An EEG-Based Attentiveness Recognition System Using Hilbert\u2013Huang Transform and Support Vector Machine

Chia-Ju Peng,Luc Chassagne,Shih-Jui Chen,Yi-Chun Chen,Chun-Chuan Chen,Barthélemy Cagneau

doi:10.1007/s40846-019-00500-y

Abstract

PurposeAttentiveness recognition benefits the detection of the mental state and concentration when humans perform specific tasks. 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 attentiveness levels by using electroencephalogram (EEG) signals and HHT analysis.MethodsSingle-channel EEG signals from 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 spectrum. Then the band powers and spectral entropies (SEs) were selected as the attributes of a support vector machine (SVM) for a two-class classification task.ResultsCompared with the predictive models of approximate entropy (ApEn) and fast Fourier transform (FFT), the results show that the band powers extracted from IMF2 to IMF5 of alpha and beta waves and their SE can best discriminate between attentive and relaxed states with the average classification accuracy of 84.80%.ConclusionIn conclusion, this integrated signal processing method is capable of attentiveness recognition that can offer efficient differentiation and may be used in a clinical setting for the detection of attention deficit.

Highlights

Attention is an important feature that reflects the mental state of the brain and can be measured by using electroencephalography (EEG)
After performing the Hilbert transform, we found that IMF2, IMF3, IMF4, and IMF5 contained the power within the desired frequency range (8–30 Hz) while the IMF1, IMF6–8 contained statistically no power in the frequencies of interest (p < 0.05)
Our results suggest that using nonlinear Hilbert–Huang transform (HHT) method instead of fast Fourier transform (FFT) and selecting appropriate features can improve the accuracy in attention recognition

Summary

Introduction

Attention is an important feature that reflects the mental state of the brain and can be measured by using electroencephalography (EEG). 30 Hz with amplitudes from 5 to 20 μV are evident during active attention. Quantifying these frequencyspecific features using EEG can be used to probe the level of attentiveness [2,3,4]. Previous studies have shown that for EEG attentiveness recognition, using a k-nearest neighbor (KNN) classifier based on the self-assessment manikin model can yield an average accuracy of 57.03% [5], and using support vector machine (SVM) model of power spectral density resulted in an average accuracy of 76.82% [6]. In this study, we proposed a method for the characterization of the levels of attentiveness based on

Methods

Results

Conclusion