Engineering

Abstract: Activity-travel patterns provide a behavioral description of daily mobility and support travel-demand forecasting, dynamic origin-destination estimation, and activity-based simulation. With the growth of passively collected mobility data, large-scale reconstruction has become increasingly feasible. However, these data are often incomplete and lack activity semantics, making it difficult to directly obtain complete activity-travel chains from raw observations. This paper reviews activity-travel pattern reconstruction from the perspectives of data collection and mathematical modeling. It first defines the reconstruction task by linking partial mobility observations with latent activity-travel chains. It then discusses major mobility data sources and explains how different observation mechanisms affect model design. Existing methods are grouped into model-driven, data-driven, and hybrid approaches, and their assumptions, advantages, and limitations are compared. Evaluation methods are further summarized at the element, chain, and population levels. The review suggests that future studies should focus on complete-chain inference, uncertainty representation, model transferability, and standard benchmarks. This survey provides an integrated framework for understanding and advancing activity-travel pattern reconstruction.

Abstract: The ability to pass slower vehicles on rural two-lane highways is important for breaking up platoons and improving the quality of service. However, as passing takes place in the lane of opposing traffic, there is an increased level of risk associated with passing maneuvers on two-lane highways. In practice, passing sight distance (PSD) is used in design and lane marking purposes to allow or prohibit passing maneuvers on different sections of two-lane highways. This study performed a thorough review of the PSD practice in the United States (US) considering the well-established PSD concepts and principles. The review examined the historical evolution of PSD criteria in the US leading to the current PSD guidelines used in practice while highlighting the theories, rationale, and underlying assumptions used for PSD models. The review results highlighted a few limitations in the current practice that are believed to have important safety implications and raise concerns about the adequacy of sight distance for passing maneuvers. Therefore, the study stresses the need for adopting a safer approach in developing PSD criteria. Meanwhile, the study strongly recommends exceeding the current minimum PSD values using site-specific information and traffic conditions. This review is important in that the engineering standards in the US are adopted in many developing countries around the world especially when working with international engineering firms or receiving funding from international organizations.

Abstract: Advanced Air Mobility (AAM) is increasingly recognized as a promising approach for improving healthcare logistics, yet evidence remains fragmented across aviation, transportation, healthcare, and digital infrastructure. This study examined the operational, clinical, and institutional evidence to characterize the evolution of healthcare-focused AAM, identify dominant research themes, and determine critical knowledge gaps. The review followed PRISMA-ScR guidelines and combined bibliometric analysis, thematic synthesis, and semantic network analysis of 168 peer-reviewed studies published between 2015 and 2025 and retrieved from IEEE Xplore, ScienceDirect, Scopus, and Web of Science. The analysis identified six thematic clusters encompassing system design, healthcare logistics, biological specimen transport, emergency response, health equity, and digital infrastructure. Publication activity increased rapidly after 2020, emergency response represented the most mature research domain, and pharmaceutical logistics, longitudinal operational validation, and health equity remained comparatively underdeveloped. These findings demonstrate that healthcare-focused AAM functions as a sociotechnical system requiring coordinated advances in technology, governance, institutional integration, and equitable access to support clinically reliable and operationally sustainable healthcare delivery.

Abstract: Highway–rail grade crossing (HRGC) safety has improved substantially over recent decades through engineering upgrades, active warning systems, crossing closures, enforcement, and public education. Recent national trends, however, suggest that these gains may have slowed, raising the question of whether HRGC safety has entered a persistent plateau. This study investigates whether the historical decline in U.S. HRGC incidents has transitioned into a statistically distinct safety regime and whether the factors associated with casualty occurrence have changed following that transition. An analytical framework integrating regime-transition analysis, cross-regime casualty comparison, and explainable machine learning was applied to nationwide Federal Railroad Administration incident records from 1976 to 2025. Trend analysis, complementary stationarity diagnostics, residual diagnostics, information criteria, and sensitivity analysis consistently identified 2012 as the onset of a statistically stationary safety plateau. Comparison of casualty outcomes showed no meaningful change in either the probability of casualty occurrence or the distribution of injury and fatality outcomes following the transition. Explainable random forest models further demonstrated substantial temporal stability in the factors associated with casualty occurrence. Train speed, vehicle occupancy, driver presence, and highway-user actions remained the dominant predictors across both safety regimes, with driver presence ranking among the most influential characteristics during the plateau period. These findings indicate that the current safety challenge is not the emergence of new collision mechanisms but the persistence of well-established operational and behavioral risk factors. Future reductions in HRGC casualties will likely require targeted engineering improvements, advanced warning technologies, connected-vehicle and vehicle-to-infrastructure systems, artificial intelligence–enabled monitoring, and focused public education to address the persistent residual risks sustaining the national safety plateau.

