A Novel Method for Single-Trial Classification in the Face of Temporal Variability
Machine learning techniques have been used to classify patterns of neural data obtained from electroencephalography (EEG) to increase human-system performance. This classification approach works well in controlled laboratory settings since many of the machine learning techniques used often rely on consistent neural responses and behavioral performance over time. Moving to more dynamic, unconstrained environments, however, introduces temporal variability in the neural response resulting in sub-optimal classification performance. This study describes a novel classification method that accounts for temporal variability in the neural response to increase classification performance. Specifically, using sliding windows in hierarchical discriminant component analysis (HDCA), we demonstrate a decrease in classification error by over 50% when compared to other state-of-the-art classification methods.
KeywordsBrain-Computer Interface (BCI) Rapid Serial Visual Presentation (RSVP) Electroencephalography (EEG) HDCA Sliding HDCA Temporal Variability Single-trial Real-world environment
Unable to display preview. Download preview PDF.
- 8.Tomioka, R., Aihara, K., Müller, K.R.: Logistic regression for single trial EEG classification. Advances in Neural Information Processing Systems 19, 1377–1384 (2007)Google Scholar
- 15.Tomioka, R., Dornhege, G., Nolte, G., Blankertz, B., Aihara, K., Müller, K.R.: Spectrally weighted common spatial pattern algorithm for single trial EEG classification. Dept. Math. Eng., Univ. Tokyo, Tokyo, Japan, Tech. Rep. 40 (2006) Google Scholar
- 19.Touryan, J., Gibson, L., Horne, J.H., Weber, P.: Real-Time Measurement of Face Recognition in Rapid Serial Visual Presentation. Front Psychol. 2 (2011)Google Scholar
- 22.Ries, A.J., Larkin, G.B.: Stimulus and response-locked P3 activity in a dynamic RSVP task. ARL-TR-6314 (2012)Google Scholar
- 23.Touryan, J., Gibson, L., Horne, J.H., Weber, P.: Real-time classification of neural signals corresponding to the detection of targets in video imagery. Presented at the International Conference on Applied Human Factors and Ergonomics, Miami, Fl (2010)Google Scholar
- 26.Luck, S.J., Lopez-Calderon, J.: ERPLAB Toolbox (2010)Google Scholar
- 27.Luck, S.J.: An Introduction to the Event-Related Potential Technique. A Bradford Book (2005)Google Scholar