<?xml version="1.0" encoding="utf-8"?>
    <rss version="2.0">
      <channel xmlns:content="http://purl.org/rss/1.0/modules/content/">
        <title>Frontiers in Future Transportation | New and Recent Articles</title>
        <link>https://www.frontiersin.org/journals/future-transportation</link>
        <description>RSS Feed for Frontiers in Future Transportation | New and Recent Articles</description>
        <language>en-us</language>
        <generator>Frontiers Feed Generator,version:1</generator>
        <pubDate>2026-05-02T22:53:42.958+00:00</pubDate>
        <ttl>60</ttl>
        <item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/ffutr.2026.1765638</guid>
        <link>https://www.frontiersin.org/articles/10.3389/ffutr.2026.1765638</link>
        <title><![CDATA[Signal reconstruction frameworks for intelligent transportation systems: from nonuniform sampling to energy-efficient sensing]]></title>
        <pubdate>2026-04-29T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Manuel J. C. S. Reis</author>
        <description><![CDATA[IntroductionUrban-scale intelligent transportation systems rely on heterogeneous sensor networks that often operate under irregular sampling schedules and strict energy constraints. These conditions challenge the stable and accurate reconstruction of sensed signals in large-scale mobility and environmental monitoring applications. This paper proposes a stability-aware framework for adaptive and energy-efficient signal reconstruction in such resource-constrained urban sensing environments.MethodsThe proposed framework builds on generalized and nonuniform sampling theory and extends B-spline and Riesz-basis formulations to irregularly sampled signals acquired by urban sensor networks. It derives explicit quantitative trade-offs among sampling density, energy consumption, and reconstruction accuracy, and establishes theoretical stability conditions under sparse and jittered acquisition. The approach is assessed through comprehensive simulations using synthetic traffic-density signals across different sampling densities, jitter levels, and additive noise conditions.ResultsThe results show that the Riesz-basis iterative reconstruction achieves fidelity comparable to spline-based reconstruction once the sampling density exceeds the predicted stability threshold. Under these conditions, sensing energy consumption is reduced by up to 60% while maintaining high reconstruction quality. The framework also exhibits graceful degradation under additive noise and preserves structural similarity above 0.8 at 10 dB SNR, demonstrating robust performance for edge-deployed sensors.DiscussionThe findings indicate that stability-aware sampling design can effectively balance reconstruction accuracy and energy efficiency in heterogeneous urban sensor networks. By integrating rigorous signal-processing theory with practical green-sensing requirements, the proposed framework provides a mathematically grounded basis for resilient and low-power data acquisition in future intelligent transportation infrastructures.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/ffutr.2026.1766069</guid>
        <link>https://www.frontiersin.org/articles/10.3389/ffutr.2026.1766069</link>
        <title><![CDATA[Equity-based spatial clustering of unmet DRT demand for fixed-route transit optimization in underserved areas]]></title>
        <pubdate>2026-04-24T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Diana Al-Nabulsi</author><author>Jun-Seok Oh</author><author>Valerian Kwigizile</author>
        <description><![CDATA[This study presents a spatially explicit framework for identifying and prioritizing unmet mobility demand for Demand-Responsive Transit (DRT) in Kalamazoo County, Michigan. By overlaying fixed-route transit stops with DRT origin–destination data, the analysis reveals persistent accessibility gaps, particularly in suburban and rural areas. A buffer sensitivity analysis shows that 22.9% of trip origins and 21.9% of destinations fall outside the standard 0.5-mile walkability threshold, highlighting structural first- and last-mile disconnects. Density-Based Spatial Clustering of Applications with Noise (DBSCAN) identifies 27 clusters of unserved demand. These clusters are ranked using a composite Priority Score Index incorporating trip density and socio-demographic indicators, including income, poverty, and disability prevalence. High-ranking clusters exhibit both concentrated unmet demand and elevated social vulnerability. Temporal analysis indicates that 82% of unserved trips occur on weekdays, with peaks during commuting hours. The findings demonstrate the limitations of fixed-route systems in dispersed environments and provide an equity-informed framework to guide targeted DRT deployment. The proposed methodology offers a replicable and scalable approach for transit agencies seeking to integrate demand-responsive services into hybrid transit systems.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/ffutr.2026.1803715</guid>
        <link>https://www.frontiersin.org/articles/10.3389/ffutr.2026.1803715</link>
        <title><![CDATA[Integrated airline recovery considering passengers’ decision-making under disruptions]]></title>