Abstract: Highway–rail grade crossing (HRGC) incidents in the United States declined substantially for several decades before stabilizing in recent years. Understanding this persistence is important because future safety improvements may depend on identifying locations where incident occurrence remains resistant to further reduction. This study developed an integrated framework to characterize persistent HRGC incident environments using 50 years (1976–2025) of Federal Railroad Administration incident records. Trend, structural-break, variance, and stationarity tests were first applied to determine whether the historical decline transitioned into a distinct persistence regime. A county-level persistence index (PI) was then developed to quantify the combined effects of incident burden and resistance to decline during the plateau period. Distributional analysis characterized the statistical behavior of the PI, while global and local Moran’s I statistics evaluated its spatial organization. Explainable machine-learning methods were subsequently used to identify incident characteristics associated with elevated persistence. The results identified a statistically significant regime change around 2010. Prior to 2010, incidents exhibited a strong declining trend, whereas the subsequent period displayed substantially reduced trend magnitude, lower variance, and behavior consistent with persistence around a stable level. The PI followed a strongly right-skewed distribution that was best represented by a bounded heavy-tailed unit log-logistic model, indicating that persistence is concentrated within a relatively small subset of counties. Spatial analysis revealed significant positive spatial autocorrelation (Moran’s I = 0.180, p = 0.001) and geographically coherent clusters concentrated primarily in the southeastern United States and several major freight-oriented regions. Explainable machine-learning models identified train-operating characteristics, warning-device contexts, movement patterns, and temporal conditions as key attributes associated with high-persistence counties. The findings demonstrate that the post-2010 incident plateau is sustained disproportionately by a limited number of geographically concentrated environments and provide a framework for supporting more targeted safety interventions.

Abstract: Work zones reduce roadway capacity and create unstable merging, queue spillback, and stop-and-go conditions that simultaneously degrade traffic operations and elevate crash risk. Conventional fixed-time, actuated, and adaptive signal controllers are poorly suited to these non-stationary conditions, and most reinforcement learning (RL) approaches optimize for mobility while treating safety only as a post-hoc evaluation measure. This study develops a safety-aware Deep Q-Network (DQN) framework for adaptive signal control at intersections operating near work zone activity areas. The framework embeds merge conflict risk, upstream spillback propagation, and stop-and-go instability directly into both the state representation and the reward formulation, alongside operational objectives such as delay, throughput, and speed. A merge-conflict model based on relative spacing, relative speed, and acceleration characterizes unsafe interactions in the merge region, and a Pareto-based multi-objective procedure samples reward-weight vectors to identify non-dominated policies balancing efficiency and safety. The framework was implemented and evaluated in a SUMO microscopic simulation of a signalized intersection under lane-closure conditions. The best policy increased throughput by 24.6%, 32.7%, 37.3%, and 29.7% for cars, trucks, buses, and mixed traffic relative to default timing (all p < 0.001; Cohen’s d = 0.53 - 1.29), with the largest gains for trucks and buses. Shockwave analysis showed a 39.1% reduction in maximum queue length and a 45.8% reduction in spillback distance, with faster queue dissipation. The results indicate that encoding surrogate safety indicators as learning objectives, rather than evaluation criteria, enables a single controller to jointly improve mobility and safety in work zones.

