J. Kalcher

40-Hz oscillations during motor behavior in man

40-Hz oscillations were measured during finger, toe and tongue movement using an electrode array of 56 electrodes over the pre and post central areas. Each movement was made 150 times in intervals of 12 s. The average power increase in narrow frequency bands between 8 and 40 Hz was then calculated and the topographical distribution studied. 40-Hz oscillations were only found contralateral over the hand area for finger movements, close to the vertex for toe movements and bilateral symmetrical for tongue movements. The maxima of the 40-Hz oscillations occurred before movement onset.

Graz Brain-Computer Interface (BCI) II

This paper describes the new setup of the Graz Brain-Computer Interface (BCI) system II, which is based on on-line classification of EEG patterns to determine which of three kinds of movement is planned by a subject. This classification can be exploited for on-line control which may constitute a great help for handicapped persons in the future.

EEG classification by learning vector quantization.

EEG classification using Learning Vector Quantization (LVQ) is introduced on the basis of a Brain-Computer Interface (BCI) built in Graz, where a subject controlled a cursor in one dimension on a monitor using potentials recorded from the intact scalp. The method of classification with LVQ is described in detail along with first results on a subject who participated in four on-line cursor control sessions. Using this data, extensive off-line experiments were performed to show the influence of the various parameters of the classifier and the extracted features of the EEG on the classification results.

A new approach to a brain-computer-interface (BCI) based on Learning Vector Quantization (LVQ3)

Planning and preparing voluntary finger movements result in a specific topographical pattern of event-related desynchronization (ERD) in the alpha band. These patterns generated for planning left and right hand movements show large enough differences to be seperable by a Learning Vector Quantizer (LVQ). This paper describes one-dimensional control of a cursor on a computer monitor based on the differentiation of two cortical activation patterns measured by two EEG channels.

Graz brain-computer interface: an EEG-based cursor control system

.Abstmcf ~ The idea of n new cnnimunicntion device a BninComputer Interface (BCI) for handicnppd penons is io record bioelectrical signals (EEC) on the intact scalp and use the cln%sificaiion of these signals for control or devices. This pnper discusses ongoing research in this neld and reports on a system developed in C m where EEC. i s used to control n cumor on n ntoniior in one dimension.

EEG-abhängige Steuerung von Cursorbewegungen. Voraussetzungen für ein Brain Computer Interface

Hin Bia in Computer Interface (BCI) soll durch die Ableitung bioelektrischer Signale vom intakten Schädel eine direkte Verbindung des Gehirns mit einem Computer herstellen. Ein solches BCI muß die Klassifizierung von verschiedenen EEG-Mustern in Echtzeit ermöglichen und kann damit für Steuerungsaufgaben, wie z.B. in Zukunft eine Prothesensteuerung bei bewegungsunfähigen Schwerstbehinderten, herangezogen werden. Im folgenden werden Prinzip und erste Ergebnisse des in Graz entwickelten BCI vorgestellt.

On-line Learning With Learning Vector Quantization; A Case Study Of EEG Classification

Real-time classification, e.g. of EEG, is one possible application of the Learning Vector Quantizer (LVQ) [1]. Its main advantage over other classifiers is its simplicity and speed but also the possibility for on-line learning. Usually, real-time EEG classifiers must be created off-line on the basis of a seperate recording. It would be preferable if the classifier could create itself on-line in a training session, i.e. start from a very sub-optimal initial state, e.g. using a classifier of another subject, and train itself on-line. Data recorded in three subjects during sessions, where a cursor was controlled in real-time based on EEG classification (Graz Brain-Computer Interface, BCI) [2], are examined in off-line simulations. Each subject participated in 4–6 sessions and the subject-dependent LVQs were updated between sessions to improve their generalization ability. Training LVQs on these data sets with varying values of the learning parameter α, suitable parameter ranges are derived for performances which are comparable to those obtained during the recording. The simulation results show that LVQ1 is a learning algorithm which is well suited for on-line learning because of a number of facilities: (1) LVQ is a very fest and well-understood classification method. Speed is an important factor when EEG classification is carried out in real-time. (2) On-line learning can be incorporated without much additional expense: only one reference vector (the winner) must be updated (either drawn further towards the current input vector or pushed slightly away), therefore the additional calculation time only depends on the input vector dimension (in our case: 10) but not on the number of reference vectors used (usuali’ about 8). Note that this would be different if we used a Multi-Layer Perceptron: the error has to be backpropagated through the whole network and therefore the time for calculation depends on the topology (the size) of the network. (3) The amount of update can be controlled via the learning parameter α. As a rule of thumb, α should range between 0.001 and 0.01, depending on the performance in former sessions. For the first session, a big a is preferable to bring the LVQ, which can stem from some other subject, into the right general position of the current user. For the following sessions, α can be lowered to freeze the LVQ in its position. Additional improvement can be expected if both learning during data processing and learning between sessions are combined. Although this study was based only on off-line examination of existing recordings, subjects in future experiments can also be expected to give improved performance: if even the first session gives more than random results they will experience the system as more trustworthy and will be more motivated in the following sessions.

LVQ-Based On-line EEG Classification

In this paper the problems of classifying EEG in both its spatial as well as its temporal aspects are described. The task was to identify the intended side of hand movement (left or right) on the basis of EEG recorded on two channels during one second before movement onset. This is part of a larger project aiming to build a “Brain-Computer Interface” (BCI) which should enable handicapped persons to communicate with their surroundings using their EEG.