This paper investigates the application of artificial neural networks for predicting road traffic accident counts in Poland and Kosovo. The study uses annual accident data collected for the period 2010–2023 from official statistical records provided by the Polish Police and the Kosovo Police. Forecasting procedures were carried out with multilayer perceptron (MLP) models developed in the Statistica environment. To assess the robustness of the models, two alternative dataset division schemes were employed, namely, 70%–15%–15% and 80%–10%–10% for the training, testing, and validation subsets. Forecast accuracy was measured using Mean Absolute Error (MAE) together with Mean Absolute Percentage Error (MAPE). The obtained forecasts suggest that the number of road traffic accidents in both analysed countries is likely to remain relatively stable over the 2024–2030 period. The analysis further demonstrates that a larger share of training observations contributes to improved predictive performance and lower estimation errors. Nevertheless, the relatively short time series constitutes a methodological limitation and requires careful interpretation of the forecasting results.
In view of the shortcomings of large dead-weight and limited spanning capacity for traditional composite girders and the fatigue failure and pavement deteriorations for steel girders, composite girders with lightweight composite deck emerged as good alternatives. Thus, trial design schemes of long-span cable-stayed bridges with steel-NC (normal concrete) and steel-UHPC (ultra-high performance concrete) composite decks were proposed under different span conditions. The static performance and technical feasibility of the designed bridges and the influence of structural parameters of main girder on different static effects were analysed, based on which, the determinative static effects and their variation with span length were investigated. The results show that the designed NC-slab schemes with main spans no more than 900 m can meet the requirements of static strength, stiffness and stability, while the 1000 m NC-slab scheme cannot meet the compressive strength requirements of the concrete slab. The UHPC-slab schemes meet the static requirements even when the main span reaches 1100 m, and the most unfavourable static effect turns to be the maximum compressive stress of steel girders. The main structural parameters of the main girder that most affect the unfavourable static effects include the main girder height and the thickness of the lower flange steel plate. Using UHPC-slab instead of NC-slab improves the spanning capacity of cable-stayed bridges by approximately 25%, close to the reduction rate of the dead-weight of main girder.
A localized landslide that occurred on a specific section of the road to the Uluyazı Campus of Çankırı Karatekin University seriously threatened road safety and disrupted transportation continuity. In this study, the ground conditions of the landslide area were examined in detail. Soil parameters were determined through field observations, drilling, Standard Penetration Test (SPT) data, laboratory experiments, liquefaction potential, bearing capacity, and consolidation behaviour were analysed. The analyses showed that the soil was safe in terms of liquefaction and that the bearing capacity was at a level suitable for road construction and use. However, consolidation settlements and dissolutions in gypsum levels were identified as critical factors that could trigger landslides. To prevent landslides and ensure road safety, double rows of bored piles with a diameter of ∅120 cm, a length of 35 m, and spaced at 1.4 m intervals were connected with a cap beam. This engineering measure cut the landslide surface, limited road deformations, and ensured transportation safety. The study demonstrated the effectiveness of bored pile applications in formations where soil-water interaction was significant and offered an applicable solution for critical areas in highway engineering.
This study investigates how traffic heterogeneity affects both traffic-flow efficiency and bridge structural demand using one year of road-based Weigh-in-Motion (WIM) data collected on a 60 m two-span simply supported prestressed-concrete girder bridge in Nanjing, China. The objective was to develop an integrated framework for quantifying the joint influence of vehicle composition on traffic performance and bridge load effects, and to evaluate whether operational mitigation measures can improve both mobility and structural performance. The methodology combined data preprocessing, vehicle classification, macroscopic traffic-flow modelling, statistical analysis, influence-line-based structural load-effect estimation, machine-learning prediction, and simulation-based intervention evaluation. Traffic-flow relationships were analysed using the Greenshields’s, Greenberg’s, and Underwood’s models, while XGBoost and SHAP were applied to predict and interpret traffic and structural indicators derived from the processed WIM dataset. The results showed that increasing heavy-vehicle proportion reduced traffic efficiency by lowering flow and speed and increasing density, while simultaneously increasing predicted bending moment, shear force, and fatigue-related demand. Among the calibrated traffic-flow models, the Underwood’s model achieved the lowest RMSE, while the Greenshields’s model remained highly competitive and was retained because of its simpler and more interpretable formulation. The scenario analysis further indicated that both lane management and speed harmonization reduced structural demand relative to the baseline observed traffic condition, with lane management providing the greater overall benefit. The proposed framework is intended as an analytical and scenario-based decision-support methodology for evaluating bridge traffic-management strategies under heterogeneous traffic conditions.