Abstract: Adherence to right-of-way (RoW) rules at uncontrolled T-intersections helps avoid accidents and alleviate congestion. In non-uniform traffic, right-turning behaviour can be characterised by distinct driving traits, such as non-compliance (failure to yield), a nonchalant attitude, and competitive behaviour. This paper presents a cost-effective computer vision framework using UAV videos to analyse right-turning behaviour and assess safety and operational performance (congestion) at uncontrolled T-intersections. A conflict cone of a vehicle is defined to automatically detect a right-of-way violation (RoWV) and yield. The impact of driving- related parameters and external traffic on non-compliant behaviour is analysed using the Tweedie generalised linear model. This paper proposes a modified surrogate safety measure, condPET, and a novel parameter, congValue, to identify critical conflicts and congestion due to non-compliant behaviour. Lateral evasive action is used to detect a constrained path because of nonchalant and competitive behaviours. Results indicate that only 7.50% of vehicles yielded, 6.25% of conflicts were critical, and congestion occurred for 44.00% of the total video time. Overall, 45.34% of vehicles created a constrained path, and 26.00% committed RoW violations, causing congestion and increasing the average travel time on major roads by 2.0 and 3.5 times, respectively.

Abstract: Bicycling is an important mode of sustainable and active transportation, but bicycle safety remains a major concern in urban areas, especially at intersections where cyclists interact with turning vehicles, crossing traffic, and complex roadway conditions. This study assesses the effect of roadway, environmental, and infrastructure-related factors on bicycle safety at intersections in Baltimore City. Crash data from 2022 to 2024 were obtained from the Maryland crash data records and analyzed for bicycle-involved crashes at intersections. The study used descriptive statistics, GIS-based spatial analysis, visualizations, and exploratory regression models, including linear regression, binary logistic regression, and multinomial logistic regression. The results showed that Baltimore City had 180 bicycle-involved crashes at intersections during the study period, most of which resulted in injury. Spatial analysis indicated that crashes were concentrated mainly in downtown Baltimore. Descriptive results showed that many crashes occurred during daylight, clear weather, and dry surface conditions, which may reflect higher bicycle activity during these periods. The Sankey diagram suggested that severe crash outcomes were more common in locations without bike lanes. However, the regression models did not identify statistically significant relationships between the selected variables and crash severity. The findings highlight the need for better bicycle exposure data, more complete infrastructure variables, and improved intersection-level safety planning in Baltimore City.

Abstract: Railway transport management has changed dramatically over the past 50 years. The advent of computer technology and the capacity for information transmission brought greater safety and the ability to remotely control interlocking devices. These enable the centralisation of railway transport management, leading to higher operational efficiency and reduced staffing costs. At the same time, this technological progress has enabled the development of additional automation functions, which we can abbreviate as ARS (Automated Route Setting). The international designation Automatic Route Setting (ARS) includes actions that enable the automation tool to execute instructions to the signal box without the intervention of operating personnel (the dispatcher). Their importance increases with line speed and the size of the remotely controlled area. Thanks to them, the dispatcher gains time because the ARS can automatically resolve some operational situations or allow the dispatcher to address them in advance, thereby distributing the workload over a wider time window. However, the interlocking system itself remains the primary safety mechanism and will prevent ARS if any element of the infrastructure is occupied. At the same time, it is not possible to automate safety-critical functions that require direct assistance from the operating personnel. In the article, the authors analysed functions in which ARS is currently widely used. In the next part, we focused on the possible expansion of the palette of these functions that could be included in the ARS regime using multi-criteria analysis. The next step was a safety-critical analysis and determination of the conditions under which they could be included in the ARS regime. The safety-critical functions are left aside. It is assumed that these will still have to be performed by the operator, not by the ARS. Detailed implementations and quantification of their impacts on the dispatcher's activities are then carried out for selected ARS functions. The last part of the article is a look into the future, because the development in the field of safe communication between the train and the infrastructure (V2I) and the transmission of valid information provides many new challenges not only in the field of ARS itself, but also in the optimisation of the entire process of managing and organising rail transport. If we can use the ARS functions today, it is only a matter of technical development to be able, for example, to guide trains to the exact time when a train route will be built for this train. This will also enable optimising the train's energy consumption and tracking capacity use. The ideal state is when the infrastructure fully communicates with the train in GoA4 mode and optimises both the train's ride and the use of the infrastructure.

