<rss version="2.0" xmlns:atom="https://www.w3.org/2005/Atom">
  <channel>
    <title>Transport Research International Documentation (TRID)</title>
    <link>https://trid.trb.org/</link>
    <atom:link href="https://trid.trb.org/Record/RSS?s=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" rel="self" type="application/rss+xml" />
    <description></description>
    <language>en-us</language>
    <copyright>Copyright © 2026. National Academy of Sciences. All rights reserved.</copyright>
    <docs>http://blogs.law.harvard.edu/tech/rss</docs>
    <managingEditor>tris-trb@nas.edu (Bill McLeod)</managingEditor>
    <webMaster>tris-trb@nas.edu (Bill McLeod)</webMaster>
    <image>
      <title>Transport Research International Documentation (TRID)</title>
      <url>https://trid.trb.org/Images/PageHeader-wTitle.jpg</url>
      <link>https://trid.trb.org/</link>
    </image>
    <item>
      <title>Noise exposure, circadian misalignment, and fatigue in maritime operations: A case study on a Ro-Pax vessel</title>
      <link>https://trid.trb.org/View/2676854</link>
      <description><![CDATA[Fatigue represents a critical human-reliability concern in maritime operations and can undermine the safety performance of ship systems. This exploratory case study examines associations between onboard noise exposure, work–rest patterns, circadian typology, and seafarer fatigue aboard a Spanish-flagged Ro-Pax vessel. Objective noise measurements were collected following IMO guidelines, and crew fatigue and mental workload were assessed using the NASA-TLX, SOFI-SM, and rMEQ instruments (n = 22, representing 95.6% of the crew). Engine-room noise exceeded 96 dB(A), and cabin noise, while compliant with IMO limits, surpassed World Health Organization recommendations for undisturbed sleep. Higher role-based noise exposure was associated with higher levels of occupational fatigue, particularly in dimensions related to physical fatigue and physical discomfort, while no significant association was observed with perceived mental workload. Fatigue levels varied descriptively across occupational roles and circadian profiles, with higher fatigue observed in duty schedules misaligned with individual circadian preferences. The findings indicate that compliance with existing noise regulations does not necessarily ensure conditions conducive to adequate recovery or sustained human reliability. While causal relationships cannot be inferred, the study provides context-specific evidence supporting the integration of noise management, circadian-aware scheduling, and improved accommodation insulation into maritime safety and reliability frameworks.]]></description>
      <pubDate>Tue, 09 Jun 2026 14:43:22 GMT</pubDate>
      <guid>https://trid.trb.org/View/2676854</guid>
    </item>
    <item>
      <title>Heterogeneity mechanism and more precise prediction of seafarer fatigue based on group modelling</title>
      <link>https://trid.trb.org/View/2710182</link>
      <description><![CDATA[Traditional research often treats seafarers as a homogeneous group when exploring the causes of fatigue, neglecting the potential heterogeneity in fatigue mechanisms arising from differences in rank and department. This study systematically analyzes the fatigue driving patterns of four subgroups – Deck Department vs. Engine Department, and Officers vs. Ratings – and constructs high-precision prediction models. Based on questionnaire survey data from 450 seafarers from two Chinese shipping companies, Exploratory Factor Analysis was conducted to extract group-specific factors. Subsequently, Multiple Linear Regression and Backpropagation Neural Network models were established to identify key influencing factors and compare predictive performance. The results show that fatigue among Deck Officers is primarily driven by “Workload and Pressure" (β = 0.398); Engine Department seafarers (regardless of rank) are jointly influenced by “Sleep Quality" (β = 0.489-0.529) and “Work Pressure and Organizational Justice" (β = 0.415-0.451); Deck Ratings are most sensitive to “Sleep Quality and Environmental Interference" (β = 0.533). The predictive accuracy of the Backpropagation (BP) Neural Network model (test set Rbp = 0.636-0.895) was significantly better than that of the traditional linear model across all groups. The research demonstrates that seafarer fatigue exhibits significant group specificity, challenging the limitations of previous holistic studies, and provides a theoretical basis and effective tools for shipping companies to implement differentiated fatigue risk management.]]></description>
      <pubDate>Mon, 08 Jun 2026 15:48:01 GMT</pubDate>
      <guid>https://trid.trb.org/View/2710182</guid>
    </item>
    <item>