        <pubdate>2026-04-24T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Shuai Wu</author><author>Enze Liu</author><author>Rui Cao</author><author>Xu Zhang</author>
        <description><![CDATA[This paper investigates the integrated airline recovery problem by incorporating passengers’ decision-making, with disrupted passengers categorized into three types: those experiencing delays, those opting for refunds, and those denied boarding due to capacity constraints. To enhance operational flexibility, an improvement is made to the aircraft swap recovery strategy, allowing the replacement of larger aircraft with smaller ones. A bi-objective mathematical model is then constructed to minimize both airline recovery costs and passenger utility loss, and the Nondominated Sorting Genetic Algorithm II (NSGA-II) is designed to solve the model. Computational results demonstrate that the proposed approach outperforms the benchmark plan, achieving average reductions of 17.15% in airline recovery costs and 16.59% in passenger utility loss. Scenario analysis further reveals that the improved aircraft swap strategy is particularly effective for small-scale disruptions, whereas the explicit consideration of passengers’ decision-making yields superior solutions in large-scale disruption scenarios. Overall, this study provides a more realistic recovery framework that balances operational efficiency with passenger-centric considerations, offering valuable insights for airline disruption management.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/ffutr.2026.1800459</guid>
        <link>https://www.frontiersin.org/articles/10.3389/ffutr.2026.1800459</link>
        <title><![CDATA[Evolutionary multicriteria planning of bus stops location in smart cities]]></title>
        <pubdate>2026-04-15T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Santiago Lopez de Haro</author><author>Sergio Nesmachnow</author><author>Diego Rossit</author>
        <description><![CDATA[In modern smart cities, public transportation systems are the foundation of mobility services. Specifically, public bus services are crucial for improving accessibility and the quality of life for many residents, as they provide an affordable and flexible means of travel. A primary consideration in bus network planning involves strategically determining the optimal placement of bus stops throughout the service area. Conventional bus network planning prioritized system operator cost-efficiency as the primary objective, relegating user quality of service to a subordinate goal. Conversely, recent modeling efforts have shifted focus toward user-centric objectives to facilitate the principles of the Transit Oriented Development paradigm. This article introduces a solution to the multicriteria Bus Stop Location Problem, to find the best placement for bus stops to effectively balance user accessibility, service efficiency, and operational costs. To solve this complex trade-off, a multi-objective evolutionary algorithm is developed. The algorithm simultaneously optimizes three key, often conflicting, objectives: i) maximize demand coverage, to ensure the service reaches the most potential users, ii) minimize travel times, by reducing the total number of stops, and iii) minimize operational costs, measured and weighted based on passenger demand. The research applies the resolution approach to real-world case studies using actual public transport mobility data from Montevideo, Uruguay, and Buenos Aires, Argentina. The experimental results confirm that the proposed multi-objective evolutionary algorithm is effective, reliably generating high-quality Pareto fronts that capture the significant trade-offs among the objectives: demand coverage, travel time, and operational cost. Compared with a local search heuristic and a single-objective evolutionary algorithm, superior convergence and diversity were obtained. The compromise solution improved up to 46.9% in the coverage-to-cost ratio compared with the local search baseline, highlighting the advantage of the multi-objective approach for balanced and cost-efficient planning decisions. The computed solutions exhibit a tendency to prioritize services in high-demand central urban areas while simultaneously offering policymakers a diverse set of feasible design alternatives.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/ffutr.2026.1797151</guid>
        <link>https://www.frontiersin.org/articles/10.3389/ffutr.2026.1797151</link>
        <title><![CDATA[Evaluating transport service quality metrics in tourism: a technological innovation-driven approach]]></title>
        <pubdate>2026-04-07T00:00:00Z</pubdate>
        <category>Brief Research Report</category>
        <author>Akhmatova Mokhigul Ergash Qizi</author><author>Qodirov Azizjon Anvarovich</author><author>Urakova Dilfuza Bakhriddinovna</author>
