International Journal of Transportation Science and Technology最新文献

{"title":"Characterization of binder and asphalt mixture modified with waste toner","authors":"Taisir Khedaywi,&nbsp;Madhar Haddad,&nbsp;Hashem Al-Masaeid,&nbsp;Islam Abu Mharib,&nbsp;Shaima Hawari","doi":"10.1016/j.ijtst.2025.05.005","DOIUrl":"10.1016/j.ijtst.2025.05.005","url":null,"abstract":"<div><div>Incorporating waste materials as additives in road and highway construction offers significant economic and environmental advantages. This study utilizes waste toner (WT) as an additive in binder and asphalt mixture at varying percentages (0%, 5%, 10%, 15%, 20%) of the binder’s volume. Standard asphalt binder tests for penetration, ductility, softening point, flash and fire points, and specific gravity are conducted. Additionally, Superpave performance grading (PG) tests are carried out with devices such as rolling thin-film oven (RTFO), pressure aging vessel (PAV), dynamic shear rheometer (DSR), and bending beam rheometer (BBR). Modified asphalt mixtures undergo tests for Marshall stability and flow, dynamic creep, and fatigue (indirect tensile modulus test). The results reveal tthat, when the WT content increases, penetration and ductility decrease, while specific gravity, softening point, flash point, fire point, and rotational viscosity (RV) increase. The DSR test indicates an enhancement in rutting resistance for asphalt-WT binders. The dynamic creep test demonstrates an increase in resilient modulus and creep stiffness compared with conventional asphalt mixtures, resulting in a reduction in cumulative strain and permanent rutting values. The fatigue test shows an improvement in pavement life, thanks to higher resilient modulus values and lower total horizontal recoverable deformation, enhancing fatigue cracking resistance in the modified asphalt mixture. The PG of the asphalt binder with 5% and 10% WT is 82–22. Also, the final PG of the asphalt binder with 15% and 20% WT content is 82–16, which is suitable for use in high-temperature regions. Therefore, incorporating an appropriate amount of WT into binder significantly enhances road pavement performance, especially in high-temperature regions. Additionally, this research offers a promising alternative recycling approach for WT, leading to substantial environmental benefits. Thus, the process can be deemed both feasible and viable.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"22 ","pages":"Pages 424-446"},"PeriodicalIF":5.1,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148545068","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Understanding the influence of affective and restorative potential of built environments on intention and walking behavior","authors":"Fatemeh Sadeghi,&nbsp;Mansour Hadji Hosseinlou,&nbsp;Mahdi Yazdanpanah","doi":"10.1016/j.ijtst.2025.04.001","DOIUrl":"10.1016/j.ijtst.2025.04.001","url":null,"abstract":"<div><div>The increase in motor trips and the decrease in physical activity lead to obesity, which has become the main concern of many societies. Promoting walking on school trips can provide an inclusive opportunity to increase physical activity and, therefore, the benefits of walking in a community. Gender-based analysis of walking for transportation in developing countries such as Iran is rare. Also, it is possible to see significant differences between groups of girls and boys in different cities, as there is gender segregation in Iranian schools and cultural and social diversity among Iranian societies. To achieve this objective, we propose a comprehensive model that utilizes the theory of planned behavior (TPB) along with structural equation modeling (SEM) to analyze the factors influencing secondary school students’ choice to walk during school trips. We collected data from 540 students in Tehran and Amol using an internet questionnaire to compare their intentions in two different residences. The research results show that in the cities of Tehran and Amol, each of the considered variables, such as environmental concern and artificial environment, has different effects on walking behavior. The final section of a web-based questionnaire, which evaluates the restorative and encouraging potentials of an environment after a virtual walk in one of five urban areas in Tehran and Amol, yields these results. Therefore, a significant finding of this research indicates that different urban environments have distinct restorative and encouraging potentials, which in turn influence the intention to walk. Furthermore, a combination of natural and built environments creates the most encouraging environment, positively influencing students’ motivation and desire to walk. This environment is pleasant to look at and safe to walk in.