International Journal of Transportation Science and Technology最新文献

{"title":"A diffusion model-based intelligent optimization method of rural road environments","authors":"Bo Yu ,&nbsp;Zehong Zhu ,&nbsp;Yuren Chen ,&nbsp;Junhua Wang ,&nbsp;Kun Gao ,&nbsp;Xin Qian","doi":"10.1016/j.ijtst.2025.01.014","DOIUrl":"10.1016/j.ijtst.2025.01.014","url":null,"abstract":"<div><div>Well-designed rural road environments can guide drivers to adopt reasonable driving behaviors, thereby significantly improving the driving experience and ensuring road safety. Existing methods for optimizing rural road environments mainly rely on expert knowledge, have low automation degrees, and are limited in efficiency and accuracy. Therefore, this study aims to propose an intelligent optimization method for rural road environments by using image generation technology. Using environment images from a naturalistic driving dataset, the area and location information of semantic components (e.g., lane markings, vegetation, guardrails, and traffic signs) in rural road environments are extracted, and their impacts on driving speed are analyzed based on explainable machine learning (extreme gradient boosting (XGBoost) and Shapley additive explanations (SHAP)). These impacts are then utilized to determine how to adjust and optimize the road environment components at appropriate locations (i.e., obtain the optimization scheme). Then, a novel image generation technique, Diffusion model, is employed to establish an intelligent optimization method, which can directly generate optimized images of rural road environments. Compared with traditional manual mapping and other popular image generation algorithms such as CycleGAN, the method proposed in this study has the advantages of high efficiency, labor saving, and superior image generation quality. This study can facilitate the design and optimization of rural road environments and enhance rural road safety in a more intelligent way.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"21 ","pages":"Pages 208-227"},"PeriodicalIF":4.8,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147556808","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":"Prediction of LWST values using ML and ANN techniques from frcition and texture measuring devices based on long term field data","authors":"Mohammad Ahmad Alsheyab ,&nbsp;Mohammad Ali Khasawneh ,&nbsp;Danah Hussain Alotaibi ,&nbsp;Nayeemuddin Mohammed ,&nbsp;Ahmad Ali Khasawneh","doi":"10.1016/j.ijtst.2025.01.015","DOIUrl":"10.1016/j.ijtst.2025.01.015","url":null,"abstract":"<div><div>Given the cost, time requirements, and limited accessibility of locked wheel skid trailer (LWST) testing, this research explores alternative approaches to predicting skid number (SN) using more affordable and readily available devices. These alternatives offer quicker results, which is particularly relevant given the standardized nature of SN measurements worldwide. The study focuses on predicting the SN generated by the LWST test through analyzing data from dynamic friction tester (DFT), British pendulum tester (BPT), and circular texture meter (CTM) using statistical and machine learning (ML) techniques. The research includes a thorough assessment of various prediction methods and factors influencing SN accuracy, including strategies for handling missing data. Prediction models employ multiple linear regression (MLR), support vector machine (SVM), artificial neural network (ANN), and ensemble bagged tree (EBT) techniques, utilizing predictors such as dynamic friction number at 20 km/h (DFT20), dynamic friction number at 64 km/h (DFT64), British pendulum number (BPN), and mean profile depth (MPD). The development of forty-eight models, including full, reduced, and individual predictor models, involved employing data imputation methods and stepwise regression. Significant correlations were observed among friction parameters, with DFT20 showing the highest correlation with SN, while MPD exhibited the lowest. Following data imputation, notable enhancements in BPN’s correlation were noted. The study emphasizes the superiority of full models in SN prediction accuracy, with EBT models, especially those enhanced by data imputation, demonstrating outstanding performance. Statistical simulations confirmed the reliability of these models, indicating minimal outliers, overfitting, and high accuracy in SN estimation. The prioritization of DFT over BPT and CTM is highlighted, with the potential for further exploration of devices to improve prediction reliability.