      <title>Long-Distance Route Planning for Electric Vehicles Considering Range Anxiety and Fatigue Constraints</title>
      <link>https://trid.trb.org/View/2709165</link>
      <description><![CDATA[This research proposes to tackle two important issues in long-distance travel for electric vehicles (EVs): range anxiety and driver fatigue. A new route planning approach integrating the perception of psychological and physiological states is presented. This model quantifies range anxiety by integrating conditions such as battery depletion, charging station coverage, and traffic congestion and explicitly considers the evolution of driver fatigue influenced by continuous driving behavior and circadian rhythms, as well as a time-overlapping strategy for simultaneously arranging charging and rest tasks. To efficiently solve the route planning problem for large-scale road networks, this research develops an optimization approach using an A*-guided adaptive genetic algorithm (A*-AGA), which integrates heuristic search and evolutionary optimization. Simulation experiments on typical long-distance routes demonstrate that the approach is highly effective in reducing driver anxiety and fatigue, optimizing the total travel time, ensuring the route's feasibility, and greatly improving the long-distance EV driving experience.]]></description>
      <pubDate>Tue, 02 Jun 2026 13:56:35 GMT</pubDate>
      <guid>https://trid.trb.org/View/2709165</guid>
    </item>
    <item>
      <title>Assessing Physical Fatigue in Highway Maintenance Workers through Electromyography: The Impact of Lifting Weights and Heights on Bag Handling</title>
      <link>https://trid.trb.org/View/2640395</link>
      <description><![CDATA[Workers’ physical fatigue can negatively affect their health and safety. Electromyography (EMG) has been widely adopted to detect physical fatigue in vertical building construction activities, while its implementation is lacking in horizontal transportation maintenance activities. Considering the differences in frequency, duration, and intensity of horizontal transportation maintenance activities, this study explored the feasibility of using wearable EMG sensors to measure electrical impulses generated by muscles of highway maintenance workers, who need to lift bags with different lifting weights and heights, to evaluate their physical fatigue. To this end, this study conducted experiments of workers lifting three different weights of dry concrete mix bags (31.5, 50, and 80 pounds) from different heights, which is considered the most common activity that highway maintenance workers perform and that causes most ergonomic injuries. EMG data was acquired from the left and right back muscles of 29 highway maintenance workers of the Indiana Department of Transportation. Results confirmed that a lighter lifting weight and a higher lifting height have significant positive effects on reducing physical fatigue among highway maintenance workers who perform lifting bags of dry concrete mix.]]></description>
      <pubDate>Thu, 28 May 2026 17:09:37 GMT</pubDate>
      <guid>https://trid.trb.org/View/2640395</guid>
    </item>
    <item>
      <title>Sleep and driving performance of Indonesian drivers during Ramadan</title>
      <link>https://trid.trb.org/View/2698556</link>
      <description><![CDATA[Ramadan fasting leads to significant alterations in daily routines, notably disrupting sleep schedules. Such changes can impair cognitive functioning and driving performance, thereby increasing the risk of accidents. This study investigated the relationship between sleep quality and driving performance among Indonesian drivers during Ramadan. A total of 273 Indonesian drivers who observed Ramadan fasting participated in an electronic survey. The survey assessed sleep behaviors, subjective sleepiness across different times of day, and self-reported driving performance. Data were analyzed using descriptive statistics, Analysis of Variance (ANOVA), and Pearson correlation tests. Participants reported increased daytime sleepiness during Ramadan, with the highest fatigue levels observed around noon. Poorer night-time sleep quality and suboptimal nap quality were significantly associated with elevated aggressive driving behaviors and reduced driving performance. Although increases in accidents and traffic violations were modest, they highlight the public health importance of sleep management during fasting periods. Ramadan fasting negatively affects sleep patterns and driving behavior among Indonesian drivers. Interventions promoting sleep hygiene and strategic napping could substantially enhance driving safety during Ramadan. Future research should incorporate objective performance assessments to strengthen and validate these findings.]]></description>
