Second-Order Bilinear Discriminant Analysis

Traditional analysis methods for single-trial classification of electro-encephalography (EEG) focus on two types of paradigms: phase-locked methods, in which the amplitude of the signal is used as the feature for classification, i.e. event related potentials; and secondorder methods, in which the feature of interest is the power of the signal, i.e. event related (de)synchronization. The process of deciding which paradigm to use is ad hoc and is driven by assumptions regarding the underlying neural generators. Here we propose a method that provides an unified framework for the analysis of EEG, combining first and secondorder spatial and temporal features based on a bilinear model. Evaluation of the proposed method on simulated data shows that the technique outperforms state-of-the art techniques for single-trial classification for a broad range of signal-to-noise ratios. Evaluations on human EEG – including one benchmark dataset from the Brain Computer Interface (BCI) competitio...

• Type: Journal
• Year: 2010
• Where: JMLR
• Authors: Christoforos Christoforou, Robert M. Haralick, Paul Sajda, Lucas C. Parra
• Keywords: Brain Computer Interface, JMLR 2010, Single-trial Classification, Traditional Analysis Methods