        <description><![CDATA[The study examines the impact of technological innovation on enhancing transport service quality in the tourism sector. Transport is a crucial element of tourism infrastructure, and its efficiency and reliability directly influence tourist satisfaction and destination competitiveness. The study highlights how digital transformation—especially via artificial intelligence (AI), Internet of Things (IoT), blockchain, and sustainable mobility technologies—has redefined operational standards, traveler expectations, and managerial decision-making in transportation companies. The empirical segment of the study examines 15 transportation firms in the Bukhara region of Uzbekistan from 2018 to 2024, evaluating the extent of innovation adoption and its correlation with visitor mobility, safety, and satisfaction. The study employs quantitative indicators and a conceptual innovation model to identify the technological, organizational, and behavioral aspects influencing the adoption of smart transport solutions. The findings indicate a robust association between innovation intensity and service quality parameters, including punctuality, safety, environmental performance, and user convenience. Organizations that implement sophisticated digital systems—such as automated ticketing, route optimization, real-time tracking, and electric transportation—attain enhanced customer satisfaction and operational efficiency. The report asserts that innovation-driven transformation of transportation services is essential for sustainable tourism development, especially in heritage places such as Bukhara. It enhances the theoretical comprehension of service quality management in tourism and provides pragmatic recommendations for policymakers and businesses aiming to incorporate smart technologies into transportation operations.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/ffutr.2026.1644979</guid>
        <link>https://www.frontiersin.org/articles/10.3389/ffutr.2026.1644979</link>
        <title><![CDATA[Deep heterogeneity learning for cross-city transit forecasting: a differentially private federated framework with mixture-of-experts and seasonal decomposition]]></title>
        <pubdate>2026-03-27T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Aivar Sakhipov</author><author>Zhanbai Uzdenbayev</author><author>Diar Begisbayev</author><author>Aruzhan Mektepbayeva</author><author>Ramazan Seiitbek</author><author>Didar Yedilkhan</author>
        <description><![CDATA[IntroductionAccurate prediction of transit flows is fundamental to optimizing intelligent transportation systems; however, centralized forecasting is frequently obstructed by heterogeneous, Non-Independent and Identically Distributed (Non-IID) cross-city data and stringent data privacy regulations.MethodsWe propose X-FedFormer, a novel framework integrating Federated Learning (FL) with Differential Privacy (DP) and a deep learning architecture combining a Mixture-of-Experts (MoE) mechanism with a Seasonal-Trend Decomposition module. The framework is evaluated on a statistically validated synthetic dataset faithfully simulating realistic inflow and outflow patterns across ten diverse urban environments (90 days of hourly records, 30 routes per city, 64,800 observations per city).ResultsX-FedFormer significantly outperforms state-of-the-art federated baselines including FedProx, achieving an aggregate coefficient of determination of 0.922 and a mean absolute error (MAE) of 7.93 passengers across all participating cities. A Wilcoxon signed-rank test confirms statistical significance over the strongest baseline (p = 0.018). Ablation studies confirm that the MoE and seasonal decomposition modules reduce forecasting error by approximately 11% and 16%, respectively, compared to standard architectures.DiscussionThe model maintains high predictive utility even under strict differential privacy guarantees (ε ≈ 2), establishing a viable privacy-utility operating point for practical deployment. These findings present a scalable, robust solution for urban computing that effectively balances algorithmic performance with data sovereignty in smart city applications.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/ffutr.2026.1759314</guid>
        <link>https://www.frontiersin.org/articles/10.3389/ffutr.2026.1759314</link>
        <title><![CDATA[Review of indicators and multi-criteria decision-making methods for assessing the sustainability of urban mobility]]></title>
        <pubdate>2026-03-09T00:00:00Z</pubdate>
        <category>Review</category>
        <author>Yamila S. Grassi</author><author>Mónica F. Díaz</author><author>Daniel A. Rossit</author>
        <description><![CDATA[Assessing the sustainability of urban mobility requires clear indicators and robust decision-making tools, yet current knowledge remains fragmented and unevenly distributed across regions. This study conducts a structured literature review of 38 recent publications to identify the main indicators and multi-criteria decision-making (MCDM) methods used to evaluate sustainable urban mobility. Thirty-five representative indicators were identified, covering traditional sustainability dimensions (economic, environmental, and social) as well as emerging ones such as operational-technical and spatial-urban. Among the MCDM methods, the Analytic Hierarchy Process (AHP) is the most frequently applied for weighting indicators, while the Technique for Order Performance by Similarity to Ideal Solution (TOPSIS) is commonly used for prioritizing alternatives. The review also highlights key research challenges, including the need for indicator sets adapted to local contexts, the generation of more region-specific information for Latin America, and the development of approaches that account for data availability and local conditions. To address these gaps, a structured expert consultation was conducted in the medium-sized Latin American city of Bahía Blanca (Argentina), resulting in a set of twelve indicators considered suitable for assessing the sustainability of the local urban mobility system. Overall, the study provides an updated overview of current practices and methodological trends in sustainable urban mobility assessment.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/ffutr.2026.1765920</guid>
