Abstract—Due to the volume conduction multi-channel electroencephalogram (EEG) recordings give a rather blurred image of brain activity. Therefore spatial filters are extremely useful in single-trial analysis in order to improve the signal-to-noise ratio. There are powerful methods from machine learning and signal processing that permit the optimization of spatio-temporal filters for each subject in a data dependent fashion beyond the fixed filters based on the sensor geometry, e.g., Laplacians. Here we elucidate the theoretical background of the Common Spatial Pattern (CSP) algorithm, a popular method in Brain-Computer Interface (BCI) research. Apart from reviewing several variants of the basic algorithm, we reveal tricks of the trade for achieving a powerful CSP performance, briefly elaborate on theoretical aspects of CSP and demonstrate the application of CSP-type preprocessing in our studies of the Berlin Brain-Computer Interface project.

A common assumption in supervised learning is that the input points in the training set follow the same probability distribution as the input points that will be given in the future test phase. However, this assumption is not satisfied, for example, when the outside of the training region is extrapolated. The situation where the training input points and test input points follow different distributions while the conditional distribution of output values given input points is unchanged is called the covariate shift. Under the covariate shift, standard model selection techniques such as cross validation do not work as desired since its unbiasedness is no longer maintained. In this paper, we propose a new method called importance weighted cross validation (IWCV), for which we prove its unbiasedness even under the covariate shift. The IWCV procedure is the only one that can be applied for unbiased classification under covariate shift, whereas alternatives to IWCV exist for regression. The usefulness of our proposed method is illustrated by simulations, and furthermore demonstrated in the brain-computer interface, where strong non-stationarity effects can be seen between training and test sessions. c2000 Masashi Sugiyama, Matthias Krauledat, and Klaus-Robert Müller.

Abstract: We outline the Berlin Brain-Computer Interface (BBCI), a system which enables us to translate brain signals from movements or movement intentions into control commands. The main contribution of the BBCI, which is a non-invasive EEG-based BCI system, is the use of advanced machine learning techniques that allow to adapt to the specific brain signatures of each user with literally no training. In BBCI a calibration session of about 20min is necessary to provide a data basis from which the individualized brain signatures are inferred. This is very much in contrast to conventional BCI approaches that rely on operand conditioning and need extensive subject training of the order 50-100 hours. Our machine learning concept thus allows to achieve high quality feedback already after the very first session. This work reviews a broad range of investigations and experiments that have been performed within the BBCI project. In addition to these general paradigmatic BCI results, this work provides a condensed outline of the underlying machine learning and signal processing techniques that make the BBCI succeed. In the first experimental paradigm we analyze the predictability of limb movement long before the actual movement takes place using only the movement intention measured from the pre-movement (readiness) EEG potentials. The experiments include both off-line studies and an online feedback

We present a system whereby the human voice may specify continuous control signals to manipulate a simulated 2D robotic arm and a real 3D robotic arm. Our goal is to move towards making accessible the manipulation of everyday objects to individuals with motor impairments. Using our system, we performed several studies using control style variants for both the 2D and 3D arms. Results show that it is indeed possible for a user to learn to effectively manipulate real-world objects with a robotic arm using only non-verbal voice as a control mechanism. Our results provide strong evidence that the further development of non-verbal voicecontrolled robotics and prosthetic limbs will be successful. Author Keywords Voice-based interface, speech recognition, motor impairment, robotics ACM Classification Keywords

Up to now even subjects that are experts in the use of machine learning based BCI systems still have to undergo a calibration session of about 20-30 min. From this data their (movement) intentions are so far infered. We now propose a new paradigm that allows to completely omit such calibration and instead transfer knowledge from prior sessions. To achieve this goal we first define normalized CSP features and distances in-between. Second, we derive prototypical features across sessions: (a) by clustering or (b) by feature concatenation methods. Finally, we construct a classifier based on these individualized prototypes and show that, indeed, classifiers can be successfully transferred to a new session for a number of subjects.

project develops a non-invasive BCI system whose key features are (1) the use of well-established motor competences as control paradigms, (2) high-dimensional features from multi-channel EEG and (3) advanced machine learning techniques. Spatiospectral changes of sensorimotor rhythms are used to discriminate imagined movements (left hand, right hand, foot). A previous feedback study ([1]) with 10 subjects provided preliminary evidence that the BBCI system can be operated at high accuracy for subjects with less than 5 prior BCI exposures. Here, we demonstrate in a group of 14 fully BCI-naïve subjects that 8/14 BCI novices can perform at>84 % accuracy in their very first BCI session, and a further 4 subjects>70%. Thus, 12/14 BCI-novices had significant above-chance level performances without any subject training even in the first session, as based on an optimized EEG analysis by advanced machine learning algorithms. I.

We introduce quasi-movements and define them as volitional movements which are minimized by the subject to such an extent that finally they become undetectable by objective measures. They are intended as overt movements, but the absence of the measurable motor responses and the subjective experience make quasi-movements similar to motor imagery. We used the amplitude dynamics of electroencephalographic alpha oscillations as a marker of the regional involvement of cortical areas in three experimental tasks: movement execution, kinesthetic motor imagery, and quasi-movements. All three conditions were associated with a significant suppression of alpha oscillations over the sensorimotor hand area of the contralateral hemisphere. This suppression was strongest for executed movements, and stronger for quasi-movements than for motor imagery. The topography of alpha suppression was similar in all three conditions. Proprioceptive sensations related to quasi-movements contribute to the assumption that the “sense of movement ” can originate from central efferent processes. Quasi-movements are also congruent with the postulated continuity between motor imagery and movement preparation/execution. We also show that in healthy subjects quasi-movements can be effectively used in brain–computer interface research leading to a significantly smaller classification error (∼47 % of relative decrease) in comparison to the errors obtained with conventionally used motor imagery strategies.

In the quest to make Brain Computer Interfacing (BCI) more usable, dry electrodes have emerged that get rid of the initial 30 minutes required for placing an electrode cap. Another time consuming step is the required individualized adaptation to the BCI user, which involves another 30 minutes calibration for assessing a subject’s brain signature. In this paper we aim to also remove this calibration proceedure from BCI setup time by means of machine learning. In particular, we harvest a large database of EEG BCI motor imagination recordings (83 subjects) for constructing a library of subject-specific spatio-temporal filters and derive a subject independent BCI classifier. Our offline results indicate that BCI-naïve users could start real-time BCI use with no prior calibration at only a very moderate performance loss. 1

Analysis of electrophysiological brain activity has long been considered as one of indispensable tools enabling clinicians and scientists to investigate various aspects of cognitive brain functionality and its underlying neurophysiological structure. The relevance of electroencephalogram (EEG) in particular, due to its inexpensive and most importantly,

Abstract—Brain-computer interfaces (BCIs) are known to suffer from spontaneous changes in the brain activity. If changes in the mental state of the user are reflected in the brain signals used for control, the behaviour of a BCI is directly influenced by these states. We investigate the influence of a state of loss of control in a variant of Pacman on the performance of BCIs based on motor control. To study the effect a temporal loss of control has on the BCI performance, BCI classifiers were trained on electroencephalography (EEG) recorded during the normal control condition, and the classification performance on segments of EEG from the normal and loss of control condition was compared. Classifiers based on event-related desynchronization (ERD) unexpectedly performed significantly better during the loss of control condition; for the event-related potential (ERP) classifiers there was no significant difference in performance. Index Terms—brain-computer interfaces, common spatial patterns, electroencephalography, loss of control, mental states, nonstationary signals, event-related desynchronization, lateralized readiness potential.