      <pubDate>Thu, 28 May 2026 09:03:40 GMT</pubDate>
      <guid>https://trid.trb.org/View/2698556</guid>
    </item>
    <item>
      <title>Exploring stress-coupling dynamics in fatigue development among high-speed railway drivers</title>
      <link>https://trid.trb.org/View/2700587</link>
      <description><![CDATA[This study explores the coupling dynamics between stress and fatigue among high-speed railway (HSR) drivers, addressing the need to understand how different stress levels and prolonged driving time jointly influence psychological and physiological responses on fatigue. A within-subject driving simulation experiment was conducted using a HSR simulator under low- and high-stress scenarios, involving 17 professional railway drivers. 27 heart rate variability (HRV) features and subjective fatigue and stress were recorded. Dynamic time warping and linear mixed-effects models were employed to characterize fatigue development patterns and examine the interaction effects of driving time and stress. Results indicate different developmental patterns under different stress levels. Both driving time and stress level significantly influence subjective and physiological fatigue. High-stress conditions affect baseline HRV levels at early time but then accelerate the fatigue accumulation process. Physiological responses exhibit similar trends across individuals. The interaction effect between time and stress is significant for subjective fatigue. This study demonstrates different developmental patterns of HSR drivers’ fatigue under different stress levels. Prolonged driving leads to cumulative fatigue, while different stress conditions affect baseline HRV levels and subjective fatigue feeling. Perceptual narrowing effect exists in high-stress driving, leading to an unconscious perception of accumulating fatigue. These findings underscore the necessity of integrating both stress and fatigue monitoring into HSR driver training and management, providing reference for designing evidence-based scheduling and safety strategies to enhance HSR operational reliability and drivers’ occupational health.]]></description>
      <pubDate>Wed, 27 May 2026 10:48:18 GMT</pubDate>
      <guid>https://trid.trb.org/View/2700587</guid>
    </item>
    <item>
      <title>Insomnia, fatigue, and risky driving behaviors among professional drivers: A cross-sectional study in Tunisia</title>
      <link>https://trid.trb.org/View/2694556</link>
      <description><![CDATA[Professional drivers worldwide face elevated risks of sleep disturbances and fatigue due to demanding occupational conditions, contributing significantly to road traffic trauma. In Tunisia, where professional drivers are involved in nearly a quarter of all accidents but account for almost a third of fatalities, research in this North African context remains critically limited.   This cross-sectional study examined the prevalence and associations of insomnia, fatigue, and risky driving behaviors among 387 professional drivers in Tunisia (mean age 42.3 ± 10.8 years; 99.7% male). Participants completed validated questionnaires including the Insomnia Severity Index (ISI), structured fatigue assessments, and risky driving behavior scales.   Results revealed that 34.6% of drivers experienced clinically significant insomnia, with 18.3% reporting moderate-to-severe symptoms. Excessive fatigue while driving was reported by 41.3% of participants, with truck drivers showing the highest prevalence (51.4%). Binary logistic regression analyses demonstrated that insomnia severity (AOR = 2.84, 95% CI: 1.76–4.58, p < 0.001), younger age (<35 years; AOR = 2.12), longer weekly work hours (>60 h; AOR = 1.89), self-employment status (AOR = 1.71), frequent night driving (AOR = 1.68), and short sleep duration (<6 h; AOR = 2.45) were significantly associated with excessive fatigue during driving. Fatigue, in turn, was strongly associated with risky driving behaviors, including drowsy driving (AOR = 7.35, p < 0.001), speeding (AOR = 2.81), mobile phone use (AOR = 2.59), and tailgating (AOR = 2.35).   These findings underscore the critical need for multi-level interventions targeting sleep health among Tunisian professional drivers, including workplace schedule optimization, insomnia screening and treatment programs, and strengthened regulatory enforcement of work hour limits. This study provides the first systematic evidence linking insomnia, fatigue, and driving safety in the North African context, contributing essential baseline data for culturally appropriate intervention development.]]></description>
      <pubDate>Tue, 19 May 2026 15:12:28 GMT</pubDate>
      <guid>https://trid.trb.org/View/2694556</guid>
    </item>
    <item>