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"22 ","pages":"Pages 177-194"},"PeriodicalIF":5.1,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148573509","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimized deep learning for pedestrian safety in autonomous vehicles","authors":"Wajdi Farhat,&nbsp;Olfa Ben Rhaiem,&nbsp;Hassene Faiedh,&nbsp;Chokri Souani","doi":"10.1016/j.ijtst.2025.04.002","DOIUrl":"10.1016/j.ijtst.2025.04.002","url":null,"abstract":"<div><div>This study focuses on enhancing pedestrian detection for autonomous driving and intelligent surveillance systems, where challenges like complex backgrounds, obstructions, and small target sizes can hinder accuracy. The researchers optimized the YOLOv8 model by redesigning its neck structure using the bidirectional feature pyramid network (BiFPN ), reducing parameters, size, and computational load. They also integrated coordinate attention (CA) into the spatial pyramid pooling-fast (SPPF) layer for improved localization and feature integration. Additionally, the complete intersection over union IoU (CIoU) loss function was applied to refine anchor regression predictions for better edge positioning accuracy. Experimental evaluations on the KITTI, Caltech Pedestrian, and EuroCity CityPersons datasets demonstrate that PD-YOLOv8 achieves superior detection performance compared with state-of-the-art methods. The findings underscore the model’s robustness across diverse environmental conditions, highly-lighting its potential for real-world deployment in autonomous vehicle perception and intelligent surveillance applications.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"22 ","pages":"Pages 195-212"},"PeriodicalIF":5.1,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148573508","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Electric vehicles vs. internal combustion engine vehicles: a comparative study of crashes involving vulnerable road users","authors":"Jiahe Ling,&nbsp;Xiaodong Qian,&nbsp;Konstantina Gkritza","doi":"10.1016/j.ijtst.2025.03.006","DOIUrl":"10.1016/j.ijtst.2025.03.006","url":null,"abstract":"<div><div>Powered by electric engines, electric vehicles (EVs) exhibit unique dynamic characteristics that may lead to different crash characteristics and outcomes compared with traditional internal combustion engine vehicles (ICEVs). This might be particularly true for vulnerable road users (VRUs), such as pedestrians and cyclists. Motivated by these concerns, this paper delves into the comparative analysis of crashes involving EVs and VRUs, exploring how crash characteristics and injury severities differ from those involving VRUs and ICEVs. Employing statistical testing and binary probit regression analyses, this study analyzes crash data from Chicago spanning from 2015 to 2022. Spatial and temporal constraints were applied to filter ICEV crashes, ensuring similar environmental conditions and VRU exposure for the considered crashes. Innovatively, this study supplements traditional police crash reports with Google street view (GSV) images and employs neural network models to uncover previously unreported environmental variables at crash scenes. The results reveal both similarities and disparities in the characteristics of crash involved VRUs between EVs and ICEVs. However, significant differences in factors, such as VRU type (pedestrians or cyclists), hit-and-run incidents, damage level, crash hour, crash weekday, weather conditions, and road surface conditions, along with the influence of season and road surface condition on injury severity, were observed between EVs and ICEVs. These distinctions may be attributed to driver demographics, vehicle design, and spatial and temporal usage patterns. These insights can guide the development of safety regulations for EVs and aid in devising specific safety measures and policies for VRUs, including pedestrians and cyclists.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"22 ","pages":"Pages 126-140"},"PeriodicalIF":5.1,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148545074","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The cooperative inspection routing problem for urban environmental management","authors":"Hengzhi Yuan,&nbsp;Siqi Wan,&nbsp;Huaqiao Mu,&nbsp;Chi Xie,&nbsp;Ke Han","doi":"10.1016/j.ijtst.2025.04.004","DOIUrl":"10.1016/j.ijtst.2025.04.004","url":null,"abstract":"<div><div>Urban environmental management against air pollution is of critical importance to public health. Despite the proliferation of ubiquitous air quality sensors and advancement of information systems, an integral part of urban environmental management in China involves routine inspections of pollution hotspots in the number of thousands distributed in the city. Departing from this particular scenario, this work proposes a routing problem termed as the cooperative inspection routing problem (CIRP) that systematically integrates subset selection with mixed mandatory and elective nodes, priority heterogeneity across inspection targets, soft time windows through time-sensitive scoring with decay functions, and synchronized visits for mandatory nodes for the first time. This complex problem is formulated as a mixed integer programming model and solved using a customized adaptive large neighborhood search (ALNS) algorithm in a timely fashion to accommodate real-time routing in response to pollution hazards. Based on the real Chengdu pollution source database, 112 test instances were established to examine the performance of the ALNS algorithm. On small-scale instances, the ALNS algorithm achieved solutions close to or even equivalent to those obtained by CPLEX. On large-scale instances, CPLEX can no longer obtain feasible solutions within the 1-hour time limit, while the proposed algorithm can still obtain satisfactory solutions within 10 to 100 s.