This study established the ratio of the base layer's elastic modulus to that of the surface layer Rm as a key variable to systematically investigate how the base layer's elastic modulus influences the mechanical response and service life of flexible pavement. A three-dimensional finite element model of a three-layer pavement system was analysed, using EverStressFE, with a constant surface layer modulus and a variable base layer modulus. The analysis included two important interfacial bonding conditions: full bonding and full slip. It also considered that the actual wheel loads are not uniform but rather follow concave and convex distribution patterns. The mechanical responses, including deflection at the top of the asphalt layer, tensile strain at the bottom of the asphalt layer epsilon xx, and vertical compressive strain at the top of the subgrade epsilon zz, were quantified to predict fatigue life (for cracking) and rutting life (for permanent deformation). The results indicated that the maximum deflection reached 0.53 mm under a full slip condition with a convex load distribution at Rm = 0.75. Critical tensile strains at the bottom of the asphalt layer were most severe under full slip with a convex load, reaching 348 & times; 10-6, while the fully bonded, concave case resulted in a much lower value of 83 & times; 10-6. Similarly, the maximum vertical compressive strain on the subgrade was 365 & times; 10-6 for the fully slipped, convex case compared to 250 & times; 10-6 for the fully bonded, concave case. A lower Rm value under full slip with a concave load distribution significantly reduced the pavement lifespan, with predicted fatigue life decreasing by over 60% and rutting life by nearly 45% compared to the fully bonded case. On the other hand, a convex load distribution greatly increased the pavement's bearing capacity by raising the critical strain thresholds and lengthening the expected service life. These findings underscore the paramount importance of interface bonding and load distribution patterns, suggesting that they can outweigh the influence of the base layer's modulus alone on pavement design.
The study investigates the factors influencing pedestrian decisions to commit temporal violations at signalized intersections, with the aim of enhancing urban road safety. To achieve this, an integrated model combining subjective components from the Theory of Planned Behaviour (TPB) and the Prototype Willingness Model (PWM) with relevant external factors was developed and validated. The findings underscore the significance of external factors-such as pedestrian red signal duration, vehicle flow, roadway length, and the presence of a median refuge island-alongside willingness and perceived behavioural control as key predictors of pedestrian behaviour. Intentions, in contrast, showed limited influence, highlighting the dominance of social-reactive pathways over reasoned decision-making in pedestrian violations. The study contributes a novel, comprehensive framework for understanding pedestrian behaviour by integrating psychological and situational predictors, thereby providing valuable insights for the design of safer urban intersections.