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"21 ","pages":"Pages 228-255"},"PeriodicalIF":4.8,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147556810","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":"Quantum-omni: a quantum computing and GPT-4o solution for camel-vehicle vollisions","authors":"Samer Abaddi","doi":"10.1016/j.ijtst.2025.02.002","DOIUrl":"10.1016/j.ijtst.2025.02.002","url":null,"abstract":"<div><div>Camel-vehicle collisions (CVCs) have been a major cause of public safety hazards in the Gulf countries, in particular, the United Arab Emirates (UAE) and Saudi Arabia. It is similar to deer-vehicle collisions in the United States and kangaroo-vehicle collisions in Australia. When it comes to road accidents, each millisecond of early warning/detection matters, potentially transforming a life-threatening situation into a manageable incident. Therefore, this study aims to mitigate CVCs by integrating quantum computing and Integrating generative pretrained transformer-4 omni (GPT-4o) into autonomous vehicles (AVs). Environmental data were sourced through high-accuracy sensors in conjunction with quantum algorithms and GPT-4o modules handling the processing through a multi-phase approach. The integration allowed for enhanced detection, tracking, and decision-making regarding camel movements. Heatmaps revealed heightened camel activity during low-visibility nighttime conditions and seasonal peaks, particularly during the breeding season. The quantum-enhanced algorithms achieved a mean detection accuracy of 95% and tracking precision of 92%, with computational speeds 10 times that of classical methods. GPT-4o vision modules further improved object detection accuracy to 98.7%, securing 0.97 s as an early warning to the AV’s braking system. This innovative approach offers a novel paradigm in AV technology, setting new standards for safety and efficiency in transportation. Future GPT-5 models can be used in AVs and with sophisticated technologies for safer driving and wildlife protection. The results obtained from this study go beyond updating AV safety technology, opening avenues for application in urban planning and real-time hazard detection systems.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"21 ","pages":"Pages 306-321"},"PeriodicalIF":4.8,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147556812","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 YOLO-based network with dynamic feature pyramid for multi-scale bridge surface defect detection","authors":"Liming Liu,&nbsp;Hongren Gong,&nbsp;Yuhui Zhou,&nbsp;Achu Zhou,&nbsp;Lin Cong","doi":"10.1016/j.ijtst.2025.01.004","DOIUrl":"10.1016/j.ijtst.2025.01.004","url":null,"abstract":"<div><div>Bridge surface defect detection is critical for guaranteeing transportation safety and maintenance planning. With the innovation of image acquisition technology and computer vision science, deep learning (DL) methods have revolutionized the ability to identify specific surface defects on bridges promptly. Bridge surface defect often exhibits different postures, appearing at different positions and scales in the image. However, the existing models need to be more satisfactory in detecting those surface defects at different scales, making them more challenging to detect and localize accurately by the models. To address this challenge, we proposed a more streamlined model, you only look once for bridge surface defect (YOLO-BSD), significantly improving the model performance on defect detection. We thoroughly evaluated our detection model’s effectiveness using a self-made dataset, and benchmarked its performance against other leading-edge models in the field. The experiments and results indicated that our proposed YOLO-BSD model surpasses current state-of-the-art (SOTA) algorithms in accuracy and operational efficiency, achieving a mean average precision (MAP) score of 0.892. Ablation experiments further demonstrated the effectiveness of our improvements, resulting in a total 6.6 <span><math><mrow><mo>%</mo></mrow></math></span> increase in MAP. Our proposed model demonstrated superior detection capabilities and excelled in processing speed, achieving an impressive inference rate of 213 (1 000/4.7 ms) FPS, with only 10.6 G FLOPs and 12 MB parameters.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"21 ","pages":"Pages 51-60"},"PeriodicalIF":4.8,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147557222","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":"Synergistic effects of natural fibres and agro-waste ash on the engineering and sustainability of stone-matrix asphalt mixes","authors":"P.K. Akarsh ,&nbsp;Shriram Marathe ,&nbsp;Harsimran Kaur Sapal ,&nbsp;Akshaya Krishna N.","doi":"10.1016/j.ijtst.2025.02.010","DOIUrl":"10.1016/j.ijtst.2025.02.010","url":null,"abstract":"<div><div>This study investigates the use of non-traditional natural fibres, specifically sisal fibres (SFs) and coconut coir fibres (CCFs), in stone mastic asphalt (SMA) mixtures. The objective was to evaluate the optimal binder content, assess Marshall properties, and investigate drain-down, indirect tensile strength (ITS), fatigue, and rutting characteristics of the SMA mixes. Additionally, the study explores the use of sugarcane bagasse ash (SBA), an agro-waste, as a substitute for ordinary portland cement (OPC), aiming to promote sustainability and waste management optimization. The research identified the optimal SMA mix with a 0.30% fibre dosage and 10% SBA, demonstrating favorable mechanical properties with Marshall stability and tensile strength ratio (TSR) exceeding 90%, alongside satisfactory rutting