        <link>https://www.frontiersin.org/articles/10.3389/ffutr.2026.1765920</link>
        <title><![CDATA[Design and feasibility study of a smart speed hump for selective urban speed management: risk-informed deployment via conditional generative modelling]]></title>
        <pubdate>2026-02-11T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Ömer Kaya</author>
        <description><![CDATA[Urban speed management in developing countries frequently relies on fixed physical speed humps. While effective for compliance, these devices can reduce comfort for compliant drivers, increase structural loads on heavy vehicles, and complicate winter maintenance operations. This study develops and evaluates a selective speed-management approach centred on an adaptive speed hump concept that remains flush for compliant drivers and actuates only when speeding is likely or detected. To support deployment decisions in data-scarce settings, a conditional generative (parametric) decision-support module is used to generate synthetic speed distributions from roadway and scenario attributes based on sparse observations. Segment-level speed-violation risk is estimated and combined with additional criteria to compute a Speed-Calming Suitability Index (SSI) for site prioritization. A low-cost laboratory prototype with real-time speed detection and a servo-driven movable surface demonstrates selective actuation at a single point. The modelling workflow produces actionable risk and SSI-based prioritization for targeted traffic calming, and the prototype demonstrates the feasibility of selective actuation. Together, these components support risk-informed selection of candidate locations and practical implementation of a selective traffic-calming mechanism. The results suggest that conditional generative modelling can support sustainable mobility by enabling risk-informed deployment of adaptive traffic-calming infrastructure under data scarcity. Here, “generative” denotes distributional speed sampling for risk inference; the implementation is a lightweight parametric conditional generator (mean plus dispersion) rather than GAN/VAE/diffusion-style architectures.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/ffutr.2026.1662480</guid>
        <link>https://www.frontiersin.org/articles/10.3389/ffutr.2026.1662480</link>
        <title><![CDATA[Freeway traffic state classification using vehicle trajectory data]]></title>
        <pubdate>2026-02-09T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Rende Cheng</author><author>An Liu</author><author>Xiaofei Sun</author><author>Fangliang Liu</author><author>Na Li</author><author>Yu Wang</author><author>Lu Yang</author><author>Quan Yu</author>
        <description><![CDATA[This study proposes the FCM-RF-SMOTE framework to resolve the issue of data imbalance in real-time freeway traffic state classification. The framework integrates Fuzzy C-Means (FCM), Random Forest (RF), and the Synthetic Minority Over-sampling Technique (SMOTE). Traffic states are classified into four categories (smooth, stable, congested, and severely congested) based on quantitative thresholds derived from FCM clustering centers. The validation utilizes SUMO simulation with Gaussian noise and a 10 Hz sampling rate to approximate millimeter-wave radar characteristics. Results show that the proposed framework significantly increases the representation of the severe congestion class from 3.67% to 19.83%. Consequently, the overall classification accuracy is enhanced from 77.67% to 97.80%, demonstrating superior performance in handling imbalanced datasets compared to baseline methods. The findings demonstrate the robustness of the algorithm for traffic monitoring systems, particularly in identifying minority traffic states, with future work planned for physical sensor validation.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/ffutr.2026.1739974</guid>
        <link>https://www.frontiersin.org/articles/10.3389/ffutr.2026.1739974</link>
        <title><![CDATA[Design and experimental analysis for a high-power wireless charging system design for electric vehicles]]></title>
        <pubdate>2026-01-28T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Idowu Adetona Ayoade</author><author>Omowunmi Mary Longe</author>
