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.
Previous studies have found that drivers’ physiological conditions can deteriorate under noise conditions, which poses a potential hazard when driving. As a result, it is crucial to identify the status of drivers when exposed to different noises. However, such explorations are rarely discussed with short-term physiological indicators, especially for rail transit drivers. In this study, an experiment involving 42 railway transit drivers was conducted with a driving simulator to assess the impact of noise on drivers’ physiological responses. Considering the individuals’ heterogeneity, this study introduced drivers’ noise annoyance to measure their self-noise-adaption. The variances of drivers’ heart rate variability (HRV) along with different noise adaptions are explored when exposed to different noise conditions. Several machine learning approaches (Support Vector Machines, K-nearest Neighbors, and Random Forests) were then used to classify their physiological status under different noise conditions according to the HRV and drivers’ self-noise adaptions. Results indicate that the volume of traffic noise negatively affects drivers’ performance in their routines. Drivers with different noise adaptions but exposed to a fixed noise were found with discrepant HRV, demonstrating that noise adaption is highly associated with drivers’ physiological status under noises. It is also found that noise adaption inclusion could raise the accuracy of classifications. Overall, the Random Forests classifier performed the best in identifying the physiological status when exposed to noise conditions for drivers with different noise adaptions.
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.