TVAR modeling of EEG to detect audio distraction during simulated driving

Dahal, Nabaraj; Nandagopal, Nanda; Cocks, Bernadine; Ramasamy, Vijayalakshmi; Dasari, Naga; Gaertner, Paul S.

doi:10.1088/1741-2560/11/3/036012

Cited by 16 publications

(3 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It was recently shown how the estimation of these parameters can be performed within a robust statistical framework [34]. Herein, we utilize a robust extension of the IF estimation algorithm utilized in [32,30], by employing a variable dynamic model and considering the impact of tracking the combination of IF and IE features for the application of interest.…”

Section: The Concept Of Instantaneous Envelope and Frequencymentioning

confidence: 99%

“…In the EEG, the time-varying center radian frequency ω 0 (n) has been attributed to the frequency at which the majority of cortical neurons in the recording lead vicinity oscillate in synchrony [30]. This is herein referred to as the instantaneous frequency (IF(n)) of the EEG, in Hz.…”

Section: Time-varying Autoregressive Model For If Estimationmentioning

confidence: 99%

“…The application of autoregressive moving-average (ARMA) model root tracking using an RLS algorithm for EEG analysis was first introduced in [28]. It has been proposed that the pole displacement of an autoregressive (AR) model fitted over a nonstationary EEG can have physiological interpretations [29,28,30]. In [31] it was shown that the IF is the most correlated feature with variations in level of consciousness in the problem of depth of anesthesia (DOA) detection.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Automatic Wake-Sleep Stages Classification using Electroencephalogram Instantaneous Frequency and Envelope Tracking

Alam

Sameni²

2020

Preprint

View full text Add to dashboard Cite

Background: The study of cerebral activity during sleep using the electroencephalograph (EEG) is a major research field in neuroscience. Despite the rich literature in this field, the automatic and accurate categorization of wake-sleep stages remains an open problem. New Method: A robust model-based Kalman filtering scheme is proposed for tracking the poles of a second order time-varying autoregressive model fitted over the EEG acquired during different wake/sleep stages. The pole angle/phase is regarded as the dominant frequency of the EEG spectrum (known as the instantaneous frequency in literature). The frequency resolution is improved by splitting the wide frequency band to subbands corresponding to well-known brain rhythms. Using recent findings in field of EEG phase/frequency tracking, the instantaneous envelope of the narrow-band signal's analytic form is also tracked as a complementary feature. Results: The minimal set of instantaneous frequency and envelope features is employed in three classification schemes, using training labels from R&k and AASM sleep scoring standards. The LDA classifier resulted in the highest performance using the proposed feature set. Comparison with Existing Methods: The proposed method resulted in a higher mean decoding accuracy and a lower standard deviation on the entire dataset, as compared with state-of-the-art techniques. Conclusions: The accurate tracking of the instantaneous frequency and envelope are highly informative for sleep stage scoring. The proposed method is shown to have additional applications, including the prediction of wake-sleep transition, which can be used for drowsiness detection from the EEG.

show abstract

Section: The Concept Of Instantaneous Envelope and Frequencymentioning

confidence: 99%

Section: Time-varying Autoregressive Model For If Estimationmentioning

confidence: 99%