and fatigue performance. The results showed that SF and CCF provided comparable, or even superior, performance to traditional cellulose fibres (CFs), positioning them as sustainable alternatives for pavement construction. Further, a life cycle cost analysis (LCCA) was conducted on conventional and modified SMA mixes, revealing substantial long-term economic benefits. Although SMA mixes incurred slightly higher initial costs, their superior durability and reduced maintenance needs resulted in a 13.6% cost reduction for SMA-CCF and 11.1% for SMA-SF over a 20-year period. Environmental assessments confirmed that substituting synthetic fibres and OPC with SFs, CCFs, and SBA substantially lowered carbon emissions and enhanced sustainability, with reductions in global warming potential (GWP) of up to 50%. These findings highlight the potential of natural fibres and SBA in reducing costs and environmental impacts, offering a sustainable solution for future pavement construction.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"21 ","pages":"Pages 432-448"},"PeriodicalIF":4.8,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147556801","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":"Machine learning framework for predicting urban road speed profiles and uncertainty","authors":"Eduard Gañan-Cardenas ,&nbsp;J. Isaac Pemberthy-R. ,&nbsp;Marta Lucía Suárez-Gómez ,&nbsp;John R. Ballesteros ,&nbsp;John W. Branch-Bedoya","doi":"10.1016/j.ijtst.2025.02.009","DOIUrl":"10.1016/j.ijtst.2025.02.009","url":null,"abstract":"<div><div>Road speed serves as a vital indicator for traffic managers and road designers due to its correlation with congestion, safety, and pollutant emissions. Traditional speed models focus mainly on predicting the 85th percentile of road speed distribution under free-flow conditions, primarily in rural areas, often overlooking speed variability. This study proposes a machine learning-based framework to predict real conditions on urban road segments and construct prediction intervals for assessing uncertainty. Utilizing a dataset of 650 road segments, this work covers various roadway configurations. Compared to existing models, the proposed framework demonstrates superior performance in accuracy and coverage metrics. It achieves an explained variance with the coefficient of determination (<em>R</em>²) of 74.30%, the root mean square error (RMSE) of 6.89 km/h, and the mean absolute percentage error (MAPE) of 19.93%. The prediction interval boasts a coverage level of 90.85%, exceeding the nominal value of 90%, and exhibits the lowest mean amplitude, enhancing its informativeness. Key variables influencing speed profile prediction include time stamps (hour and day), road classification, boundary conditions, density of speed bumps, and median strip presence. Notably, a signalized intersection reduces speed by approximately 27%, while the presence of a median increases it by about 6.1%.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"21 ","pages":"Pages 414-431"},"PeriodicalIF":4.8,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147556802","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":"Construction of airport digital runway based on in-situ sensing data","authors":"Jianming Ling ,&nbsp;Zhaoyang Li ,&nbsp;Fan Yang ,&nbsp;Libin Han ,&nbsp;Jiake Zhang","doi":"10.1016/j.ijtst.2025.01.010","DOIUrl":"10.1016/j.ijtst.2025.01.010","url":null,"abstract":"<div><div>Performance evaluation of facilities in flight area is a key factor affecting the safety of airport, and monitoring the infrastructures in real time and reporting the performance of the airport runway are critical for ensuring the airport in safe condition. However, traditional way of evaluating the airport infrastructure needs to shutdown the traffic, and cannot report the performance of airport infrastructure in real time. Nowadays, many airport authorities are trying to use multiple sensors to measure the properties of airport infrastructure in real time, but the performance evaluation parameters for the airport runway are still needed. This work proposed an airport digital runway construction method based on in-situ sensing data for potentially developing the airport runway performance evaluation parameters in a timely format. The method consists of obtaining real-time multi-source state information of the runway through sensors, analyzing the runway evaluation indexes through the measured data, as well as the architecture and main functions of the digital runway system. The airport digital runway, constructed by using 3Ds Max + DATAV, can provide the performance information of runway and predict the potential risks of runway, which helps the airport runway management department to better understand the performance of airport runway. This result has been piloted at Chengdu Tianfu International Airport and greatly enhanced the ability to manage safety risks.