Accurate estimation of road maintenance and repair costs is of strategic importance for the efficient management of public resources and the safety of transportation systems. In Turkey, these costs are influenced by a wide range of multidimensional factors, including meteorological and environmental conditions, infrastructure characteristics, traffic intensity, economic indicators, and financial cost components. This study aims to comprehensively examine these factors and to develop a high-accuracy prediction model for road maintenance and repair costs. A national dataset covering a 19-year period (2004-2022) and comprising 21 independent variables identified through the literature and expert judgement was employed. Methodologically, classical statistical approaches-Multiple Linear Regression, Ridge Regression, Least Absolute Shrinkage and Selection Operator, Stepwise Akaike Information Criterion, and Granger Causality Analysis-were integrated with soft computing techniques, including Random Forest, Gradient Boosting, Support Vector Machines, Artificial Neural Networks, Genetic Algorithms, Principal Component Analysis, and Sensitivity Analysis. In total, ten variable-selection techniques were combined with five prediction models, resulting in 50 hybrid model configurations. The results indicate that the RR-ANN hybrid model, constructed using Freight KM, bitumen and salt consumption and minimum wage variables selected via RR, achieves the highest predictive accuracy (MSE = 175 474.92; RMSE = 418.90; R2 = 0.985; AdjR 2 = 0.980; MAPE = 1.36%). Computational performance analysis further shows that the trade-off between accuracy and execution time is critical in practical applications: RR-based models are the fastest, whereas ANN-based hybrids provide superior accuracy at the cost of higher computational and implementation effort. Overall, the findings demonstrate that hybrid modelling approaches yield more reliable and robust predictions than single-method specifications. The proposed framework contributes methodologically to the literature and offers policymakers a practical and standardised tool to support budget planning and the development of sustainable road maintenance strategies.
Corrugated soil-steel composite bridges due to their out-of-plane stiffness and interaction with surrounding soil are extensively used in the underground engineering. The demand for larger span of corrugated soil-steel structures is rising due to their high strength-to-cost ratio. Larger spans are usually related to the bigger cross-sections of corrugation profile. The use of the deepest corrugations like 500 mm pitch and 237 mm depth is associated with a higher risk of local buckling of straight region (tangent mt) of corrugation. This study analyses the resistance to local buckling of four widely used corrugation profiles. It also examines the impact of circular hollow section steel pipes and high strength steel influence on plate width-to-thickness ratio limit. The numerical three-dimensional model was developed for the investigation. At first, parametric study was conducted to reveal the influence mechanisms on critical parameters, incorporating finite element mesh size, number of corrugations, plate height, and plate thickness. Afterwards, local buckling behaviour of corrugated steel plate was studied and width-to-thickness ratio limit was proposed considering that local buckling of the plate would not occur before steel yielding. It was found that corrugated plate thickness could be significantly reduced as a result of the reduction of buckling length by steel pipes. Therefore, innovative corrugation profile has the great potential to be rational more than the increase of the thickness of the regular corrugated steel plate.
This article presents a study aimed at integrating two road safety approaches to effectively prioritise road sections requiring safety improvements. The study examines the role of injury severity assessment in evaluating the safety of road networks. It outlines the fundamental principles of the MAIS3+ methodology, discusses its relevance to road-safety analysis, and highlights its potential applications for assessing road infrastructure risk. A pilot safety assessment of the Lithuanian main road network is presented, based on the severity of traffic accident outcomes classified according to the MAIS3+ criterion. Furthermore, the study addresses the challenges of linking hospital and police data and provides recommendations to improve data integration.
This study investigates the stability of skeleton-reinforced concrete arch bridges during the concrete encasement process, employing a homogeneous generalized yield functions for extreme buckling load determination in nonlinear finite element analysis. Through an analysis of the stability of a stiff skeleton arch bridge with a 600 m span during the concrete wrapping stage, this study delves into and elucidates the mechanism by which the transverse brace enhances the out-of-plane stability capacity of the skeleton arch ribs. Additionally, a method for improving stability by controlling the lateral rotation angle of arch ribs is proposed. The results indicate that the lateral deflection angle of arch ribs serves as a crucial metric for assessing the out-of-plane stability of arch bridges. Transverse braces effectively coordinate and constrain the lateral deflections of two isolated arch ribs through their bending stiffness along the tangential direction of the arch axis. Notably, transverse braces within the range of L/8 to 3L/8 make the most substantial contribution to the lateral stiffness of arch ribs. Consequently, wrapping surrounding concrete on transverse braces within the L/8 to 3L/8 range proves advantageous for enhancing the stability of a stiff skeleton arch bridge under construction. Specifically, it is recommended to pour surrounding concrete on transverse braces at L/4 before the closure of the bottom plate’s concrete ring. After the ring of bottom plate’s concrete is closed, a symmetrical pouring of surrounding concrete on transverse braces from L/4 to the arch spring and vault is proposed.