      <title>Assessing how physical and mental fatigue affect driving speed on the Banda Aceh–Medan highway, Indonesia</title>
      <link>https://trid.trb.org/View/2701233</link>
      <description><![CDATA[This study was motivated by the relatively high number of traffic accidents along Banda Aceh–Medan highway, where driver fatigue has been repeatedly cited as the key contributing factor. The research aimed to determine the extent to which physical and mental fatigue influence driving speed behavior on this long-distance route. A quantitative survey was conducted with 400 drivers, both professional and private, using the validated fatigue scales and Structural Equation Modeling for the data analysis. The results indicated that physical fatigue negatively affects speed stability, while mental fatigue significantly increases speed variability. Nevertheless, both physical and mental fatigue explaining 57.8% of the variance in driving speed. These findings highlight the dual cognitive and physiological dimensions of fatigue, emphasizing its role in impaired speed regulation and increased accident risk. This study contributes to existing knowledge by quantifying the distinct effects of physical and mental fatigue on driving performance in a real-world setting, thereby offering empirical support for targeted fatigue management interventions on long-distance routes.]]></description>
      <pubDate>Mon, 11 May 2026 15:23:43 GMT</pubDate>
      <guid>https://trid.trb.org/View/2701233</guid>
    </item>
    <item>
      <title>The unintended consequences of monitoring technologies: Evidence from the Electronic Logging Device mandate</title>
      <link>https://trid.trb.org/View/2661790</link>
      <description><![CDATA[The electronic logging device (ELD) final rule was passed in 2015 and implemented in phases over the course of four years. The mandate required that most commercial motor vehicles be fitted with an ELD by December 2019. The primary purpose of the transportation safety policy is to better enforce existing hours-of-service (HOS) regulations. HOS rules seek to limit the amount of driving time commercial drivers are on the road each day to avoid fatigued driving that may cause accidents and fatalities. Prior to the ELD mandate, commercial long-haul drivers cited that they regularly violated daily and weekly HOS rules when paper driving logs could be easily manipulated.Using data from the Fatality Analysis Reporting System (FARS) on traffic fatalities, we run two sets of difference-in-differences analyses exploiting the introduction of the ELD mandate: one predicting the change in fatal truck accidents as well as fatalities and injuries in these accidents and one showing the possible aggressive driving mechanisms (e.g., speeding, drunk driving) behind the main effects. Our first model finds that the ELD mandate led to an increase in fatal truck accidents by 8 %, an increase in truck fatalities by 11 %, and an increase in the number of surviving passengers with severe injuries experienced by 17 %. Our second model finds that fatal crashes with aggressive driving behaviors by truck drivers increased by 12 % in the post period, supporting the first model's results. Additionally, and as placebo exercises, we find no change in the average fatality and injury rates once we modify the timing of the policy (post-ELD period to the years before the phased-in compliance of 2017), the presence of outliers or the composition of the treated group.]]></description>
      <pubDate>Thu, 30 Apr 2026 16:38:37 GMT</pubDate>
      <guid>https://trid.trb.org/View/2661790</guid>
    </item>
    <item>
      <title>Implementation of Karolinska sleepiness scale to improve pilots awareness and confidence in fatigue reporting</title>
      <link>https://trid.trb.org/View/2666901</link>
      <description><![CDATA[Fatigue among pilots in short-haul, multi-sector night freight operations remains a critical challenge to aviation safety. Irregular schedules and prolonged exposure to the Window of Circadian Low (WOCL) cause cognitive impairments, slower reaction times, and reduced situational awareness. Despite regulatory frameworks such as Fatigue Risk Management Systems (FRMS), cultural and organisational barriers, including fear of punitive action and lack of standardised tools, continue to limit effective fatigue reporting. This study investigates the use of the Karolinska Sleepiness Scale (KSS) as a subjective fatigue management tool in short-haul night freight operations. A mixed-methods approach was applied, combining a six-week survey with semi-structured interviews. The study provides the first systematic evaluation of the KSS not only as a fatigue measurement instrument but also as a communication tool that bridges the gap between pilot experience and FRMS reporting