Billiet, Lieven
[STADIUS Center for Dynamical Systems, Signal processing and Data Analysis, KU Leuven, Belgium]
Hunyadi, Borbala
[STADIUS Center for Dynamical Systems, Signal processing and Data Analysis, KU Leuven, Belgium]
Matic, Vladimir
[STADIUS Center for Dynamical Systems, Signal processing and Data Analysis, KU Leuven, Belgium]
Van Huffel, Sabine
[STADIUS Center for Dynamical Systems, Signal processing and Data Analysis, KU Leuven, Belgium]
Verleysen, Michel
[UCL]
Subspace methods have been applied in various application fields to obtain robust results. Using multilinear algebra, they can also be applied on structured tensorial data. This work combines this principle with the power of non-linear kernels to investigate its merits in single trial classification for a mobile BCI ERP classification task. The accuracy difference with regard to more conventional vector kernels is evaluated for sitting and walking condition, increasing training data set and averaging over multiple trials. The study concludes that in general, the tensorial approach does not yield any advantage, though it might for specific subjects.
Bibliographic reference |
Billiet, Lieven ; Hunyadi, Borbala ; Matic, Vladimir ; Van Huffel, Sabine ; Verleysen, Michel. Single trial classification in Mobile BCI - A multiway Kernel approach.8th International Conference on Bio-Inspired Systems and Signal processing (BIOSIGNALS 2015) (Lisbon (Portugal), du 12/01/2015 au 15/01/2015). In: Proceedings of BIOSIGNALS 2015, SciTePress2015, p.5-11 |
Permanent URL |
http://hdl.handle.net/2078.1/171366 |