Transportation Engineering最新文献

{"title":"Metaheuristic-optimized neural networks for travel time index prediction: A comparative study of wild horse and coot optimization algorithms","authors":"Navid Khorshidi ,&nbsp;Soheil Rezashoar ,&nbsp;Pegah Amini ,&nbsp;Shahriar Afandizadeh Zargari ,&nbsp;Hamid Mirzahossein","doi":"10.1016/j.treng.2025.100395","DOIUrl":"10.1016/j.treng.2025.100395","url":null,"abstract":"<div><div>Accurate travel time prediction is essential for effective Intelligent Transportation Systems (ITSs). Unlike traditional gradient-based methods, which may get trapped in local optima, metaheuristic algorithms efficiently navigate complex optimization landscapes without needing derivative computations. This study compares two metaheuristic algorithms—Wild Horse Optimization (WHO) and Coot Optimization Algorithm (COA)—for optimizing the weights and biases of a Multilayer Perceptron (MLP) neural network to predict the Travel Time Index (TTI). The MLP uses four input variables (traffic volume, weather, crash rate, and section length), one hidden layer with 12 neurons, and one output neuron. The model was trained and tested on a dataset of 472 observations from Virginia’s transportation network (2014–2017), with input variables showing mean values of 1.19 (traffic volume), 6.92 mm (precipitation), 0.17 (crash rate), and 2.76 miles (section length), and standard deviations of 0.20, 5.21, 0.12, and 1.64, respectively. Performance was assessed using Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Correlation Coefficient (R). The WHO-optimized model outperformed COA, achieving an MSE of 0.0026, RMSE of 0.0511, and R of 0.7516, compared to COA’s MSE of 0.0028, RMSE of 0.0533, and R of 0.7262. WHO also showed better computational efficiency (147 s vs. 160 s for COA). These results highlight the WHO-MLP model’s superior accuracy and speed, making it ideal for real-time navigation systems.</div></div>","PeriodicalId":34480,"journal":{"name":"Transportation Engineering","volume":"22 ","pages":"Article 100395"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145332736","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"How does the built environment affect driver behaviours? A methodological framework for large-scale analysis that combines Onboard Diagnostic and Geographical Data to promote Road Safety","authors":"V. Nicolosi ,&nbsp;M. Mameli ,&nbsp;S. Shiralizadeh ,&nbsp;I.G. Coltea ,&nbsp;M. D’Apuzzo ,&nbsp;G. Cappelli","doi":"10.1016/j.treng.2025.100384","DOIUrl":"10.1016/j.treng.2025.100384","url":null,"abstract":"<div><h3>Background</h3><div>Driving behaviours are a set of actions made by drivers during their driving tasks and could be detected with the help of onboard sensors in vehicles. The interest from researchers in evaluating fuel consumption and enhancing overall safety has increased in recent years, thanks to the availability of algorithms and methods that can manage the large amount of data obtained from sensors.</div></div><div><h3>Method</h3><div>In this paper, both Onboard Diagnostic (OBD) data from the DDD20 dataset and open-source Geographic Data are used to study driver behaviours. After the preprocessing phases, a Multi-Layer Perceptron (MLP) classifier is used to classify driver behaviours, and a Shapley Additive Explanations (SHAP) Analysis is implemented to perform feature selection.</div></div><div><h3>Results</h3><div>Three models are created: the first combines OBD and geographical data, the second is based only on geographical data, and the last one contains a reduced subset of features retrieved from geographical data. The model with a reduced number of features shows good prediction accuracy, comparable with the full previous models. In addition to that, SHAP analysis highlights how the presence of schools, hospitals, bridges, parking, subways, cycleways, and footways increases the likelihood of having aggressive driver behaviour.</div></div><div><h3>Conclusions</h3><div>This study aims to show how the external context influences driver behaviours and to create a methodological framework for future developments in road safety. The model that uses only open-source geographical data with a reduced number of features is particularly suited for large-scale analysis in the context of road safety.</div></div>","PeriodicalId":34480,"journal":{"name":"Transportation Engineering","volume":"22 ","pages":"Article 100384"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144933717","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Leveraging artificial intelligence for predictive health assessment of Lithium-Ion batteries","authors":"Alaa Alqaryuti ,&nbsp;Karim Moawad ,&nbsp;Ahmad Mayyas","doi":"10.1016/j.treng.2025.100391","DOIUrl":"10.1016/j.treng.2025.100391","url":null,"abstract":"<div><div>Predictive maintenance has become an essential strategy for improving the reliability and safety of critical systems, particularly those dependent on lithium-ion batteries in applications such as electric vehicles, aerospace, and renewable energy storage. This study presents a data-driven framework for predicting the end-of-life (EOL) of lithium-ion batteries by analyzing both charging and discharging cycles from the NASA battery dataset. Engineered features were extracted using quartile segmentation and min–max normalization to capture key patterns in voltage, current, and