K.-R. Müller

Publications of K.-R. Müller

• Toward Unsupervised Adaptation of LDA for Brain–Computer Interfaces

  Authors: C. Vidaurre, M. Kawanabe, P. von Bünau, B. Blankertz, K.R. Müller

  Biomedical Engineering, IEEE Transactions on. 04/2011;

  There is a step of significant difficulty experienced by brain-computer interface (BCI) users when going from the calibration recording to the feedback application. This effect has been previouslyThere is a step of significant difficulty experienced by brain-computer interface (BCI) users when going from the calibration recording to the feedback application. This effect has been previously studied and a supervised adaptation solution has been proposed. In this paper, we suggest a simple unsupervised adaptation method of the linear discriminant analysis (LDA) classifier that effectively solves this problem by counteracting the harmful effect of nonclass-related nonstationarities in electroencephalography (EEG) during BCI sessions performed with motor imagery tasks. For this, we first introduce three types of adaptation procedures and investigate them in an offline study with 19 datasets. Then, we select one of the proposed methods and analyze it further. The chosen classifier is offline tested in data from 80 healthy users and four high spinal cord injury patients. Finally, for the first time in BCI literature, we apply this unsupervised classifier in online experiments. Additionally, we show that its performance is significantly better than the state-of-the-art supervised approach.

• Localization of class-related mu-rhythm desynchronization in motor imagery based Brain-Computer Interface sessions

  Authors: S. Haufe, R. Tomioka, T. Dickhaus, C. Sannelli, B. Blankertz, G. Nolte, K.-R. Müller

  Engineering in Medicine and Biology Society (EMBC), 2010 Annual International Conference of the IEEE; 10/2010

  We localize the sources of class-dependent event-related desynchronisation (ERD) of the mu-rhythm related to different types of motor imagery in Brain-Computer Interfacing (BCI) sessions. OurWe localize the sources of class-dependent event-related desynchronisation (ERD) of the mu-rhythm related to different types of motor imagery in Brain-Computer Interfacing (BCI) sessions. Our approach is based on localization of single-trial Fourier coefficients using sparse basis field expansions (S-FLEX). The analysis reveals focal sources in the sensorimotor cortices, a finding which can be regarded as a proof for the expected neurophysiological origin of the BCI control signal. As a technical contribution, we extend S-FLEX to the multiple measurement case in a way that the activity of different frequency bins within the mu-band is coherently localized.

• Modeling Sparse Connectivity Between Underlying Brain Sources for EEG/MEG

  Authors: S. Haufe, R. Tomioka, G. Nolte, K.-R. Müller, M. Kawanabe

  Biomedical Engineering, IEEE Transactions on. 09/2010;

  We propose a novel technique to assess functional brain connectivity in electroencephalographic (EEG)/magnetoencephalographic (MEG) signals. Our method, called sparsely connected sources analysisWe propose a novel technique to assess functional brain connectivity in electroencephalographic (EEG)/magnetoencephalographic (MEG) signals. Our method, called sparsely connected sources analysis (SCSA), can overcome the problem of volume conduction by modeling neural data innovatively with the following ingredients: 1) the EEG/MEG is assumed to be a linear mixture of correlated sources following a multivariate autoregressive (MVAR) model; 2) the demixing is estimated jointly with the source MVAR parameters; and 3) overfitting is avoided by using the group lasso penalty. This approach allows us to extract the appropriate level of crosstalk between the extracted sources and, in this manner, we obtain a sparse data-driven model of functional connectivity. We demonstrate the usefulness of SCSA with simulated data and compare it to a number of existing algorithms with excellent results.

• Combining Brain-Computer Interfaces and Assistive Technologies: State-of-the-Art and Challenges.

  Authors: J D R Millán, R Rupp, G R Müller-Putz, R Murray-Smith, C Giugliemma, M Tangermann, C Vidaurre, F Cincotti, A Kübler, R Leeb, C Neuper, K-R Müller, D Mattia

  Frontiers in neuroscience. 01/2010; 4.

  In recent years, new research has brought the field of electroencephalogram (EEG)-based brain-computer interfacing (BCI) out of its infancy and into a phase of relative maturity through manyIn recent years, new research has brought the field of electroencephalogram (EEG)-based brain-computer interfacing (BCI) out of its infancy and into a phase of relative maturity through many demonstrated prototypes such as brain-controlled wheelchairs, keyboards, and computer games. With this proof-of-concept phase in the past, the time is now ripe to focus on the development of practical BCI technologies that can be brought out of the lab and into real-world applications. In particular, we focus on the prospect of improving the lives of countless disabled individuals through a combination of BCI technology with existing assistive technologies (AT). In pursuit of more practical BCIs for use outside of the lab, in this paper, we identify four application areas where disabled individuals could greatly benefit from advancements in BCI technology, namely, "Communication and Control", "Motor Substitution", "Entertainment", and "Motor Recovery". We review the current state of the art and possible future developments, while discussing the main research issues in these four areas. In particular, we expect the most progress in the development of technologies such as hybrid BCI architectures, user-machine adaptation algorithms, the exploitation of users' mental states for BCI reliability and confidence measures, the incorporation of principles in human-computer interaction (HCI) to improve BCI usability, and the development of novel BCI technology including better EEG devices.

