This paper describes a new type of BCI system that uses rapid prototyping to enable a fast transition of various types of parameter estimation and classification algorithms to real-time implementation and testing. Rapid prototyping is possible by using Matlab, Simulink, and the Real-Time Workshop. It is shown how to automate real-time experiments and perform the interplay between on-line experiments and offline analysis. The system is able to process multiple EEG channels on-line and operates under Windows 95 in real-time on a standard PC without an additional digital signal processor (DSP) board. The BCI can be controlled over the Internet, LAN or modem. This BCI was tested on 3 subjects whose task it was to imagine either left or right hand movement. A classification accuracy between 70% and 95% could be achieved with two EEG channels after some sessions with feedback using an adaptive autoregressive (AAR) model and linear discriminant analysis (LDA).

Current trends in Graz Brain-Computer Interface (BCI) research.

This paper 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.

Artifact processing in computerized analysis of sleep EEG - a review.

Quantitative analysis of sleep EEG data can provide valuable additional information in sleep research. However, analysis of data contaminated by artifacts can lead to spurious results. Thus, the first step in realizing an automatic sleep analysis system is the implementation of a reliable and valid artifact processing strategy. This strategy should include: (1) high-quality recording techniques in order to minimize the occurrence of avoidable artifacts (e.g. technical artifacts); (2) artifact minimization procedures in order to minimize the loss of data by estimating the contribution of different artifacts in the EEG recordings, thus allowing the calculation of the 'corrected' EEG (e.g. ocular and ECG interference), and finally (3) artifact identification procedures in order to define epochs contaminated by remaining artifacts (e.g. movement and muscle artifacts). Therefore, after a short description of the types of artifacts in the sleep EEG and some typical examples obtained in different sleep stages, artifact minimization and identification procedures will be reviewed.

Enhancement of left-right sensorimotor EEG differences during feedback-regulated motor imagery.

EEG feedback studies demonstrate that human subjects can learn to regulate electrocortical activity over the sensorimotor cortex. Such self-induced EEG changes could serve as control signals for a Brain Computer Interface. The experimental task of the current study was to imagine either right-hand or left-hand movement depending on a visual cue stimulus on a computer monitor. The performance of this imagination task was controlled on-line by means of a feedback bar that represented the current EEG pattern. EEG signals recorded from left and right central recording sites were used for on-line classification. For the estimation of EEG parameters, an adaptive autoregressive model was applied, and a linear discriminant classifier was used to discriminate between EEG patterns associated with left and right motor imagery. Four trained subjects reached 85% to 95% classification accuracy in the course of the experimental sessions. To investigate the impact of continuous feedback presentation, time courses of band power changes were computed for subject-specific frequency bands. The EEG data revealed a significant event-related desynchronization over the contralateral central area in all subjects. Two subjects simultaneously displayed synchronization of EEG activity (event-related synchronization) over the ipsilateral side. During feedback presentation the event-related desynchronization/event-related synchronization patterns showed increased hemispheric asymmetry compared to initial control sessions without feedback.

Design of an EEG-based brain-computer interface (BCI) from standard components running in real-time under Windows.

An EEG-based brain-computer interface (BCI) is a direct connection between the human brain and the computer. Such a communication system is needed by patients with severe motor impairments (e.g. late stage of Amyotrophic Lateral Sclerosis) and has to operate in real-time. This paper describes the selection of the appropriate components to construct such a BCI and focuses also on the selection of a suitable programming language and operating system. The multichannel system runs under Windows 95, equipped with a real-time Kernel expansion to obtain reasonable real-time operations on a standard PC. Matlab controls the data acquisition and the presentation of the experimental paradigm, while Simulink is used to calculate the recursive least square (RLS) algorithm that describes the current state of the EEG in real-time. First results of the new low-cost BCI show that the accuracy of differentiating imagination of left and right hand movement is around 95%.

Quality control of polysomnographic sleep data by histogram and entropy analysis.

OBJECTIVE AND METHODS: Sixteen polysomnographic recordings from 8 European sleep laboratories were analyzed. The histogram analysis was used to introduce quality control of all-night EEG recordings. RESULTS: It was found that the header information does not always provide the real saturation values of the recording equipment. The entropy measure was used for the quantitative analysis of the dynamic range of routinely used polysomnographic recorders. It was found that the recording equipment provides EEG data with entropy in the range of 8-11 bits. CONCLUSION: In the all-night sleep EEG were observed non-linearities. It is recommended that the equipment provide the saturation values in order to apply automated overflow detection.

Separability of EEG signals recorded during right and left motor imagery using adaptive autoregressive parameters.

Electroencephalogram (EEG) recordings during right and left motor imagery can be used to move a cursor to a target on a computer screen. Such an EEG-based brain-computer interface (BCI) can provide a new communication channel to replace an impaired motor function. It can be used by, e.g., patients with amyotrophic lateral sclerosis (ALS) to develop a simple binary response in order to reply to specific questions. Four subjects participated in a series of on-line sessions with an EEG-based cursor control. The EEG was recorded from electrodes overlying sensory-motor areas during left and right motor imagery. The EEG signals were analyzed in subject-specific frequency bands and classified on-line by a neural network. The network output was used as a feedback signal. The on-line error (100%-perfect classification) was between 10.0 and 38.1%. In addition, the single-trial data were also analyzed off-line by using an adaptive autoregressive (AAR) model of order 6. With a linear discriminant analysis the estimated parameters for left and right motor imagery were separated. The error rate obtained varied between 5.8 and 32.8% and was, on average, better than the on-line results. By using the AAR-model for on-line classification an improvement in the error rate can be expected, however, with a classification delay around 1 s.