        <description><![CDATA[Wireless electric vehicle (EV) charging systems enhance user convenience and are fundamental to realising autonomous and contactless mobility. Nevertheless, efficiency at high power levels remains constrained by coil misalignment, magnetic leakage, and switching losses. This study presents the design of an analytical hypothesis model formulated to relate the coupling coefficient, mutual inductance, and load conditions to achieve power transfer. The model is then simulated and experimentally validated through a 5 kW at 85 kHz inductive power transfer (IPT) system employing a series–series compensated resonant topology. The mutual inductance coupling and the efficiency (k2Q1Q2) were developed to quantify the sensitivity of power transfer to variations in air gap and misalignment, as well as the quality factor, Q1,Q2. The proposed system achieved a peak simulated efficiency of 92.5% and a measured wall-to-battery efficiency of 88.4%, with harmonic distortion below 6.5% and stable soft-switching operation across the 85–88 kHz range. The experimental prototype maintained zero-voltage switching (ZVS), precise DC-link voltage regulation (310 ± 2 V), and stable constant-current/constant-voltage (CC–CV) battery charging for a 72 V, 40 Ah lithium-ion pack. Power loss analysis indicated that coil copper losses increased from 6.2% at nominal alignment to 10.5% under a 60 mm lateral offset, while inverter and rectifier losses accounted for 4.1% and 3.0%, respectively. Efficiency decreased from 5.02 kW (92.5%) at 10 mm air gap to 3.8 kW (86.7%) at 60 mm, validating the predicted dependence on coupling coefficient and mutual inductance (M≈25μH). Magnetic field mapping confirmed emissions below the ICNIRP 27 µT limit at 10 cm, ensuring user safety. Simulation and experimental results demonstrated strong alignment, confirming effective harmonic mitigation, robust inverter modulation, and accurate CC–CV control. The system’s validated performance, analytical model, and experimental results collectively verify the design’s robustness, safety, and scalability, meeting SAE J2954 standards and offering a high-efficiency solution for next-generation residential and light-commercial EV charging applications.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/ffutr.2025.1721997</guid>
        <link>https://www.frontiersin.org/articles/10.3389/ffutr.2025.1721997</link>
        <title><![CDATA[From motorcycle taxi to private bikes: how distraction and riding behavior influence traffic incidents in greater jakarta]]></title>
        <pubdate>2026-01-07T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Maya Arlini Puspasari</author><author>Beryl Putra Sanjaya</author><author>Richard J. Hanowski</author><author>Hardianto Iridiastadi</author><author>Salsabila Annisa Arista</author><author>Hasna Hamida Nurkamila</author><author>Claresta Yasmine Putri Pribadyo</author><author>Ahmad Ghanny</author><author>Keishandra Nabila Junistya</author>
        <description><![CDATA[Urban transport research encompasses transport safety, as accident-related fatalities are a significant problem, particularly in developing countries. In Indonesia, motorcycle crashes account for over 70% of all vehicle crashes. These crashes primarily result from behavioral and performance factors associated with the drivers of other vehicles. Most studies on motorcycle riders focus mainly on riding behavior and skills. However, few have examined how distractions influence rider behavior and traffic incidents, particularly when comparing private riders with motorcycle taxi riders. This study aims to develop a model for motorcycle riders by examining the causal relationships between variables through partial least squares structural equation modeling (PLS-SEM). This study also compares differences in driving behavior among age groups, genders, and driver types (private riders and motorcycle taxi riders). The results show that distractions significantly increase both errors and incidents, while risk perception directly influences speeding behavior. Riding errors and the use of protective equipment also make significant contributions to incident occurrence. Chi-square analyses further reveal that male and older riders report more consistent use of protective gear, younger riders exhibit higher levels of speeding and distraction, and taxi riders adopt safer practices compared to private riders. Based on these findings, this study proposes targeted safety strategies that include strengthening rule enforcement, implementing technological systems, conducting regular infrastructure inspections, and promoting public safety campaigns to enhance rider safety.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/ffutr.2025.1735788</guid>
        <link>https://www.frontiersin.org/articles/10.3389/ffutr.2025.1735788</link>
        <title><![CDATA[Times of ships in container ports: automatic identification system data for analyzing traffic conditions at a maritime terminal]]></title>
        <pubdate>2026-01-05T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Orlando Marco Belcore</author><author>Antonio Polimeni</author>