Abstract: Many models exist to describe the nature of sloshing, an intricate phenomena, including the linear mechanical model and the Duffing oscillator. This paper attempts to provide an alternative model that describes the maximum slosh wave height (MSWH) of different sloshing liquids, to more accurately predict the nuanced phenomena as well as to better understand the inherent nature of sloshing. We explore three different models, the classical linear mechanical model, the non-linear Duffing model and finally the novel fractional visco-elastic model. The latter illustrates promising results after being validated via experimentation. The paper leads to the conclusion that sloshing of liquids, particularly low-viscosity fluids, is better described to have a spectrum of fractional-order visco-elastic forces at near and post resonant excitation frequencies rather than independent viscous and elastic forces as assumed by the linear and non-linear mechanical models.

Abstract: Rapid urbanization has increased the demand for intelligent traffic management systems capable of real-time monitoring and predictive analysis. Modern smart city applications require the integration of heterogeneous data sources to improve traffic efficiency and safety.However, existing approaches frequently treat vision-based perception and sensor-driven forecasting as distinct processes, limiting their ability to capture dynamic traffic interactions and large-scale spatio-temporal dependencies.To address this limitation, we propose a unified multimodal traffic intelligence framework that integrates YOLOv8-based object detection, DeepSORT-based tracking, and DCRNN-based traffic forecasting, enabling joint perception and prediction within a single system.The framework consists of three tightly coupled modules. First, a vision module performs real-time detection of vehicles and accidents from CCTV and drone data. Second, a tracking module establishes temporal consistency by associating objects across frames. Third, a DCRNN-based forecasting module models traffic flow using IoT sensor data, capturing both spatial and temporal dependencies.In addition, a multi-cluster strategy with overlapping nodes is introduced to enhance scalability while preserving spatial dependencies within large-scale traffic networks. Experimental results demonstrate strong performance across tasks. The detection model achieves up to 93.60% precision and 93.91% mAP, while the integrated accident detection framework maintains robust generalization. The DCRNN model achieves low prediction errors, particularly for short-term forecasting.

Abstract: Highway–rail grade crossing (HRGC) incidents remain a persistent safety concern due to repeated interactions between roadway users and rail operations under varying environmental and operational conditions. Existing studies rely on raw incident counts or partial exposure measures, which do not provide a consistent basis for comparing risk across locations or accounting for spatial dependence. This study developed an exposure-normalized framework to model incident intensity at the county level using accumulated incidents per crossing (AIPC). The analysis integrated statistical distribution modeling, spatial clustering, and supervised machine learning. The study combined county-level HRGC data for the contiguous United States with infrastructure, traffic, environmental, and accessibility variables. Results showed that AIPC was consistent with a gamma distribution, indicating a continuous representation of incident intensity without discrete risk regimes. Local Moran’s I identified statistically significant high-intensity clusters in specific regions, confirming spatial dependence in incident intensity. Machine learning models achieved strong predictive performance, with the extra trees model reaching AUC = 0.907 and ensemble methods outperforming linear and kernel approaches. Feature importance analysis identified temperature, train frequency, and accessibility measures as the most influential predictors, while aggregate density measures contributed the least. The results provided consistent evidence that incident intensity was associated with environmental conditions, operational exposure, and network structure. The proposed framework supports exposure-based risk assessment and enables identification of high-intensity counties for targeted intervention. This approach provides a transparent and transferable method for improving HRGC safety analysis and prioritizing resource allocation across large geographic areas.

Abstract: The rapid growth of social media has transformed digital communication while simultaneously increasing the spread of hate speech, offensive language, and abusive online behavior. Automated hate speech detection has therefore become a critical research challenge in Natural Language Processing (NLP) and Machine Learning (ML). This paper presents a machine learning framework for hate speech detection using TF-IDF and Word2Vec feature extraction techniques combined with Logistic Regression, Support Vector Machine (SVM), Random Forest, and Naïve Bayes classifiers. Experimental evaluation demonstrates that SVM achieved the highest performance with 93.4% accuracy and 92.9% F1-score. The study further discusses contextual ambiguity, sarcasm detection challenges, feature interpretability, and future integration with transformer-based architectures such as BERT and multilingual NLP models.