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"22 ","pages":"Pages 231-246"},"PeriodicalIF":5.1,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148545083","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Investigating safety implications of median U-turn (MUT) intersections based on dilemma zone and critical gap analysis","authors":"Syed Ibrahim Kamili,&nbsp;Tazim Ameen,&nbsp;Hazim Arshad Wani,&nbsp;Abdullah Ahmad","doi":"10.1016/j.ijtst.2025.04.006","DOIUrl":"10.1016/j.ijtst.2025.04.006","url":null,"abstract":"<div><div>Median U-turn (MUT) intersections present a distinctive configuration where certain vehicular movements, such as right-turns and crossings from the primary road or secondary crossroads, are achieved through indirect, downstream U-turn maneuvers. The U-turning maneuver is governed by the gap acceptance behavior of the U-turning vehicle (UTV). A certain range of gaps offered by the mainstream approaching vehicle (MAV) can create a dilemma for UTV drivers when deciding whether to accept or reject the offered gap. This decision-making juncture is termed as the “dilemma zone”. This study endeavors to investigate the potential risk associated with the U-turning maneuver in consideration with the dilemma zone boundaries and spatial critical gaps at MUT intersections within Srinagar city. Cumulative distribution method (CDM) and binary logit method (BLM) were used to evaluate the dilemma zone boundaries and the spatial critical gaps (SCGs) at the selected MUT sites. The risk was quantified using a novel term “potential risk ratio (PRR)”. The study discerned that the U-turning maneuver of two wheelers posed a higher potential risk than other classes of UTVs, while the U-turning maneuver of the light commercial vehicles (LCVs) posed the least potential risk. This behavior was invariably observed at all the selected sites. These insights hold the potential to guide strategies and interventions for enhancing the safety and efficiency of such intersections.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"22 ","pages":"Pages 263-281"},"PeriodicalIF":5.1,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148545085","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Erosion-enhanced rain optimization algorithm for efficient blood bag transport in multimodal healthcare logistics","authors":"Tejinder Singh Lakhwani,&nbsp;Yerasani Sinjana,&nbsp;Anuj Pal Kapoor","doi":"10.1016/j.ijtst.2025.05.002","DOIUrl":"10.1016/j.ijtst.2025.05.002","url":null,"abstract":"<div><div>The erosion-enhanced rain optimization algorithm (ROA) is introduced as an advanced framework to address pressing challenges in multimodal healthcare logistics, focusing on the efficient and timely delivery of critical supplies such as blood bags. This study integrates dynamic erosion penalties and predictive machine learning models into the ROA, enabling real-time adaptation to route degradation, traffic congestion, and environmental variability. The algorithm balances operational efficiency, sustainability, and resilience by utilizing trucks for long-distance transport, and drones for last-mile delivery. The predictive component, with metrics such as mean squared error (MSE) (0.030 1), root mean squared error (RMSE) (0.173 6), and coefficient of determination (<em>R</em>₂) (0.839 3), forecasts route degradation trends, supporting preemptive maintenance and rerouting strategies to ensure consistent performance. Validated using real-world datasets from Delhi, India, under conditions like no-fly zones, adverse weather, and high traffic density, the ROA demonstrated remarkable performance. It reduced delivery times by 9%, improved drone energy efficiency by 15%, and achieved a 12%–18% reduction in carbon emissions compared with static models. Maintenance-based erosion recovery reduced overall route degradation by 8%, reinforcing the system’s adaptability and long-term sustainability. These results underscore the model’s capacity to handle complex and dynamic healthcare logistics networks effectively. This study highlights the ROA’s unique contributions, including its dynamic adaptation mechanisms and predictive insights, and focuses on balancing efficiency with environmental sustainability. Its scalability and versatility extend its application potential beyond healthcare logistics to other industries facing real-time logistical challenges.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"22 ","pages":"Pages 355-382"},"PeriodicalIF":5.1,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148545088","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Adaptive federated learning framework for predicting EV charging stations occupancy","authors":"Khaled Hallak,&nbsp;Oudom Kem","doi":"10.1016/j.ijtst.2025.04.007","DOIUrl":"10.1016/j.ijtst.2025.04.007","url":null,"abstract":"<div><div>Forecasting the occupancy of electric vehicle (EV) charging stations is crucial for addressing key challenges in e-mobility, including charging inefficiency, traffic congestion, and drivers’ difficulty in locating available stations. Recent studies on predicting charging station occupancy have predominantly employed conventional centralized machine learning models. However, these models struggle to adapt to evolving data streams, limiting their accuracy and practical applicability. Furthermore, centralized approaches exacerbate these limitations by conflicting with privacy requirements, as they necessitate sharing sensitive data from charging stations and users. To address these limitations, this study introduces a novel federated learning framework designed to collaboratively predict EV charging