Variable Speed Limit (VSL) control is essential for managing highway tunnel maintenance work, as it adjusts speed limits based on road conditions to regulate traffic flow. Developing a VSL control strategy that balances traffic efficiency and safety during maintenance can be challenging. This paper addresses this issue by proposing a VSL control strategy based on Model Predictive Control (MPC) that considers the spatial characteristics of traffic flow in a tunnel maintenance work zone. The strategy aims to minimise total travel time, reduce speed variance, and maximise traffic flow through a multi-objective optimisation approach using a Non-dominated Sorting Genetic Algorithm II (NSGA-II). With the Qinling Tiantai Mountain Tunnel selected as the experimental object, a simulation section is constructed based on the SUMO model with the measured data, and a comparative experiment of different speed limit control cycles in the maintenance work zone is designed. The results show that the method of this paper can effectively reduce the total travel time under the influence of maintenance operations by more than 17.5%, reduce the standard deviation of speed by about 22.1%, and enhance the traffic volume by about 7.8%, which can effectively improve the efficiency of road access and safety level.
This study examines the challenges and potential solutions associated with the retention of stormwater from road surfaces – a critical component of urban infrastructure in the face of climate change. The research highlights that intensified urbanisation and the increasing prevalence of extreme weather events have exacerbated issues related to rapid rainwater runoff, leading to urban flooding and infrastructural degradation. Employing quantitative empirical methods, a survey was conducted among 362 road infrastructure managers in Poland, assessing the technical condition of roads, drainage system performance, and the barriers to adopting modern retention and infiltration solutions. Findings reveal a mixed perception of current drainage performance, with many respondents reporting inadequate solutions that compromise both safety and sustainability. Key barriers include high implementation costs, technical and infrastructural challenges, resistance to change, and limited public awareness. The results underscore the necessity for modern, integrated stormwater management practices that not only protect infrastructure but also enhance urban water balance and sustainability.
This study investigates the temporal dynamics and predictive modelling of fatal traffic accidents in Hatay province, Türkiye, using both classical time series approaches (ARIMA, SARIMA, Holt–Winters) and machine learning techniques (Random Forest, Gradient Boosting). Monthly accident data from 2017–2021 were analysed through seasonal decomposition, stationarity testing, and comparative model evaluation. Results revealed a distinct seasonal pattern, with accident counts peaking during summer months and declining in winter, and a long-term trend showing a notable reduction in fatalities after 2017. Among the tested models, the Enhanced Gradient Boosting approach demonstrated the highest predictive accuracy (R² = 0.97, RMSE = 1.59), outperforming both classical time series and other ensemble methods. Forecast results for 2021 indicated seasonal peaks in June and August, corresponding to increased traffic density during the holiday period. The COVID-19 pandemic was associated with a marked short-term reduction in fatalities, though the effect appeared to diminish post-lockdown. These findings highlight the value of integrating advanced ensemble learning methods into traffic safety forecasting and underscore the importance of seasonally targeted interventions.
Road safety continues to be a major international concern, with approximately 1.19 million fatalities and up to 50 million injuries occurring annually. In response, the European Union and the United Nations have launched ambitious strategies like “Vision Zero” and the Decade of Action for Road Safety (2021–2030), aiming to drastically reduce or eliminate traffic-related deaths. Countries such as Poland have shown measurable progress, achieving a 35% reduction in fatalities and a 29% decline in total accidents since 2019. As human error remains the dominant cause of traffic accidents, autonomous vehicles (AVs) are being considered a transformative solution. AVs are expected to eliminate typical driver mistakes such as distraction, fatigue, and impaired judgment. However, their deployment requires substantial investment in digital infrastructure, such as V2X and C-V2X communication, HD maps, and 5G networks. This study estimates and compares the annual cost of road accidents caused by human error (EUR 11.13 billion) with the infrastructure investments needed to support AVs in Poland. Based on population density modelling, the number of intersections was estimated at 1.9 million, leading to a V2X deployment cost of EUR 140.1 billion. Adding HD mapping (EUR 1.84 billion) and 5G rollout (EUR 2 billion), the total estimated investment is approximately EUR 143.94 billion. Assuming AVs fully eliminate human error, the investment could be recouped in about 13 years through accident cost savings. While based on simplified assumptions, this initial analysis highlights the potential long-term value of AV implementation in achieving road safety objectives and reducing economic losses from traffic incidents.