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"21 ","pages":"Pages 144-156"},"PeriodicalIF":4.8,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147557219","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":"Examining causal factors of traffic instability using traffic flow and driving behavior data","authors":"Haiyi Yang ,&nbsp;Xiaohua Zhao ,&nbsp;Sen Luan ,&nbsp;Ying Yao ,&nbsp;Hang Qi","doi":"10.1016/j.ijtst.2025.01.009","DOIUrl":"10.1016/j.ijtst.2025.01.009","url":null,"abstract":"<div><div>Developing proactive prevention measures before accidents is a powerful means of kerbing traffic accidents. Many studies have confirmed that the state of the traffic would fluctuate significantly before an accident, representing as traffic instability. This study develops a traffic instability index (TII) to evaluate and identify factors affecting traffic instability, utilizing non-negative matrix factorization (NMF) based on aggressive driving behaviors (ADBs) and traffic flow data. Machine learning algorithms and partial dependency plots (PDPs) reveal that traffic status significantly influence TII, followed by road attributes. The findings show that high TII is linked to more fatal accidents and that traffic instability is adversely impacted by increased speed differences, traffic volume, and the number of entrances and exits but reduced proportion of trucks and median openings. Vehicle type mix has a non-linear effect on TII. Additionally, median openings mitigate, while entrances and exits exacerbate the adverse effects of vehicle mix and truck proportion on instability.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"21 ","pages":"Pages 125-143"},"PeriodicalIF":4.8,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147557220","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":"Comparison of approaches to assessing ballast layer contamination using ground penetrating radar","authors":"Vladimir Shapovalov,&nbsp;Vitaly Arkhipov,&nbsp;Maksim Okost,&nbsp;Andrey Morozov","doi":"10.1016/j.ijtst.2025.02.001","DOIUrl":"10.1016/j.ijtst.2025.02.001","url":null,"abstract":"<div><div>The railway ballast layer plays an important role in the functioning of the entire track structure as a whole, provides the connection of the rail-sleeper grid with the roadbed and its stability in the longitudinal and transverse directions. An increase in the contamination of crushed stone worsens the characteristics of the ballast layer, leading to higher operating costs. The study is devoted to the comparison of various approaches for determining contamination using ground penetrating radar (GPR). Several basic GPR attributes used to assess the contamination of the ballast layer are considered and compared on several operating sections of the railway track. An approach based on a multiple linear regression model is proposed, simultaneously considering several attributes, which allows for increasing the accuracy of contamination estimation .</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"21 ","pages":"Pages 286-305"},"PeriodicalIF":4.8,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147557211","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":"Optimal seat occupancy rate of customized bus services considering in-vehicle infection risk cost during public health emergencies","authors":"S. Sun ,&nbsp;Shuxian Hao ,&nbsp;Fengtao Ding ,&nbsp;Yiqi Cai","doi":"10.1016/j.ijtst.2025.01.012","DOIUrl":"10.1016/j.ijtst.2025.01.012","url":null,"abstract":"<div><div>Customized bus (CB), offering personalized routes and reserved seat arrangements, meets the diverse travel needs of passengers. However, the usage of public transit drops significantly during public health emergencies due to concern of in-vehicle infection risks. To enhance the competitiveness of CB during public health emergencies by raising profits and maintaining an acceptable level of in-vehicle infection risk, this study proposes a bi-level seat occupancy rate optimization model which integrates the Wells-Riley (W-R) equation to measure in-vehicle infection risks. The upper-level model optimizes seat occupancy to maximize profits while penalizing the expected number of infected CB passengers after traveling. The lower-level model is a logit mode choice model considering infection risk cost. Numerical examples are conducted to explore model properties. Results indicate that while shorter average travel route is generally considered beneficial, longer average CB travel route can actually help control in-vehicle infection rates in certain circumstances. Moreover, during severe outbreaks, the risk of infection during travel does not necessarily increase with the severity of the outbreak, because passengers tend to place a greater emphasis on personal protection. Furthermore, the results suggest that optimizing the CB seat occupancy rate is essential in the context of epidemic prevention and control. Additionally, when the performance of bus services is relatively good, CB has potential for profit growth during public health emergencies.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"21 ","pages":"Pages 173-190"},"PeriodicalIF":4.8,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147556804","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}