temperature. Multiple classification algorithms, including XGBoost, Logistic Regression, Support Vector Classifier, K-Nearest Neighbors, and Gaussian Naïve Bayes, were evaluated based on accuracy, precision, recall, and F1-score. XGBoost demonstrated superior performance with 99% accuracy for charging and 97.3% for discharging cycles. To improve interpretability, explainable AI techniques were applied, namely feature importance and SHAP, to uncover the most influential predictors of battery degradation. The analysis revealed that the instability of the early cycle voltage was a key driver in the prediction of EOL based on charging, while the variability of the temperature was most significant during discharge. These insights support the development of transparent and reliable predictive maintenance systems for safety-critical battery applications.</div></div>","PeriodicalId":34480,"journal":{"name":"Transportation Engineering","volume":"22 ","pages":"Article 100391"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145267237","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A comparison of functional characteristics of railway rolling stock based on resilience indicators","authors":"Luca De Matteis ,&nbsp;Marilisa Botte ,&nbsp;Rosario Stefanelli ,&nbsp;Luca D’Acierno","doi":"10.1016/j.treng.2025.100411","DOIUrl":"10.1016/j.treng.2025.100411","url":null,"abstract":"<div><div>Rail systems are recognized for their sustainability and high operational performance; however, they remain highly vulnerable to disruptions. Therefore, service reliability and operational resilience result to be a critical priority for transport operators. Among the factors influencing network resilience, rolling stock procurement plays a significant role, yet its impact is often underestimated. This study emphasises the importance of incorporating resilience metrics into rolling stock acquisition decisions to enhance overall system robustness. To illustrate how this approach can be applied, Line 1 of the Naples metro system in Italy has been selected as a case study.</div></div>","PeriodicalId":34480,"journal":{"name":"Transportation Engineering","volume":"22 ","pages":"Article 100411"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145747063","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Developing strategies for improving travel time performance in multimodal public transport using ANP, PROMETHEE, network DEA, and optimization algorithms","authors":"Rahul Tanwar ,&nbsp;Sudesh Kumari","doi":"10.1016/j.treng.2025.100408","DOIUrl":"10.1016/j.treng.2025.100408","url":null,"abstract":"<div><div>This study proposes an integrated framework combining Multi-Criteria Decision Making (MCDM), Data Envelopment Analysis (DEA), and optimization algorithms to improve travel time performance in multimodal public transport systems. This novel integrated framework represents the first comprehensive combination of MCDM, DEA, and optimization techniques for multimodal transport optimization. Applied to Bhopal, India's bus, BRT, and metro systems, the framework employs ANP, PROMETHEE, Network DEA, Super-Efficiency DEA, GA, and PSO techniques. ANP analysis identified in-vehicle travel time (0.35) and transfer time (0.28) as highest priority criteria. PROMETHEE ranking placed transfer synchronization (Φ=0.352) and dedicated bus lanes (Φ=0.283) as top improvement strategies. Network DEA revealed BRT system efficiency of 0.92, compared to metro (0.85) and conventional bus (0.78). Super-Efficiency DEA confirmed BRT superiority with score 1.25. Optimization algorithms achieved significant travel time reductions: GA (28.5 minutes, 19 % improvement, R²=0.87) and PSO (27.8 minutes, 21 % improvement, R²=0.91) compared to current performance (35.2 minutes). Results demonstrate the framework's effectiveness for evidence-based multimodal transport optimization and sustainable urban mobility planning.</div></div>","PeriodicalId":34480,"journal":{"name":"Transportation Engineering","volume":"22 ","pages":"Article 100408"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145575970","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Who rides the feeder? A multi-group SEM analysis of commuters’ intention to use paratransit as a feeder to a dedicated bus lane public transportation system","authors":"Simeon Stevenson Turay ,&nbsp;Charles Anum Adams ,&nbsp;Augustus Ababio-Donkor ,&nbsp;R. Sivanandan ,&nbsp;Karthik K. Srinivasan","doi":"10.1016/j.treng.2025.100410","DOIUrl":"10.1016/j.treng.2025.100410","url":null,"abstract":"<div><div>In most Sub-Saharan African cities, promoting an integrated public transportation system often requires complementary feeder services. In Greater Freetown, Sierra Leone, proposals for the city’s first dedicated bus lane public transportation (DBLPT) system with high-quality buses are expected to transform existing service operations. A critical question is whether commuters will be willing to use paratransit services as a feeder to this new system. To explore this, the current study employs a multi-group structural equation modelling approach to investigate the factors influencing commuter intentions to adopt paratransit feeder services, thereby offering insights into service quality needs, potential behavioural shifts and system integration. The intention to use was tested for invariance across gender, age, and