Sliding HDCA: Single-Trial EEG Classification to Overcome and Quantify Temporal Variability

摘要: Patterns of neural data obtained from electroencephalography (EEG) can be classified by machine learning techniques to increase human-system performance. In controlled laboratory settings this classification approach works well; however, transitioning these approaches into more dynamic, unconstrained environments will present several significant challenges. One such challenge is an in temporal variability measured behavioral and responses, which often results suboptimal Previously, we reported a novel method designed account for the response order improve performance using sliding windows hierarchical discriminant component analysis (HDCA), demonstrated decrease error over 50% when compared standard HDCA (Marathe et al., 2013). Here, expand upon show that embedded within new signal transformation that, applied EEG signals, significantly improves signal-to-noise ratio thereby enables accurate single-trial analysis. The presented here have implications both brain-computer interaction technologies basic science research processes.