Abstract: Sustainable transportation systems can remain operational while becoming functionally vulnerable when access to them deteriorates. We distinguish two dimensions of transport resilience—operational resilience, the continued running of the main transport services, and functional accessibility resilience, users’ capacity to reach them—and locate weather-induced vulnerability in the latter. We focus on weather-induced last-mile vulnerability and examine how adverse weather alters mode choice. Drawing on a discrete choice experiment with 760 respondents in Portland, we estimate a mixed logit model capturing the effects of rain. The results reveal that rain significantly increases the disutility of travel time, intensifies the burden of last-mile walking, and strongly discourages bicycle use. In contrast, no statistically significant additional average disutility is found for transit itself. Marginal willingness to pay for travel time reduction increases from $1.53 per minute in sunny weather to $2.54 in rainy weather, while the average predicted probability of choosing car rises from 34.9% to 54.4%. These findings suggest that weather sensitivity is driven less by main transit services than by the surrounding access conditions and active travel links. The study contributes to transportation resilience research by showing that strengthening last-mile access under adverse weather is essential for sustaining low-carbon mobility choices.

Abstract: This study investigates how intersection-related factors affect traffic crash severity through a comparative analysis of two major U.S. cities: Chicago and New York City (NYC). Using large-scale crash datasets, the analysis applies logistic regression and machine-learning methods to assess how intersections and temporal conditions influence injury outcomes. The results indicate that intersection-related crashes significantly increase the probability of injury in both cities, though the magnitude is substantially larger in Chicago. Nighttime conditions consistently elevate crash severity across both cities. Model evaluation using ROC curves suggests moderate predictive performance, indicating the influence of additional unobserved factors. A comparative modeling framework further reveals that the relationship between intersection-related factors and crash severity is context-dependent, varying across urban environments. These findings highlight the importance of developing location-specific traffic safety strategies and demonstrate the value of integrating statistical, machine-learning, and spatial analyses in crash severity research.

Abstract: Existing unmanned aerial vehicle (UAV) urban logistics planning follows a sequential paradigm—depot siting first, routing second—that embeds a structural information loss. Straight-line distance screening systematically overestimates the feasible service radius of candidate depots, creating a blindzone of depot–demand pairs that appear reachable but prove operationally infeasible under road-network distances. We term this range-feasibility blindness and derive its analytical radius Δ=Rmax(α−1)/(2α), where α is the road-to-straight-line distance ratio. Empirical measurement across three Chinese urban districts confirms α∈[1.40,1.52] and blindzone radii exceeding 2.8 km, establishing the phenomenon as a systemic property of high-density urban road geometry. To eliminate this failure by construction, we formulate a feasibility-embedded location–routing mixed-integer linear programme (MILP) that enforces road-network range constraints simultaneously with depot-opening decisions, making blindzone configurations implicitly inadmissible. A structure-aware Adaptive Large Neighbourhood Search (ALNS) solves the model at practical scales. Benchmark experiments across all three cities show consistent cost reductions of 20.6–28.2% over sequential baselines, with gains increasing monotonically with instance scale. These results position joint optimisation as a necessary methodological shift for city-scale UAV infrastructure planning.

Abstract: Highway–rail grade crossing (HRGC) safety analysis is often based on raw incident counts or site-level models that do not control for exposure and ignore spatial dependence. This limits the ability to identify where risk is structurally concentrated across the rail network. The problem is important because misidentifying high-risk environments leads to inefficient allocation of limited safety resources and weakens corridor-level intervention strategies. This study introduces accumulated incidents per crossing (AIPX), an exposure-normalized metric that measured cumulative incident burden at the county level over a 51-year period (1975–2025). The study developed an algorithmic framework that integrates data reconciliation with spatial autocorrelation analysis, distributional modeling, and nonparametric machine learning to identify and interpret high-intensity risk environments. Global Moran’s I indicates statistically significant positive spatial autocorrelation (I = 0.359, p = 0.001), confirming that incident intensity is spatially clustered rather than random. Local indicators identify coherent high and low intensity county clusters. Distributional analysis shows that AIPX in high intensity clusters follows heavy-tailed behavior best represented by lognormal and Johnson SU distributions, indicating concentrated risk in a small subset of counties. Machine learning models achieve strong classification performance (AUC ≈ 0.85), with explainability methods consistently identifying temperature, train direction, crossing warning configuration, train composition, and track class as dominant associated features. These variables function as proxies for exposure intensity and network structure rather than causal drivers. The findings demonstrate that HRGC risk is a regional, network-driven phenomenon concentrated along freight-intensive corridors. The study provides a transparent and transferable framework that supports corridor-level prioritization of safety interventions and more effective allocation of infrastructure investments.