income groups. Data on the operations, service quality improvement, and commuters' intention to use the service were collected through a combination of onboard vehicle traffic and questionnaire surveys. Findings revealed that system accessibility and comfort positively influenced the intention to use paratransit feeder services. Gender and age differences were evident: males expressed stronger intentions to use an integrated feeder system, while females placed greater emphasis on comfort and convenience. Mid-aged adults were more sensitive to shorter commute distances, safety, intermodal connections, fare integration, and service accessibility. No significant differences were found across income groups for any of the measured attributes. Modal preference patterns indicated that minibuses were favoured by males and younger adults, whereas three-wheelers were preferred by females and mid-aged adults. These insights provide baseline evidence for planning and implementing integrated feeder services in developing cities.</div></div>","PeriodicalId":34480,"journal":{"name":"Transportation Engineering","volume":"22 ","pages":"Article 100410"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145690613","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Application of deep neural networks in detecting speed bumps and speed humps for fuel consumption optimization","authors":"Sayyedmehdi Hosseinikhah ,&nbsp;Hamid Mirzahossein ,&nbsp;Mohammad Ali Asadi ,&nbsp;Ali Naderan","doi":"10.1016/j.treng.2025.100387","DOIUrl":"10.1016/j.treng.2025.100387","url":null,"abstract":"<div><div>The rapid expansion of urbanization and growing urban populations have led to a significant increase in the number of vehicles. This trend, particularly in the absence of comprehensive transportation planning, has resulted in higher traffic congestion and, consequently, more accidents. As such, traffic calming has emerged as a key strategy for reducing vehicle speeds and enhancing urban road safety. Effective traffic calming measures—such as speed bumps and humps—require precise engineering studies and public awareness campaigns to maximize their benefits. When properly designed and implemented, these measures not only improve safety for pedestrians and drivers by controlling vehicle speeds but also mitigate potential drawbacks, including noise pollution, environmental impact, increased fuel consumption, and vehicle wear. In this study, we identified and prioritized key criteria and sub-criteria influencing the placement of speed bumps and humps in urban road networks through interviews with traffic and urban transportation experts. Using a Convolutional Neural Network (CNN), we developed a model to determine the optimal number and placement of these traffic calming devices in each street, aiming to enhance traffic safety while reducing fuel consumption. Analysis of data from 48 urban streets in Fars Province demonstrated that optimizing the quantity and location of speed bumps not only improves traffic safety but also leads to a significant reduction in fuel consumption for passing vehicles. These findings highlight how data-driven, intelligent design can simultaneously achieve both safety and environmental objectives.</div></div>","PeriodicalId":34480,"journal":{"name":"Transportation Engineering","volume":"22 ","pages":"Article 100387"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145106264","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Application of machine learning-based AI in defect monitoring of earth retaining structures and tunnels of transport systems: A review","authors":"Md Zahidul Islam ,&nbsp;Chin Jian Leo ,&nbsp;Ju Jia Zou ,&nbsp;Eileen An ,&nbsp;Samanthika Liyanapathirana ,&nbsp;Pan Hu ,&nbsp;Bo Xiao ,&nbsp;Stanley Yuen","doi":"10.1016/j.treng.2025.100385","DOIUrl":"10.1016/j.treng.2025.100385","url":null,"abstract":"<div><div>The transport system in a modern city is a complex and challenging web of roads, railways, metros, and pedestrian networks. The networks consist of various components, including transport tunnels and earth-retaining structures (ERS). Transport tunnels are passageways serving road traffic, trains, and pedestrians, while ERS are designed to support earth embankments and slopes along the road and rail networks. Inspecting these tunnels and ERS requires significant resources and planning, often using human inspectors which relies significantly on the experience and skill of trained personnel. Researchers have begun to consider employing artificial intelligence (AI) techniques to automate certain aspects of monitoring previously performed by personnel in a rapidly advancing area of interest. This article presents a rare review of machine learning-based AI (ML-b AI) techniques for defect monitoring of ERS and tunnels. It is organized based on different categories of ML-b AI defect detection techniques, including current development stages, practical impacts, and future directions, many aspects of which have not been reviewed previously. It contributes to much-needed literature on this topic and also highlights broad challenges faced by ML-b AI techniques for defect monitoring of ERS and tunnels, especially the lack of development in the detection of non-crack defects.