        <description><![CDATA[Maritime shipping is the primary means connecting countries and global economies, with ports serving as critical logistics hubs in the supply chain. In recent decades, international conflicts and economic disruptions have increasingly stressed maritime transport, highlighting the need to focus more on terminal performance. This paper presents a methodology to evaluate port traffic conditions using data from open Automatic Identification System (AIS) repositories. A rule-based approach is applied to segment the vessel trajectories into underway, anchoring, and berth operations, allowing the assessment of all stages that characterize a port call and the calculation of the vessel turnaround time. The methodology is demonstrated in the Port of Los Angeles, the busiest container hub on the United States West Coast. Historical AIS data are analyzed to obtain traffic conditions, and a set of key performance indicators is computed to quantify terminal operations and docks utilization during the observation period. The proposed framework provides a scalable tool for maritime traffic monitoring and decision support in port management.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/ffutr.2025.1690626</guid>
        <link>https://www.frontiersin.org/articles/10.3389/ffutr.2025.1690626</link>
        <title><![CDATA[Assessment of urban rail train drivers’ emergency handling capability based on a physio-psycho-machine-environment-management multidimensional framework]]></title>
        <pubdate>2026-01-05T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Jingwen Yang</author><author>Jing He</author><author>Wei Liu</author><author>Xiaowei Huang</author><author>Pan Li</author>
        <description><![CDATA[This study addresses two major limitations in the current evaluation system for urban rail train drivers’ emergency handling capability: the lack of clearly defined criteria, and an overemphasis on technical skills to the neglect of psychological factors. We innovatively construct a multidimensional evaluation framework based on the Physio-Psycho-Machine-Environment-Management (PPMEM) model. Through a systematic analysis of the core components of emergency response capability and its influencing factors, a mechanism model rooted in “Human-Machine-Environment-Management” theory is established. Empirically, 30 key influencing factors were identified and categorized into seven dimensions: cognitive, physiological, skill-based, psychological, equipment, environmental, and managerial. A mixed-methods approach was adopted. During the qualitative phase, a system of influencing factors was determined through field studies and in-depth expert interviews. In the quantitative phase, a questionnaire survey was administered to employees of Kunming Rail Transit Operations Co., Ltd. (N = 538 valid responses), and a multidimensional evaluation model was developed using structural equation modeling (SEM) with Amos 26 Graphics. The results indicate that the total effects of latent variables on emergency handling capability, in descending order, are: psychological factors (β = 0.214) > physiological factors (β = 0.212) > environmental factors (β = 0.205) > equipment status (β = 0.126) > cognitive factors (β = 0.105) = skill-based factors (β = 0.105) > managerial factors (β = 0.102). Notably, psychological, physiological, and environmental factors all exhibited effect sizes exceeding the significant threshold of 0.2, constituting a core group of determinants for emergency response performance. Therefore, metro operators should prioritize improvements in drivers’ workload management, mental health support, and environmental adaptability, supplemented by targeted skill and cognitive training, as well as policy refinement. These measures will contribute to a systematic enhancement of emergency response capabilities. The findings provide both a theoretical foundation and practical guidance for strengthening emergency management systems in urban rail transit.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/ffutr.2025.1677442</guid>
        <link>https://www.frontiersin.org/articles/10.3389/ffutr.2025.1677442</link>
        <title><![CDATA[A vision-based drowsiness detection system for railway operators using lightweight convolutional neural networks]]></title>
        <pubdate>2025-11-11T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Guisella Stefany Lozano-Reyes</author><author>Carlos Andrés Mugruza-Vassallo</author>
        <description><![CDATA[This research addresses the challenge of monitoring railway driver drowsiness using a real-time, vision-based system powered by convolutional neural networks, specifically the YOLOv8 architecture including attention mechanisms. The core idea is to keep the eye on subtle facial features like eyelid closure durations as indicators of fatigue. The model is designed to be lightweight for fast processing, which is critical for real-time applications. To build the model, a custom dataset of 6,991 frames was compiled. It also boosted the dataset’s diversity using data augmentation, improving the model’s robustness against real-world variability. And it paid off: the system hit an overall accuracy of 96.8%, precision of 97.28%, and recall of 97.46%, which is impressive, especially under different lighting conditions. The system works best in low sunlight. When strong solar glare kicks in, detection dips, showcasing the impact environmental factors can have on vision-based systems. In short, this study highlights how deep learning can realistically enhance railway safety by alerting operators before drowsiness leads to incidents. For future work, the plan was to toughen up the system to handle tough lighting better and explore combining vision with other sensor types (e.g., electroencephalography) for a fuller fatigue picture. Discussion about particular cognitive brain computer interface and health issues as anemia for further studies.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/ffutr.2025.1720356</guid>
