Considering that driving stress is a major contributor to traffic accidents, detecting drivers’ stress levels in time is helpful for ensuring driving safety. This paper attempts to investigate the ability of ultra-short-term (30-s, 1-min, 2-min, and 3-min) HRV analysis for driver stress detection under real driving circumstances. Specifically, the t-test was used to investigate whether there were significant differences in HRV features under different stress levels. Ultra-short-term HRV features were compared with the corresponding short-term (5-min) features during low-stress and high-stress phases by the Spearman rank correlation and Bland–Altman plots analysis. Furthermore, four different machine-learning classifiers, including a support vector machine (SVM), random forests (RFs), K-nearest neighbor (KNN), and Adaboost, were evaluated for stress detection. The results show that the HRV features extracted from ultra-short-term epochs were able to detect binary drivers’ stress levels accurately. In particular, although the capability of HRV features in detecting driver stress also varied between different ultra-short-term epochs, MeanNN, SDNN, NN20, and MeanHR were selected as valid surrogates of short-term features for driver stress detection across the different epochs. For drivers’ stress levels classification, the best performance was achieved with the SVM classifier, with an accuracy of 85.3% using 3-min HRV features. This study makes a contribution to building a robust and effective stress detection system using ultra-short-term HRV features under actual driving environments.
Elevated mental workload (MWL) experienced by pilots can result in increased reaction times or incorrect actions, potentially compromising flight safety. This study aims to develop a functional system to assist administrators in identifying and detecting pilots’ real-time MWL and evaluate its effectiveness using designed airfield traffic pattern tasks within a realistic flight simulator. The perceived MWL in various situations was assessed and labeled using NASA Task Load Index (NASA-TLX) scores. Physiological features were then extracted using a fast Fourier transformation with 2-s sliding time windows. Feature selection was conducted by comparing the results of the Kruskal-Wallis (K-W) test and Sequential Forward Floating Selection (SFFS). The results proved that the optimal input was all PSD features. Moreover, the study analyzed the effects of electroencephalography (EEG) features from distinct brain regions and PSD changes across different MWL levels to further assess the proposed system’s performance. A 10-fold cross-validation was performed on six classifiers, and the optimal accuracy of 87.57% was attained using a multi-class K-Nearest Neighbor (KNN) classifier for classifying different MWL levels. The findings indicate that the wireless headset-based system is reliable and feasible. Consequently, numerous wireless EEG device-based systems can be developed for application in diverse real-driving scenarios. Additionally, the current system contributes to future research on actual flight conditions.
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.
hi@scite.ai
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.