practices in short-haul night freight operations. Pilots used the KSS during operational duties to assess fatigue levels and evaluate its influence on awareness and reporting practices. Findings indicate that the KSS improves pilots’ ability to recognise and communicate fatigue, supports proactive workload management, and fosters collaboration within crews. However, organisational gaps remain, including the absence of integration into Standard Operating Procedures (SOPs), lack of structured training, and hesitancy among less experienced pilots without formal company endorsement. The study recommends the formal adoption of the KSS into SOPs, supported by recurrent training and feedback mechanisms, together with integration of objective measures such as biometrics. Results highlight the potential of the KSS as a cornerstone of fatigue risk management and emphasise the importance of supportive safety cultures in prioritising pilot well-being as a key component of operational safety.]]></description>
      <pubDate>Wed, 29 Apr 2026 16:34:58 GMT</pubDate>
      <guid>https://trid.trb.org/View/2666901</guid>
    </item>
    <item>
      <title>Fatigue estimation of OOWs based on eye-tracking technology: A hybrid experimental study</title>
      <link>https://trid.trb.org/View/2638337</link>
      <description><![CDATA[Seafarer fatigue caused by prolonged and monotonous work is a key contributing factor in maritime accidents. This study designs an experiment using eye-tracking technology aimed at developing an objective fatigue estimation method for Officer on Watch (OOW). Sixteen nautical students from different majors participated in simulator experiments, during which data from subjective fatigue assessments, eye movement indicators, reaction time, and stress levels were recorded. The results indicate that participants experienced increasing fatigue over time, as reflected by major changes in these indicators. Spearman correlation analysis revealed strong correlations between fatigue levels and pupil diameter. Additionally, machine learning models and Receiver Operating Characteristic curves were used to evaluate the predictive ability of the recorded indicators. The findings suggest that pupil diameter is the most reliable OOW fatigue indicator. Subsequent real-ship experiments verified these findings, demonstrating the feasibility of using eye movement indicators to objectively estimate and quantify OOW fatigue. From a safety management perspective, personalized fatigue management strategies are recommended to mitigate OOW fatigue and enhance navigational safety.]]></description>
      <pubDate>Mon, 27 Apr 2026 15:01:22 GMT</pubDate>
      <guid>https://trid.trb.org/View/2638337</guid>
    </item>
    <item>
      <title>Remote Tower Air Traffic Controller Multimodal Fatigue Detection</title>
      <link>https://trid.trb.org/View/2691613</link>
      <description><![CDATA[Remote tower (rTWR) operations are reshaping air traffic control but introduce significant human-factor risks, notably cognitive fatigue induced by prolonged screen-based visual surveillance. To mitigate these risks in a safety-critical domain where missed detections can be catastrophic, we propose a non-intrusive, multimodal fatigue detection framework fusing ocular and cardiac signals. A high-fidelity simulation study with 36 controllers was conducted to collect eye-tracking and electrocardiogram (ECG) data, from which a 12-dimensional feature vector-integrating gaze entropy and heart rate variability (HRV)-was extracted. Addressing the severe class imbalance and scarcity of fatigue samples in physiological data, we developed a cost-sensitive XGBoost classifier combining SMOTE oversampling with a dynamically weighted loss function. Experimental results show that the proposed framework performed well under mixed-subject evaluation and improved sensitivity to fatigue events. Although a marked performance drop was observed under LOSO evaluation, personalized calibration partially alleviated this limitation, indicating the potential of the framework for real-time fatigue monitoring in remote tower operations.]]></description>
      <pubDate>Mon, 27 Apr 2026 15:01:14 GMT</pubDate>
      <guid>https://trid.trb.org/View/2691613</guid>
    </item>
    <item>
      <title>A Multimodal Drowsiness Dataset Using Video, Biometric, and Behavioral Data</title>
      <link>https://trid.trb.org/View/2691606</link>