• Subject-independent mental state classification in single trials

  Authors: S. Fazli, F. Popescu, M. Danóczy, B. Blankertz, K.-R. Müller, C. Grozea

  Neural Networks. 06/2009;

• A benchmark data set for in silico prediction of ames mutagenicity

  Authors: K Hansen, S. Mika, T Schroeter, A Sutter, Ter Laak A, T Steger-Hartmann, N Heinrich, K.-R. Müller

  Chemistry Central Journal. 01/2009;

• Virtual screening for PPAR-gamma ligands using the ISOAK molecular graph kernel and gaussian processes

  Authors: T Schroeter, M Rupp, K Hansen, K.-R. Müller, G Schneider

  Chemistry Central Journal. 01/2009;

• Machine learning for real-time single-trial EEG-analysis: From brain–computer interfacing to mental state monitoring

  Authors: K. R. Müller, M. Tangermann, G. Dornhege, M. Krauledat, G. Curio, B. Blankertz

  J. Neurosci. Methods. 01/2008; 167:82--90.

• The Berlin Brain-Computer Interface: Accurate performance from first-session in BCI-naive subjects

  Authors: B. Blankertz, F. Losch, M. Krauledat, G. Dornhege, G. Curio, K. R. Müller

  IEEE Trans. Biomed. Eng. 01/2008;

• Optimizing spatial filters for robust EEG single-trial analysis

  Authors: B. Blankertz, R. Tomioka, S. Lemm, M. Kawanabe, K.R. Müller

  IEEE Signal. Proc. Mag. 01/2008; 25:41--56.

• Brain-computer interfacing for intelligent systems

  Authors: A. Nijholt, D. Tan, G. Pfurtscheller, C. Brunner, B. Allison, B. Graimann, F. Popescu, B. Blankertz, K.R. Müller

  IEEE Intell. Syst. 01/2008; 23:72--99.

• Improving the emphCaenorhabditis elegans genome annotation using machine learning

  Authors: G. Rätsch bf, S. Sonnenburg, J. Srinivasan, H. Witte, K--R. Müller, R--J. Sommer, B. Schölkopf

  PLoS Comput Biol. 02/2007; 3(2):e20.

• The non-invasive Berlin Brain--Computer Interface: Fast acquisition of effective performance in untrained subjects

  Authors: B. Blankertz, G. Dornhege, M. Krauledat, K.R. Müller, G. Curio

  Neuroimage. 01/2007; 37:539--550.

• Reducing calibration time for brain-computer interfaces: A clustering approach

  Authors: M. Krauledat, M. Schröder, B. Blankertz, K. R. Müller

  01/2007

• Robustly estimating the flow direction of information in complex physical systems

  Authors: G. Nolte, A. Ziehe, V.V. Nikulin, A. Schlögl, N. Krämer, T. Brismar, K.R. Müller

  Arxiv preprint arXiv:0712.2352. 01/2007;

• Covariate Shift Adaptation by Importance Weighted Cross Validation

  Authors: M. Sugiyama, M. Krauledat, K. -R. Müller

  Journal of Machine Learning Research. 01/2007; 8:985-1005.

• Improving human performance in a real operating environment through real-time mental workload detection

  Authors: J. Kohlmorgen, G. Dornhege, M. Braun, B. Blankertz, K. R. Müller, G. Curio, K. Hagemann, A. Bruns, M. Schrauf, W. Kincses

  01/2007: pages 409–422;

• The Berlin Brain-Computer Interface (BBCI)--towards a new communication channel for online control in gaming applications

  Authors: R. Krepki, B. Blankertz, G. Curio, K. R. Müller

  Multimedia Tools and Applications. 01/2007; 33:73--90.

• Berlin Brain--Computer Interface—The HCI communication channel for discovery

  Authors: R. Krepki, G. Curio, B. Blankertz, K.R. Müller

  International Journal of Human-Computer Studies. 01/2007; 65:460--477.

• Spectrally weighted common spatial pattern algorithm for single trial EEG classification

  Authors: R. Tomioka, G. Dornhege, G. Nolte, B. Blankertz, K. Aihara, K.R. Müller

  07/2006;