An EEG-based attentiveness recognition system using Hilbert-Huang transform and support vector machine
Résumé
Hilbert-Huang transform (HHT) is useful for the analysis of nonlinear or nonstationary bio-signals including brainwaves. In this work, a method is proposed for the characterization of the levels of attentiveness by using electroencephalogram (EEG) signals and HHT analysis. Single channel EEG signals over the frontal area were acquired from participants at different levels of attentiveness and were decomposed into a set of intrinsic mode functions (IMF) by empirical mode decomposition (EMD). Hilbert transform analysis was applied to each IMF to obtain the marginal frequency spectra, and then the band powers and spectral entropies (SE) were selected as the attributes entered a support vector machine (SVM) for the two-class classification. Compared with the predictive models of approximate entropy (ApEn) and fast Fourier transform (FFT), the results showed that the band powers extracted from IMF2 to IMF5 of and waves and their SE can best discriminate between attentive and relaxed states with the classification average accuracy of 84.80%. In conclusion, this integrated signal processing method is capable of attentiveness recognition and may be used in a clinical setting for the detection of attention deficit.
Origine | Fichiers produits par l'(les) auteur(s) |
---|
Loading...