- Modeling sparse connectivity between underlying brain sources for EEG/MEGStefan Haufe
Berlin Institute of Technology, Berlin 10623, Germany
IEEE Trans Biomed Eng 57:1954-63. 2010..We demonstrate the usefulness of SCSA with simulated data and compare it to a number of existing algorithms with excellent results...
- Combining sparsity and rotational invariance in EEG/MEG source reconstructionStefan Haufe
Machine Learning Group, Department of Computer Science, TU Berlin, Franklinstr 28 29, D 10587 Berlin, Germany
Neuroimage 42:726-38. 2008..Compared to its peers FVR was the only method that delivered correct location of the source in the somatosensory area of each hemisphere in accordance with neurophysiological prior knowledge...
- Localization of class-related mu-rhythm desynchronization in motor imagery based brain-computer interface sessionsStefan Haufe
Berlin Institute of Technology, Franklinstr 28 29, D 10587, Germany
Conf Proc IEEE Eng Med Biol Soc 2010:5137-40. 2010..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...
- Large-scale EEG/MEG source localization with spatial flexibilityStefan Haufe
Department of Computer Science, Berlin Institute of Technology, Berlin, Germany
Neuroimage 54:851-9. 2011..Our approach based on single-trial localization of complex Fourier coefficients yields class-specific focal sources in the sensorimotor cortices...
- Single-trial analysis and classification of ERP components--a tutorialBenjamin Blankertz
Berlin Institute of Technology, Machine Learning Laboratory, Berlin, Germany
Neuroimage 56:814-25. 2011....
- EEG potentials predict upcoming emergency brakings during simulated drivingStefan Haufe
Machine Learning Group, Department of Computer Science, Berlin Institute of Technology, Franklinstraße 28 29, D 10587 Berlin, Germany
J Neural Eng 8:056001. 2011....
- Pre-stimulus sensorimotor rhythms influence brain-computer interface classification performanceCecilia L Maeder
Berlin Institute of Technology, Machine Learning Laboratory, Germany
IEEE Trans Neural Syst Rehabil Eng 20:653-62. 2012..Our findings support the idea that exploiting information about the ongoing SMR might be the key to boosting performance in future SMR-BCI experiments and motor related tasks in general...
- A critical assessment of connectivity measures for EEG data: a simulation studyStefan Haufe
Machine Learning Group, Department of Computer Science, Berlin Institute of Technology, Franklinstr 28 29, 10587 Berlin, Germany
Neuroimage 64:120-33. 2013..Integrating the insights of our study, we provide a guidance for measuring brain interaction from EEG data. Software for generating benchmark data is made available...
- Automatic classification of artifactual ICA-components for artifact removal in EEG signalsIrene Winkler
Machine Learning Laboratory, Berlin Institute of Technology, Franklinstr, 28 29, 10587 Berlin, Germany
Behav Brain Funct 7:30. 2011..Existing ICA-based removal strategies depend on explicit recordings of an individual's artifacts or have not been shown to reliably identify muscle artifacts...