T
TN Lal
Researcher at Max Planck Society
Publications - 21
Citations - 5580
TN Lal is an academic researcher from Max Planck Society. The author has contributed to research in topics: Brain–computer interface & Support vector machine. The author has an hindex of 13, co-authored 21 publications receiving 5214 citations.
Papers
More filters
Proceedings Article
Learning with Local and Global Consistency
TL;DR: A principled approach to semi-supervised learning is to design a classifying function which is sufficiently smooth with respect to the intrinsic structure collectively revealed by known labeled and unlabeled points.
Journal ArticleDOI
Support vector channel selection in BCI
TN Lal,Michael Schröder,Thilo Hinterberger,Jason Weston,Martin Bogdan,Niels Birbaumer,Bernhard Schölkopf +6 more
TL;DR: Recursive Feature Elimination and Zero-Norm Optimization which are based on the training of support vector machines (SVM) can provide more accurate solutions than standard filter methods for feature selection for EEG channels.
Proceedings Article
Methods Towards Invasive Human Brain Computer Interfaces
TN Lal,Thilo Hinterberger,Guido Widman,Michael Schröder,N. J. Hill,Wolfgang Rosenstiel,Christian E. Elger,Niels Birbaumer,Bernhard Schölkopf +8 more
TL;DR: This paper presents the method and examples of intracranial EEG recordings of three epilepsy patients with electrode grids placed on the motor cortex, and analyzes the classifiability of the data using Support Vector Machines (SVMs) and Recursive Channel Elimination (RCE).
Journal ArticleDOI
Classifying EEG and ECoG signals without subject training for fast BCI implementation: comparison of nonparalyzed and completely paralyzed subjects
NJ Hill,TN Lal,Michael Schröder,Thilo Hinterberger,Barbara Wilhelm,Femke Nijboer,Ursula Mochty,Guido Widman,Christian E. Elger,Bernhard Schölkopf,Andrea Kübler,Niels Birbaumer +11 more
TL;DR: While it was relatively easy to obtain classifiable signals quickly from most of the nonparalyzed subjects, it proved impossible to classify the signals obtained from the paralyzed patients by the same methods, highlighting the fact that though certain BCI paradigms may work well with healthy subjects, this does not necessarily indicate success with the target user group.
Journal ArticleDOI
Robust EEG channel selection across subjects for brain-computer interfaces
Michael Schröder,TN Lal,Thilo Hinterberger,Martin Bogdan,N. Jeremy Hill,Niels Birbaumer,Wolfgang Rosenstiel,Bernhard Schölkopf +7 more
TL;DR: Although the RCE method was not provided with prior knowledge about the mental task, channels that are well known to be important were consistently selected whereas task-irrelevant channels were reliably disregarded.