station occupancy by leveraging data from all participating stations without sharing any raw data. The framework addresses critical challenges, including concept drift, data heterogeneity among clients, and model generalization. It clusters stations with similar drift patterns and leverages personalized models, updated using incremental learning (IL), to ensure adaptive and precise forecasting. This adaptability allows the system to respond to dynamic environments characterized by changing traffic patterns, user behaviors, and station utilization trends. Three datasets with diverse characteristics were used to validate the proposed framework, demonstrating its robustness, adaptability, and scalability in improving forecasting accuracy. This work provides a robust, privacy-preserving, and scalable framework to enhance the reliability and efficiency of EV infrastructures, promoting broader adoption of sustainable transportation.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"22 ","pages":"Pages 282-296"},"PeriodicalIF":5.1,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148545090","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Modeling response time and hazard identification in a video-based hazard perception test for car drivers","authors":"T.K. Akshay,&nbsp;Nishant Mukund Pawar,&nbsp;Kirti Mahajan","doi":"10.1016/j.ijtst.2025.02.012","DOIUrl":"10.1016/j.ijtst.2025.02.012","url":null,"abstract":"<div><div>This study aimed to evaluate hazard perception ability of car drivers by analyzing response time and hazard identification performance measures. A video-based test method was selected to evaluate hazard perception ability of car drivers. Initially, a field study was conducted on three random days to collect videographic data for capturing maximum possible hazardous traffic events. Time headway and critical speed were considered to differentiate traffic events as hazardous and non-hazardous. Finally, thirty short video clips consisting of hazardous and non-hazardous traffic events were created for video-based hazard perception test. The response time and hazard identification data of 120 car drivers were collected and analyzed using parametric survival regression and logistic regression, respectively. The parametric survival regression and logistic regression results showed that drivers with greater driving experience and no crash history responded more quickly and identified hazardous traffic events more accurately than drivers with less driving experience or a crash history. The model results showed positive influence of higher education on hazard perception skill, indicating that education provides a sense of responsibility and improves the level of understanding related to safety risks while driving. The overall results obtained are consistent with the previous studies, indicating that the test is a valid measure of hazard perception skill. It can be concluded that the video-based test can be adopted to evaluate hazard perception ability, and with further research, it may be utilized to develop training modules for improving hazard perception skill of drivers.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"22 ","pages":"Pages 61-74"},"PeriodicalIF":5.1,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148545058","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A robust deep learning-based system for pedestrian-aware collision prevention in autonomous vehicles","authors":"Wajdi Farhat,&nbsp;Marwa Guizani,&nbsp;Olfa Ben Rhaiem,&nbsp;Radhia Zaghdoud,&nbsp;Hassene Faiedh,&nbsp;Chokri Souani","doi":"10.1016/j.ijtst.2025.05.007","DOIUrl":"10.1016/j.ijtst.2025.05.007","url":null,"abstract":"<div><div>Pedestrian collisions remain a critical concern in road safety research due to pedestrians’ heightened vulnerability and the substantial impacts on road networks and public healthcare systems. These incidents often lead to significant traffic disruptions, emphasizing the importance of pedestrian-focused road design. In dynamic urban environments, understanding street layouts and pedestrian behavior is essential for improving safety. In response to these challenges, this research presents an innovative and efficient automated collision avoidance system, leveraging an enhanced YOLOv9 architecture to achieve high accuracy and real-time performance. The proposed system is designed to detect and predict potential pedestrian collisions, while delivering proactive accident warnings and autonomously initiating the automatic emergency braking (AEB) mechanism when required, thereby effectively mitigating collision risks. By analyzing key behavioral and environmental factors including pedestrian exposure, jaywalking, intersection crowding, and hazardous turning locations, the system employs a proactive methodology aimed at enhancing pedestrian safety. Experimental evaluations using the KITTI and CityPersons datasets demonstrate the system’s efficacy, achieving precision rates of 98.79% and 96.62%, respectively, and [email protected] scores of 96.21% and 94.83%. These results underscore the system’s capability to deliver high accuracy, fast inference, and proactive accident mitigation across diverse urban scenarios.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"22 ","pages":"Pages 447-469"},"PeriodicalIF":5.1,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148545069","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}