Fatigue among urban railway transit (URT) drivers affects their performance and is a contributing factor in many railway accidents and incidents. This paper attempts to develop a robust fatigue detection system for URT drivers. An experimental study was conducted in actual work conditions, involving 198 professional URT drivers, to provide authentic and representative data. Fatigue scores based on the Karolinska Sleepiness Scale were used as the ground truth, and heart rate variability (HRV) data were collected using wearable photoplethysmography (PPG) sensors under actual working conditions. An extensive statistical analysis found that continuous working hours were a major factor in driver fatigue. HRV features were able to differentiate various fatigue levels. Four classifiers (k-nearest neighbors, Naive Bayes, support vector machines, and random forests) were trained to detect fatigue in real time for binary and three-class fatigue classifications, respectively. For the binary classification, the best performance was achieved by the random forest classifier using the corrected feature set as input with an accuracy of 92.5%. However, the accuracy dropped by 8 to 27 percentage points for the three-class classification. Moreover, the research found that the corrected feature set circumventing inter-individual variability in HRV could improve the performance of fatigue classifiers. The findings from this research could contribute to developing a robust and real-time URT driver fatigue detection system and improve current URT operational safety regulations.
Driver fatigue has a direct impact on urban railway transit (URT) drivers’ driving behavior and can cause driver error. The existing methods for fatigue detection mainly train the models with supervised learning, relying heavily on the annotation of recorded data. However, labeled data are unobtainable in some environments, especially for URT driver fatigue levels during actual driving. Therefore, this study proposes a fatigue detection method using unlabeled heart rate variability data to monitor URT driver fatigue in actual working conditions. By utilizing the existing conclusions with regard to factors contributing to fatigue and physiological changes, this study annotated a small number of samples and then used a novel positive and unlabeled learning algorithm based on nearest neighbors and random forest to divide samples into different fatigue levels. The proposed method was evaluated using the URT driver fatigue data sets collected in the lab. Binary classification achieved an accuracy of 79.0%. However, the accuracy of three-class classification was only 55.7%. In addition, the proposed method performed as well using the field data set as it did using the lab data set. The results show the high generalization performance of the proposed method, which could contribute to addressing the issue of lack of labeled training data for fatigue detection in actual working 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.