        <link>https://www.frontiersin.org/articles/10.3389/ffutr.2025.1720356</link>
        <title><![CDATA[Freight and logistics grand challenges]]></title>
        <pubdate>2025-10-27T00:00:00Z</pubdate>
        <category>Specialty Grand Challenge</category>
        <author>Russell George Thompson</author>
        <description></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/ffutr.2025.1671246</guid>
        <link>https://www.frontiersin.org/articles/10.3389/ffutr.2025.1671246</link>
        <title><![CDATA[Simulation study on optimization of delivery path for community group buying]]></title>
        <pubdate>2025-10-08T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Minyan Yu</author><author>Laigen Luo</author><author>Xuejun Cheng</author>
        <description><![CDATA[This paper addresses the optimization of community group-buying distribution paths by considering both cost efficiency and time constraints. Focusing on dense neighbourhoods where such services thrive, the study highlights how current distribution strategies often prioritize proximity over effectiveness. To minimize total costs—including vehicle fixed costs, fuel expenses, and time-constrained penalties—a mathematical model is developed and solved using an improved genetic algorithm. The model incorporates real-world constraints from community group-buying platforms. Simulation in AnyLogic, using actual order data from the Flowers and Fruits platform, demonstrates that the proposed approach reduces distribution costs by 31.62%, achieving the lowest-cost distribution path while meeting time window requirements. The results validate the model’s effectiveness in balancing economic and operational efficiency.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/ffutr.2025.1671565</guid>
        <link>https://www.frontiersin.org/articles/10.3389/ffutr.2025.1671565</link>
        <title><![CDATA[Why drivers refuse to yield: power of neutralization over deterrence in Chinese urban cross-walks]]></title>
        <pubdate>2025-10-07T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Chen Yin</author><author>Naikan Ding</author><author>Jinrui Zhang</author><author>Zufeng Shao</author><author>Chenggang Tang</author>
        <description><![CDATA[Drivers’ yielding behavior toward pedestrians is a key determinant of urban road safety. Although deterrence-based interventions such as fines and penalties are widely employed, little is known about the psychological rationalizations drivers use to justify non-compliance. To address this gap, this study integrates neutralization theory and deterrence theory to examine the determinants of yielding intentions. A structural equation model (SEM) was constructed using survey data from 400 licensed drivers in Wuhan, China, to evaluate the dual effects of neutralization techniques and deterrence mechanisms. The results show that three neutralization strategies—denial of injury, denial of victim, and defense of necessity—significantly undermine yielding intentions, while deterrence mechanisms such as formal sanctions and shame exert positive but comparatively weaker influences. Among these factors, denial of victim emerges as the strongest deterrent to yielding, and license-related penalties are perceived as more severe than monetary fines. Overall, the findings demonstrate that the negative impact of neutralization substantially outweighs the positive effect of deterrence, highlighting the limitations of overreliance on punitive measures and underscoring the importance of addressing drivers’ moral disengagement to enhance pedestrian safety.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/ffutr.2025.1627368</guid>
        <link>https://www.frontiersin.org/articles/10.3389/ffutr.2025.1627368</link>
        <title><![CDATA[Dissociation of subjective and objective measures of trust in vehicle automation: a driving simulator study]]></title>
        <pubdate>2025-10-02T00:00:00Z</pubdate>
        <category>Perspective</category>
        <author>Samuel Petkac</author><author>Tetsuya Sato</author><author>Kun Xie</author><author>Yusuke Yamani</author>
