Utilization of a combined EEG/NIRS system to predict driver drowsiness

Abstract

The large number of automobile accidents due to driver drowsiness is a critical concern of many countries. To solve this problem, numerous methods of countermeasure have been proposed. However, the results were unsatisfactory due to inadequate accuracy of drowsiness detection. In this study, we introduce a new approach, a combination of EEG and NIRS, to detect driver drowsiness. EEG, EOG, ECG and NIRS signals have been measured during a simulated driving task, in which subjects underwent both awake and drowsy states. The blinking rate, eye closure, heart rate, alpha and beta band power were used to identify subject’s condition. Statistical tests were performed on EEG and NIRS signals to find the most informative parameters. Fisher’s linear discriminant analysis method was employed to classify awake and drowsy states. Time series analysis was used to predict drowsiness. The oxy-hemoglobin concentration change and the beta band power in the frontal lobe were found to differ the most between the two states. In addition, these two parameters correspond well to an awake to drowsy state transition. A sharp increase of the oxy-hemoglobin concentration change, together with a dramatic decrease of the beta band power, happened several seconds before the first eye closure.

Investigation of brain functional connectivity in patients with mild cognitive impairment: A functional near‐infrared spectroscopy (fNIRS) study

“…Five caps (two for short channel PDs and LEDs, and three for long channel PDs) were connected to form an fNIRS probe (Figure A). The detailed system design can be found in our previous studies . The fNIRS probe was firmly attached on the subjects' foreheads using a medical double‐layer tape such that the center cap was placed at exactly 15 mm below the Fpz position of EEG 10‐20 standard system (Figure A).…”

“…On the other hand, fNIRS is relatively low‐cost, and it can be applied to the populations previously inaccessible to fMRI . Additionally, whereas fMRI is sensitive to the concentration change of the deoxygenated form of hemoglobin (deoxyhemoglobin), fNIRS can measure signals of both oxyhemoglobin (HbO) and deoxyhemoglobin (Hb) . Furthermore, fNIRS is portable and unsusceptible to the motion artifact, and therefore, it can be utilized in a more flexible condition.…”

Decoding Neural Correlates of Cognitive States to Enhance Driving Experience

“…A wide range of classification methods has been applied for EEG-based mental state detection -from simple classifier models such as Linear Discriminant Analysis (LDA) [4], [17], and Support Vector Machines [18], [19] to artificial neural networks [10], [19]- [21]. Interestingly, some research groups have evaluated the possibility of applying transfer learning methods to reduce the amount of subject-specific data required to calibrate the EEG decoder [8], [9].…”

A novel time-frequency multilayer network for multivariate time series analysis

“…For each subject, the continuous EEG signals are segmented into 5 s non-overlapped epochs, and then we obtain 60 alert epochs and 60 fatigue epochs. The raw signals are down- [51,53]. We then overlap all 13 layers into a weighted projection network P i j , via equation (14).…”

“…Min et al [52] detected the driving fatigue through multiple entropy fusion and got high accuracy. Nguyen et al [53] combined EEG and NIRS to predict driving drowsiness via studying different brain regions and EEG bands. Wang et al [54] used power spectrum density and sample entropy in the online detection of mental fatigue based on EEG signals.…”