Research on the microscopic mechanisms of open-graded friction courses (OGFCs) is still in its early stages, and the specific effects of various factors on the fatigue performance of OGFCs have not been fully explored. This study investigates the effects of oil-stone ratios, void fractions, and maximum nominal particle sizes on the fatigue life of OGFCs at the macroscopic and microscopic scales. At the macroscopic level, indirect tensile fatigue tests were conducted on OGFC specimens. At the microscopic level, a three-dimensional (3D) reconstruction model of OGFC was developed using computed tomography (CT) and image processing techniques. Additionally, a 3D randomized aggregate model was developed using the Monte Carlo method and an aggregate random placement algorithm. Virtual splitting and fatigue tests were conducted to analyse the correlation between virtual and experimental macroscopic tests. The results showed that the splitting strength and fatigue life of the OGFC increased at higher oil-stone ratios but decreased at higher void fractions and larger nominal maximum particle sizes. The variation in the results of the virtual splitting fatigue tests derived from the CT reconstruction model and the experimental results was only 9–11%, indicating a strong correlation between the two approaches.
Micromobility is gaining momentum in many countries, helping reduce congestion and pollution in the streets of major cities. The use of e-scooters has increased rapidly over the past three years, posing additional risks to road safety. Therefore, it is necessary to identify the key factors influencing the number of accidents and their consequences. The current article assesses eight e-scooter safety importance criteria, applying various methods and consulting highly qualified experts. It is noteworthy that the maximum weights of criteria determined by the ARTIW-L, ARTIW-N (Average Rank Transformation into Weight Linear and Non-Linear), and AHP (Analytic Hierarchy Process) methods are consistent. Evaluating the opinions of 15 experts using the ARTIW-L, ARTIW-N, DPW (Direct Percentage Weight), and AHP methods allowed for the determination of average criterion weights and the ranking of their priorities. Averaging the criteria weights calculated by the four expert evaluation methods yields the following overall priority order: Type and quality of road surface≻Road or street element≻Maximum power≻Speed limits≻Mandatory helmet use≻Seasonality≻Age of the road user≻Educational activities. The findings highlight that the type and quality of the road surface, as well as road or street design, have the greatest impact on e-scooter safety. These insights can guide urban planners and policymakers in prioritizing infrastructure improvements and developing evidence-based safety regulations for micromobility users.
This study investigates the seasonal structural behaviour of flexible pavement structures constructed on subgrades with varying types of treatment. Eight road sections in Lithuania, featuring natural subgrades or soils stabilised with lime, cement, or hydraulic road binder (HRB), were evaluated using Falling Weight Deflectometer (FWD) testing during thawed and recovered states. Structural condition was assessed using deflection-based indices: the Surface Curvature Index (SCI), Base Damage Index (BDI), and Base Curvature Index (BCI). Seasonal changes were quantified, and Wilcoxon signed-rank tests were applied to assess the statistical significance of deflection differences. The results revealed that the untreated subgrades experienced the largest seasonal softening, with BCI increases of up to 45%. Cement stabilization provided the most effective mitigation, limiting the BCI to 14% and preserving the stability of SCI. Lime-treated sections showed a dosage-dependent improvement, while HRB treatment yielded results comparable to high-percentage lime stabilisation. The study confirms that the type and dosage of subgrade treatment significantly influence pavement resistance under freeze-thaw conditions and highlights the importance of evaluating the geometry of the deflection bowl to correctly interpret structural indicators. These findings contribute to improved mechanistic understanding of seasonal load response in flexible pavements and inform best practices for subgrade stabilisation.