      <description><![CDATA[We present a comprehensive public dataset for driver drowsiness detection, integrating multimodal signals of facial, behavioral, and biometric indicators. Our dataset includes 3D facial video, infrared footage, posture videos, and biometric signals like heart rate, electrodermal activity, blood oxygen saturation, skin temperature, and accelerometer data. This data set provides grip sensor data and telemetry data to provide more information about drivers' behavior while they are alert and drowsy. Drowsiness levels were self-reported every four minutes using the Karolinska Sleepiness Scale (KSS). Data were collected from 19 subjects in two conditions: when they were fully alert and when they exhibited signs of sleepiness. Unlike other datasets, our multimodal dataset has a continuous duration of 40 minutes for each data collection session per subject, contributing to a total length of 1,400 minutes. We recorded gradual changes in the driver state rather than discrete alert/drowsy labels. This study aims to create a publicly available multimodal dataset of driver drowsiness that captures a wider range of physiological, behavioral, and driving-related signals.]]></description>
      <pubDate>Mon, 27 Apr 2026 15:01:14 GMT</pubDate>
      <guid>https://trid.trb.org/View/2691606</guid>
    </item>
    <item>
      <title>Stress on the road: Linking coping strategies, resilience, and fatigue in female school service drivers</title>
      <link>https://trid.trb.org/View/2694333</link>
      <description><![CDATA[BackgroundOccupational stress can lead to various physical and psychological issues, including fatigue, anxiety, and burnout. Fatigue, in particular, influences drivers’ behavior, and resilience is a key factor in mitigating occupational stress and fatigue.ObjectiveThis study aims to explore the relationship between coping styles, occupational fatigue, occupational stress, and resilience in female school service drivers.MethodsA cross-sectional descriptive study was conducted in 2024 among 206 female school service drivers in Isfahan, selected through random sampling. Data were collected using the Swedish Job Fatigue Questionnaire (SOFI-20), Connor-Davidson Resilience Scale, HSE Questionnaire, and the Coping Inventory for Stressful Situations (CISS). Statistical analysis was performed using SPSS22 at a 0.05 significance level.ResultsThe study found that female drivers had mean scores of 61.44 (±11.37) for resilience, 109.31 (±21.95) for occupational fatigue, and 118.10 (±31.68) for occupational stress. Emotion-oriented coping was the most frequent strategy (37.5%), while avoidance-oriented coping was the least frequent (26.4%). A significant negative correlation between resilience and occupational fatigue indicated that higher fatigue levels reduce resilience, increasing the risk of health-related issues.ConclusionThe study reveals that occupational fatigue negatively impacts resilience and shifts coping strategies toward emotion-oriented approaches, increasing accident risks among female school service drivers. It emphasizes the need for interventions to reduce fatigue and enhance resilience through targeted training programs for safer driving behavior.]]></description>
      <pubDate>Thu, 23 Apr 2026 09:11:30 GMT</pubDate>
      <guid>https://trid.trb.org/View/2694333</guid>
    </item>
    <item>
      <title>From single-modal to multi-modal: How does multi-modal data integration enhance the precision of seafarer fatigue detection?</title>
      <link>https://trid.trb.org/View/2660619</link>
      <description><![CDATA[Seafarer fatigue, stemming from monotonous navigational tasks and high work pressure, significantly increases accident risk. Existing studies often lack accuracy and reliability, relying on single-modal, simulated data. To fill this gap, this study conducted a 24-day real navigation experiment, collecting physiological (EEG, EDA, ECG) and psychological (Psych) data from 24 seafarers, yielding 212 labeled samples. Next, a total of 32-dimensional fatigue features were extracted from the multi-modal data, and a feature layer fusion strategy was proposed. Eight machine learning algorithms (including DT, KNN, SVM, ANN, RF, AdaBoost, XGBoost, and LightGBM) were then used to establish the multi-modal fatigue recognition model. The dataset was split 7:3 (train/test), with class imbalance corrected using SMOTE. Model performance was subsequently evaluated on the held-out test set using accuracy, precision, recall, and F1-score as primary indicators. A thorough comparison between single-modal, bi-modal, and multi-modal situations was conducted. The results indicated that the multi-modal approach (integrating EEG, EDA, ECG, and Psych) significantly outperforms other methods. The LightGBM model achieved a maximum accuracy of 95.93 %. This study contributes to more effective fatigue detection, enhancing seafarer management and navigation safety.]]></description>
      <pubDate>Tue, 21 Apr 2026 14:30:16 GMT</pubDate>
      <guid>https://trid.trb.org/View/2660619</guid>
    </item>
  </channel>
</rss>