</div></div>","PeriodicalId":34480,"journal":{"name":"Transportation Engineering","volume":"22 ","pages":"Article 100385"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145027114","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Measurement and modelling effect of street trees distress on asphalt pavements by using experimental and 3-D finite element methods","authors":"Shadi Hanandeh ,&nbsp;Frank I. ANEKE ,&nbsp;Wassel Al-Bodour ,&nbsp;Rana Imam ,&nbsp;Bara’ Al-Mistarehi","doi":"10.1016/j.treng.2025.100394","DOIUrl":"10.1016/j.treng.2025.100394","url":null,"abstract":"<div><div>This study used Artificial Neural Networks (ANN) to investigate correlations between the type and severity of distresses with a group of factors related to the trees and site conditions to identify the tree species that lead to pavement distresses and damage by using Pavement Condition Index (PCI). A Finite Element Model (FEM) was developed to represent two scenarios, with and without the trees, for both curb trees and median trees to highlight the effects attributed solely to the trees. The analysis results provide strategies and plan for tree farming along roads depend on the research results and scientific. In a finite element model that ignores tree-root effects, deformation achieves an upper limit of 0.57 mm below the outer vehicle wheel, while the internal load produces 0.43 mm of deformation, with strains in the x, y, and z directions far below failure limits. When tree-root movements are observed on a traffic-free road, deformations around the roots may reach over 25 mm, affecting a seven-fold wider area than the root zone. In Model 1, vertical displacements above the roots vary between 0.6 cm and 3 cm, indicating pavement expansion. Root pressure causes tension and compression zones to emerge, which can lead to injury. The stress and displacement characteristics in Model 2 are unbalanced due to the trees being planted in the median. Vertical displacements around the roots might reach four centimeters, suggesting serious damage. Longitudinal displacements indicate tensile cracking, suggesting a potential for additional pavement failure due to root growth. The observed types of pavement failure were longitudinal cracking and swelling. For roadside trees located at the outer edge, the failures occurred within 0 to 2 meters of the pavement edge. In the case of median trees, the pavement failures extended from 0 to 5 meters from the median. According to the field study, these failures correspond to the distress types associated with Cluster 1 and Cluster 2 species. The extent and type of modeled distresses were consistent with the on-site observations. In contrast, such distress patterns were absent in areas with Cluster 3 species (California Fan Palm, Elm, Golden Rain, Olea europaea, Pagoda Tree, and Quercus robur), where the induced strains were well below the failure threshold.</div></div>","PeriodicalId":34480,"journal":{"name":"Transportation Engineering","volume":"22 ","pages":"Article 100394"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145332484","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Capturing local vehicle behavior in city-specific typical driving cycles using machine learning: Case of Bogota, Colombia","authors":"Daniel Robayo-Rueda ,&nbsp;Miguel Angel Uribe-Laverde ,&nbsp;Cesar L. Barraza-Botet","doi":"10.1016/j.treng.2025.100399","DOIUrl":"10.1016/j.treng.2025.100399","url":null,"abstract":"<div><div>This work presents a novel methodology based on machine learning for developing city-representative typical driving cycles (TDCs) of light-duty vehicles. The methodology incudes the combination of principal component analysis to reduce dimensionality of the parameters space, k-means clustering with metaheuristics for micro-trips clusterization, and Markov chains to connect representative micro-trips into fully computed TDCs. Existing on-road datasets from the U.S. cities of El Paso, San Antonio, and Houston/Galveston were used to validate the methodology by computing three corresponding local TDCs. The computed TDCs were assessed in their representativeness of each city’s dataset and compared to standard TDCs. Representativeness assessments show that the proposed methodology is robust, and that the various metaheuristics applied do not have a significant effect on the average error between the computed TDCs and the datasets. Comparisons demonstrate that the computed city-specific TDCs present much smaller mean error values than the standard TDCs used for regulatory purposes. Finally, the validated methodology was applied to on-road test data in Bogota metro areas, producing a local ‘Bogota TDC’ with average mean errors lower than 5 % with respect to the dataset. The typical driving emissions and fuel consumption obtained from measurements on a chassis dynamometer using the Bogota TDC are also reported. Notably, the dynamometer tests with the Bogota TDC reveal ∼25 % higher fuel consumption compared to standard TDCs. These findings highlight the importance of developing representative local TDCs to better estimate vehicles’ near-Real World behavior, as well as fuel economy and emission measurements for regulatory compliance with environmental standards.</div></div>","PeriodicalId":34480,"journal":{"name":"Transportation Engineering","volume":"22 ","pages":"Article 100399"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145332735","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}