Abstract: Addressing the issues of insufficient adaptability and limited energy efficiency optimization capabilities in traditional tunnel lighting control methods under complex traffic conditions, this paper proposes a dynamic dimming strategy for tunnel lighting based on the Proximal Policy Optimization (PPO) algorithm.First, the tunnel lighting system is modeled as a reinforcement learning environment. A state space integrating multi-dimensional information—including traffic flow, vehicle speed, external brightness, and tunnel section location—is constructed, and a continuous action space is designed to enable precise dimming control for each functional section. Based on this, a multi-objective reward function is established that integrates brightness tracking error, energy consumption optimization, control stability, and environmental adaptability to guide the agent in learning the optimal dimming strategy.Subsequently, model training and experimental validation were conducted using actual tunnel operation data.Experimental results indicate that, compared to traditional L20 control strategies, the proposed method achieves smoother brightness regulation and higher zone control accuracy while ensuring driving safety and visual comfort, and demonstrates significant energy-saving advantages during periods of high lighting demand. In summary, the dynamic dimming strategy based on the PPO algorithm shows promising application prospects and engineering value in intelligent tunnel lighting systems.

Abstract: To address the complex spatiotemporal dependencies and dynamically evolving spatial relationships in tunnel traffic flow prediction, a macro–micro collaborative two-stage prediction method is proposed.The Grey Wolf Optimizer (GWO) is first employed to optimize the GRU model for predicting incoming traffic flow at the tunnel entrance, providing reliable macro-level input for subsequent modeling.Based on this, a spatiotemporal graph structure is constructed, and an FSE-ST-GCN model integrating an adaptive adjacency matrix with spatial and channel attention mechanisms is developed to capture dynamic spatial dependencies and enhance key feature representation.Experiments are conducted using real-world traffic flow data collected from the Shizuizi Tunnel on the Jilin–Caoshi Expressway. The results show that the proposed method outperforms baseline models in terms of MAE, RMSE, and MAPE, achieving superior prediction accuracy and stability. This work provides effective technical support for refined tunnel traffic management and lighting control.

Abstract: Student safety during daily school transportation remains a major concern, particularly in systems that rely mainly on GPS tracking and manual supervision. Existing approaches often lack proactive safety mechanisms for monitoring both student attendance and driver condition in real time. This paper presents MUTMA’INN derived from the Arabic word “مطمئن”, meaning being reassured, at peace, or tranquil, reflecting the system’s role in ensuring the safety and security of students during transportation. The proposed system is an AI-powered school bus safety framework designed to improve the security and reliability of daily student transportation in alignment with Saudi Vision 2030’s Quality of Life Program. The proposed system consists of two integrated components: a cross-platform Flutter mobile application for parents, drivers, and school administrators, and a Python-based edge system connected to Firebase for real-time synchronization. The framework automates student attendance through facial recognition at the bus gate, reducing manual effort and the risk of human error. In addition, it monitors the driver using contactless remote photoplethysmography and facial analysis techniques to estimate heart rate and detect signs of fatigue or emotional distress. When abnormal conditions are detected, immediate alerts are sent to administrators to support timely intervention. By combining mobile computing, edge intelligence, computer vision, and cloud services into a unified platform, MUTMA’INN provides a proactive approach to school transportation safety. The proposed framework demonstrates how AI can support safer and more intelligent student transit systems.