raxDAWN: Circumventing Overfitting of the Adaptive xDAWN
Mario Michael Krell, Anett Seeland, Hendrik Wöhrle
In Proceedings of the International Congress on Neurotechnology, Electronics and Informatics (http://www.neurotechnix.org/), (NEUROTECHNIX-2015), 16.11.-17.11.2015, Lissabon, SciTePress, pages 68-75, 2015.
The xDAWN algorithm is a well-established spatial filter which was developed to enhance the signal quality of brain-computer interfaces for the detection of event-related potentials. Recently, an adaptive version has been introduced. Here, we present an improved version that incorporates regularization to reduce the influence of noise and avoid overfitting. We show that regularization improves the performance significantly for up to 4%, when little data is available as it is the case when the brain-computer interface should be used without or with a very short prior calibration session.
xDAWN, Spatial Filtering, Online Learning, Electroencephalogram, Event-Related Potential, Brain-Computer Interface