Pavement must have the characteristics that allow safe, fast, comfortable, economical and reliable vehicle traffic. The normative documents introduce limit values and permissible deviations of the controlled parameters of the road pavement, for which penalty deductions are levied if they are not satisfied or exceeded. The asphalt pavement installation rules for the ĮT ASFALTAS 08 contain 10 such indicators, whose relevance in respect of road quality is investigated in this paper. The relative weights of each indicator (defect) have been determined using assessments from 91 experts. The methods used in the study are rank correlation, ARTIW-L, ARTIW-N (Average Rank Transformation into Weight Linear and Non-linear), and DPW (Direct Percentage Weight). The expert team’s opinions are consistent because the empirical concordance coefficient value of 0.715 is 34.6 times higher than the minimum concordance coefficient value of 0.021. The most important indicators for the experts are the lower degree of compaction, the lower thickness of the layer, and the lower amount of binder. A pilot project dedicated to determining the required number of experts has shown that the number of experts in a team, exceeding 20, has almost no effect on the average of ranks and percentage weights of the criteria.
Road infrastructure is critical to the economic, social, and environmental sustainability of modern societies. This study compares classical methods (Multiple Linear Regression, Ridge, and LASSO) with soft computing techniques (Artificial Neural Networks, Fuzzy Logic, Random Forests, Gradient Boosting, Support Vector Machines, and Genetic Algorithms) for predicting road maintenance and repair costs. A comprehensive search has been conducted in Web of Science, and Scopus for studies published between January 2010 and March 2024. Boolean operators and specific key terms such as “road maintenance costs,” “soft computing,” and “classical prediction methods” have been used. The approach has been PRISMA-inspired but adapted for narrative review purposes; hence, no formal quality assessment or meta-analysis has been performed. Peer-reviewed journal articles have been included, while grey literature has been excluded to ensure methodological consistency. While classical methods offer simplicity and computational efficiency, they often fall short in addressing complex data structures such as non-linear relationships and multicollinearity. Conversely, soft computing techniques excel in modelling non-linear systems and managing uncertainties. Hybrid models combining classical and soft computing approaches enhance prediction accuracy by 20–30%, providing improved capabilities in modelling environmental factors. However, further research is required to evaluate their long-term performance and adaptability to diverse geographical conditions. This study highlights the theoretical advantages of hybrid models while offering practical solutions for sustainable infrastructure management. The findings provide policymakers and engineers with actionable insights, promoting efficient public resource use and sustainable development goals. Future research should focus on integrating IoT and big data analytics to address dynamic environmental variables, fostering innovation in infrastructure management.
The analysed research question raises the problem of modernisation of technical specifications of the locomotive on electric traction. The authors of the scientific research consider the modernisation of the DS3 locomotive with the transition from a single-phase (25 kV 50 Hz AC) to a two-phase (25 kV 50 Hz AC/3 kV DC) power supply system, which aims to increase interoperability with neighbouring railway networks. A multi-level literature review has been carried out, transient and dynamic characteristics have been modelled in MATLAB, and the principles of control of traction converters and motors have been formulated. Ensuring stable operating modes when switching power systems is confirmed by optimal attenuation ζ ≈ 0.7, and the electromagnetic compatibility analysis has revealed characteristic interference of 500–3000 Hz, thus allowing us to propose filters in accordance with EN 50121. The radar graph of the comparative analysis provides an improvement in the main metrics (power, traction efforts, efficiency, and reaction time) in the context of an ideal 100% scale. A step-by-step roadmap for the functional compatibility of ERTMS / ETCS and GSM-R in the Siemens SIBAS 32 platform has been designed and technical conditions for certification according to TSI and EN standards have been formed. The modernisation of DS3 is recognised as technically feasible, cost-effective and compliant with international technical aspects, which ensures prospects for joint operation in Ukraine and the EU.
