Heart Rate Variability-Based Driver Drowsiness Detection and Its Validation With EEG

Abstract

Driver drowsiness detection is a key technology that can prevent fatal car accidents caused by drowsy driving. The present work proposes a driver drowsiness detection algorithm based on heart rate variability (HRV) analysis and validates the proposed method by comparing with electroencephalography (EEG)-based sleep scoring. Methods: Changes in sleep condition affect the autonomic nervous system and then HRV, which is defined as an RR interval (RRI) fluctuation on an electrocardiogram trace. Eight HRV features are monitored for detecting changes in HRV by using multivariate statistical process control, which is a well known anomaly detection method. Result: The performance of the proposed algorithm was evaluated through an experiment using a driving simulator. In this experiment, RRI data were measured from 34 participants during driving, and their sleep onsets were determined based on the EEG data by a sleep specialist. The validation result of the experimental data with the EEG data showed that drowsiness was detected in 12 out of 13 pre-N1 episodes prior to the sleep onsets, and the false positive rate was 1.7 times per hour. Conclusion: The present work also demonstrates the usefulness of the framework of HRV-based anomaly detection that was originally proposed for epileptic seizure prediction. Significance: The proposed method can contribute to preventing accidents caused by drowsy driving.

Feature Extraction and Evaluation for Driver Drowsiness Detection Based on Thermoregulation

“…In addition, an accuracy of around 78% corresponds to these results. In contrast to the two prior studies which used behavioral signs as a reference for the state of the driver, Fujiwara et al validated their HRV-based drowsiness detection with EEG measurements [33]. Here, the algorithm was successful if drowsiness was indicated in a period of 15 min before sleep onset (NREM sleep stage 1).…”

“…By executing the measurements at different moments, a generalization of the results is possible. For instance, Fujiwara et al [33] used data collected at 11:00 and after lunch. However, we have to keep in mind that the theory behind this method is related to actual sleep onset and does not relate directly to short drops in attention throughout the day.…”

The Design of CNN Architectures for Optimal Six Basic Emotion Classification Using Multiple Physiological Signals

“…There have been many studies using various parameters of bio signals using sensors. Fujiwara et al [45] proposed drowsiness detection and validation with HRV analysis and EEG-based signals. Szypulska et al [46], similar to Fujiwara et al [45], used HRV analysis to predict fatigue and sleep onset.…”

“…Fujiwara et al [45] proposed drowsiness detection and validation with HRV analysis and EEG-based signals. Szypulska et al [46], similar to Fujiwara et al [45], used HRV analysis to predict fatigue and sleep onset. In addition, research has been proposed to reconstruction PPG signals into ECG signals using MLP.…”

Ad-Hoc Shallow Neural Network to Learn Hyper Filtered PhotoPlethysmoGraphic (PPG) Signal for Efficient Car-Driver Drowsiness Monitoring

“…The results obtained by the authors in [3] are interesting and can be used to develop a drowsiness detection system for ADAS applications. A very interesting approach has been proposed by the authors of [4]. The authors monitored specific changes in sleep condition reflected over the ANS and then on the related HRV.…”