Thus, an important advantage of the EAR method is that no a priori information about the frequency bands is necessary .

For both approaches, two closely spaced bipolar recordings from the left and right seniority cortex were used. In further studies, spatial information from a dense array of electrodes located over central areas was considered to improve the classification accuracy. For this purpose, the SSP method was used to estimate spatial liters that reflect the specific activation of cortical areas during hand movement imagination. Each electrode is weighted according to their importance for the classification.

LAVE was mainly applied to online experiments with delayed feedback presentation. In these experiments, the input features were extracted from a I-s epoch of GEE recorded during motor imagery. The GEE was filtered in one or two subject-specific frequency bands before calculating four band power estimates, each representing a time interval of 250 ms, per GEE channel and frequency range. Based n these features, the LAVE classifier derived a classification and a measure describing the certainty of this classification, which in turn was provided to the subject as a feedback symbol at the end of each trial.

In experiments with continuous feedback based on either EAR parameter estimation or Caps, a linear discriminate classifier has usually been applied for on- line classification. The EAR parameters of two GEE channels or the variance time series of the Caps are linearly combined and a time-varying signed distance (TTS) function is calculated. With this method it is possible to indicate the result and the retainer of classification, e. G. , by a continuously moving feedback bar.The different methods of GEE preprocessing and classification have been compared in extended on-line experiments and data analyzes.

These experiments were carried out using a newly developed BCC system running in real-time under Windows with a 2, 8, or 64 channel GEE amplifier . The installation of this system, based on a rapid prototyping environment, includes a software package that supports the real-time implementation and testing of different GEE parameter estimation and classification algorithms.