        <description><![CDATA[Trust is a crucial factor that influences human-automation interaction in surface transportation. Previous research indicates that participants tend to display higher levels of subjective trust toward lower-level automated systems compared to high-level automated systems. However, administering subjective trust measures via questionnaires can interfere with primary task performance, limiting researchers’ ability to measure trust continuously in a real-world manner. The current study investigated whether objective and subjective measures of trust exhibit similar patterns across different levels of automation in a simulated driving environment. Twenty-five drivers using an automated driving system (ADS) were randomly assigned to either an active (L2) or passive (L3) automated driving condition. Participants experienced eight near-miss driving scenarios with or without obstructions in a distributed driving simulator and rated their subjective trust before and after navigating the scenarios. Additionally, we coded hand positions from recorded video footage of the participants’ in-vehicle behavior. Hand placements were coded on a predefined five-point system near the time of the simulated connected vehicle technology’s collision alert. Results showed that drivers progressively lost trust in the automated system as they approached and passed the projected collision point in each scenario. Furthermore, drivers in the active condition displayed lower levels of trust than those in the passive condition. This finding contrasts with previous research suggesting that subjective trust ratings are comparable between Level 2 and Level 3 vehicle automation groups. These findings highlight a dissociation between subjective and behavioral measures of trust, suggesting that self-report methods may overlook important aspects of drivers’ trust that can be captured through behavioral measures.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/ffutr.2025.1603726</guid>
        <link>https://www.frontiersin.org/articles/10.3389/ffutr.2025.1603726</link>
        <title><![CDATA[Adaptive vehicle routing for humanitarian aid in conflict-affected regions: a practitioner-informed deep reinforcement learning approach]]></title>
        <pubdate>2025-09-24T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Khaled Mili</author><author>Majdi Argoubi</author>
        <description><![CDATA[Humanitarian aid delivery in conflict-affected regions faces significant challenges due to dynamic security risks, uncertain demand, and complex operational constraints. Traditional optimization methods struggle with computational intractability and lack adaptability for real-time decision-making in volatile environments. To address these limitations, we propose a novel hybrid framework that integrates Deep Reinforcement Learning (DRL) with Graph Neural Networks (GNNs) and deterministic constraint validation, informed by practitioner insights to ensure real-world applicability. Our approach employs Proximal Policy Optimization (PPO) enhanced by GNN-based spatial representations to learn adaptive, efficient vehicle routing policies under uncertainty. A post-decision validation mechanism enforces feasibility by penalizing constraint violations based on a deterministic equivalent model. We evaluate our method on realistic, georeferenced datasets reflecting Afghan road networks and conflict data, comparing it against classical PPO and heuristic baselines. Results demonstrate that PPO-GNN significantly reduces operational costs (by 7.9%), security risk exposure (by 15.2%), and unmet demand, while improving reliability and adherence to constraints. The approach scales effectively across network sizes and maintains robustness under stochastic variations in demand and security conditions. Our framework balances computational efficiency with practical relevance, aligning with humanitarian priorities and offering a promising decision-support tool for aid logistics in conflict zones.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/ffutr.2025.1601538</guid>
        <link>https://www.frontiersin.org/articles/10.3389/ffutr.2025.1601538</link>
        <title><![CDATA[Research on text information recognition and mining methods for fault records of traction power supply equipment]]></title>
        <pubdate>2025-09-22T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Like Pan</author><author>Tong Xing</author><author>Haibo Zhang</author><author>Yingxin Zhao</author><author>Yuan Yuan</author><author>Wenrui Dai</author><author>Zhanhao Dong</author>
        <description><![CDATA[The fault records of traction power supply equipment contain rich historical fault processing experience, which is of great significance to the fault handling of traction power supply equipment. However, the fault records of TPSE are unstructured text data, and manual processing of them is time-consuming, labor-intensive, and inefficient. Therefore, the fault records have long been left idle in data systems, lacking exploration and application. In view of this situation, this paper proposes an entity information recognition method for fault records based on the BERT-BiLSTM-CRF algorithm, achieving automated and efficient mining of fault record information. Subsequently, based on the recognized entity information from fault records, a knowledge graph for traction power supply equipment fault handling is constructed. Finally, the retrieval capability of the knowledge graph is improved through an entity similarity-based fast retrieval algorithm, and a decision-making method for fault handling in traction power supply equipment is proposed. This method can quickly associate and recommend similar historical fault handling cases for current equipment faults, thus facilitating knowledge sharing and assisting in enhancing the efficiency and intelligence level of fault handling for maintenance operators.]]></description>
      </item>
      </channel>
    </rss>