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.

The resurgence of passenger flows after the pandemic poses a significant challenge to the safe operation of rail transit. Therefore, adopting the waiting hall of an ultralarge railway station hub as an example, thermal radiation and evacuation simulations were conducted by the Fire Dynamics Simulator and Pathfinder, respectively. Island-style shops, known for their high crowd density and fire load, were defined as fire sources, and the effectiveness of a 6 m wide fire isolation zone was validated via the adoption of the dual-validation model. By comparing the relationships between the total evacuation population after passenger flow recovery and various evacuation parameters, it was shown that passengers were not evenly distributed among the exits in the waiting hall during an emergency, leading to uneven utilization. Furthermore, to gain a comprehensive understanding of the evacuation process under simulated fire conditions, an evacuation simulation involving 10,000 evacuees over a duration of 324.8 s was conducted. This study provides a theoretical basis for optimizing fire emergency evacuation plans for ultralarge railway station hubs.

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 machine, K-nearest neighbour and random forest) 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.

In status quo, electric vehicles are gradually replacing fuel-powered cars as the preferred mode of transportation in cities due to their unique advantages such as being environmentally friendly, easy to maintain, and low in noise. Comfort during the ride has also become a concern for people. This article investigates this issue by establishing a model. One criterion for evaluating comfort is the root mean square value of the acceleration generated by vibrations. This study focuses on a five-degree-of-freedom coupled model of electric vehicles and analyzes the vibrations during their movement on the road. A kinematic model of the five-degree-of-freedom coupled vibration of half of an electric vehicle is established, and the mathematical model of the motion model is obtained using the coefficient method. A simulation model of the kinematic model is constructed in MATLAB/Simulink, and road roughness input is generated using Simulink's filtered white noise. To ensure the accuracy of the simulation, a combined simulation model based on Adams and Simulink is also established in this study. Finally, the optimization design tool in Adams software is utilized to optimize some parameters of the model to achieve a comfortable ride.