Parametric models and spectral analysis for classification in brain-computer interfaces
Citation:
Kelly, S., Burke, D., deChazal, P., Reilly, R.B., Parametric models and spectral analysis for classification in brain-computer interfaces: proceedings of the 14th International Conference on Digital Signal Processing: DSP2002, Santorini: IEEE, 2002, pp307-310Download Item:
Abstract:
Parametric modelling strategies and spectral analysis are explored in conjunction with linear discriminant analysis to facilitate an EEG based direct-brain interface for use by disabled people. A self-paced typing exercise is analysed by employing for feature extraction, respectively, an autoregressive model, an autoregressive with exogenous input model, and a time-frequency decomposition of the data. Modelling both the signal and noise is found to be more, effective than modelling the noise alone with the former yielding an accuracy of 70.7% and the latter an accuracy of 57.4%. Experiments, using the raw samples of a short-time power spectral density estimate of each trial as features, yielded an accuracy of 62.5%.
Author's Homepage:
http://people.tcd.ie/reillyriDescription:
PUBLISHED
Author: REILLY, RICHARD
Other Titles:
International Conference on Digital Signal Processing: 14th: Santorini: 2002DSP2002
Publisher:
IEEEType of material:
Conference PaperAvailability:
Full text availableKeywords:
Brain-computer interfaces, EEGMetadata
Show full item recordLicences: