Objective: Driver fatigue is considered to be a major contributor to road traffic crashes. Cardiac monitoring and heart rate variability (HRV) analysis is a candidate method for early and accurate detection of driver sleepiness. This study has 2 objectives: to evaluate the (1) suitability of different preprocessing strategies for detecting and removing outlier heartbeats and spectral transformation of HRV signals and their impact of driver sleepiness assessment and (2) relation between common HRV indices and subjective sleepiness reported by a large number of drivers in real driving situations, for the first time. Methods: The study analyzed >3,500 5-min driving epochs from 76 drivers on a public motorway in Sweden. The electrocardiograph (ECG) data were recorded in 3 studies designed to evaluate the physiological differences between awake and sleepy drivers. The drivers reported their perceived level of sleepiness according to the Karolinska Sleepiness Scale (KSS) every 5 min. Two standard methods were used for identifying outlier heartbeats: (1) percentage change (PC), where outliers were defined as interbeat intervals deviating >30% from the mean of the four previous intervals and (2) standard deviation (SD), where outliers were defined as interbeat interval deviating >4 SD from the mean interval duration in the current epoch. Three standard methods were used for spectral transformation, which is needed for deriving HRV indices in the frequency domain: (1) Fourier transform;(2) autoregressive model; and (3) Lomb-Scargle periodogram. Different preprocessing strategies were compared regarding their impact on derivation of common HRV indices and their relation to KSS data distribution, using box plots and statistical tests such as analysis of variance (ANOVA) and Student's t test.Results: The ability of HRV indices to discriminate between alert and sleepy drivers does not differ significantly depending on which outlier detection and spectral transformation methods are used. As expected, with increasing sleepiness, the heart rate decreased, whereas heart rate variability overall increased. Furthermore, HRV parameters representing the parasympathetic branch of the autonomous nervous system increased. An unexpected finding was that parameters representing the sympathetic branch of the autonomous nervous system also increased with increasing KSS level. We hypothesize that this increment was due to stress induced by trying to avoid an incident, because the drivers were in real driving situations. Conclusions: The association of HRV indices to KSS did not depend on the preprocessing strategy. No preprocessing method showed superiority for HRV association to driver sleepiness. This was also true for combinations of methods for frequency domain HRV indices. The results prove clear relationships between HRV indices and perceived sleepiness. Thus, HRV analysis shows promise for driver sleepiness detection. ARTICLE HISTORY
Objective: This paper aims to describe and test novel computational driver models, predicting drivers’ brake reaction times (BRTs) to different levels of lead vehicle braking, during driving with cruise control (CC) and during silent failures of adaptive cruise control (ACC). Background: Validated computational models predicting BRTs to silent failures of automation are lacking but are important for assessing the safety benefits of automated driving. Method: Two alternative models of driver response to silent ACC failures are proposed: a looming prediction model, assuming that drivers embody a generative model of ACC, and a lower gain model, assuming that drivers’ arousal decreases due to monitoring of the automated system. Predictions of BRTs issued by the models were tested using a driving simulator study. Results: The driving simulator study confirmed the predictions of the models: (a) BRTs were significantly shorter with an increase in kinematic criticality, both during driving with CC and during driving with ACC; (b) BRTs were significantly delayed when driving with ACC compared with driving with CC. However, the predicted BRTs were longer than the ones observed, entailing a fitting of the models to the data from the study. Conclusion: Both the looming prediction model and the lower gain model predict well the BRTs for the ACC driving condition. However, the looming prediction model has the advantage of being able to predict average BRTs using the exact same parameters as the model fitted to the CC driving data. Application: Knowledge resulting from this research can be helpful for assessing the safety benefits of automated driving.
The standard preprocessing methods for HRV data for outlier heartbeat detection and spectral transformation show low levels of agreement. This finding implies that, prior to designing algorithms for detection of sleepy drivers based on HRV analysis, the impact of different preprocessing methods and combinations thereof on driver sleepiness assessment needs to be studied.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.